A European Excellence Centre for Media, Society and Democracy

Livrables

Intermediate report on dissemination and communication activities
Intermediate toolset for robust, explainable, fair, and privacy-preserving AI
Overview & Analysis of the AI Policy Initiatives in EU level

Overview Analysis of the AI Policy Initiatives in EU level

Initial call documentation
Second generation of Human- and Society-centered AI algorithms
Initial White Paper on the social, economic, and political impact of media AI Technologies

Initial White Paper on the social economic and political impact of media AI Technologies

Initial approaches for decentralised and high-performance learning

Initial approaches for decentralised and highperformance learning Contains outputs of T34 T35 T38

Report on Computationally Demanding Deep Learning
IAIDA organisation and curriculum design
AI technologies and applications in media: State of Play, Foresight, and Research Directions

AI technologies and applications in media State of Play Foresight and Research Directions

Initial outcomes of new learning paradigms research

Initial outcomes of new learning paradigms research Contains outputs of T31 T33 T37

Analytics on the submitted proposals
AI4Media Strategic Research Agenda

The AI4Media Strategic Research Agenda lays out the strategic plan for AI4Media's R&I activities, presenting the main research themes to be tackled by the consortium and the potential impact of this research.

Initial analysis of the legal and ethical framework of trusted AI
Initial report on dissemination and communication activities
Final analysis of the legal and ethical framework of trusted AI
Pilot Policy Recommendations for the use of AI in the Media Sector
Report on European AI branding and excellence spreading
Initial report on Multimedia Production
Initial report on Multimedia Summarisation and Analysis
Initial toolset for robust, explainable, fair, and privacy-preserving AI

Initial toolset for robust explainable fair and privacypreserving AI

Final White Paper on the social, economic, and political impact of media AI Technologies
Report on Policy for Content Moderation
Intermediate outcomes of new learning paradigms research

Intermediate outcomes of new learning paradigms research: Update of D3.1, including additionally inputs from T3.2 and T3.6.

First generation of Human- and Society-centered AI algorithms

First generation of Human and Societycentered AI algorithms

Prototype platform for AI dataset benchmarking
Extended version of the integration result with the AI-On-Demand-Platform
Integration plan and initial version of the integration result with the AI-On-Demand-Platform

Integration plan and initial version of the integration result with the AIOnDemandPlatform

Final platform for AI dataset benchmarking

Initial Data Management Plan

Publications

Hebbian semi-supervised learning in a sample efficiency setting

Auteurs: Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Publié dans: Neural Networks, Numéro 143, 2021, Page(s) 719-731, ISSN 0893-6080
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.neunet.2021.08.003

Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th VBS

Auteurs: Jakub Lokoč, Stelios Andreadis, Werner Bailer, Aaron Duane, Cathal Gurrin, Zhixin Ma, Nicola Messina, Thao-Nhu Nguyen, Ladislav Peška, Luca Rossetto, Loris Sauter, Konstantin Schall, Klaus Schoeffmann, Omar Shahbaz Khan, Florian Spiess, Lucia Vadicamo, Stefanos Vrochidis
Publié dans: Multimedia Systems, Numéro 88, 2023, ISSN 0942-4962
Éditeur: Springer Verlag
DOI: 10.1007/s00530-023-01143-5

100-Driver: A Large-scale, Diverse Dataset for Distracted Driver Classification

Auteurs: Jing Wang; Wenjing Li; Fang Li; Jun Zhang; Zhongcheng Wu; Zhun Zhong, Nicu Sebe
Publié dans: IEEE Transactions on Intelligent Transportation Systems, Numéro 24, 2023, ISSN 1524-9050
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tits.2023.3255923

Quasi-Equilibrium Feature Pyramid Network for Salient Object Detection

Auteurs: Yue Song, Hao Tang, Mengyi Zhao, Nicu Sebe, Wei Wang
Publié dans: IEEE Transactions on Image Processing, Numéro 31, 2022, Page(s) 7144 - 7153, ISSN 1057-7149
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tip.2022.3220058

Multi-Camera Vehicle Counting Using Edge-AI

Auteurs: Luca Ciampi, Claudio Gennaro, Fabio Carrara, Fabrizio Falchi, Claudio Vairo, Giuseppe Amato
Publié dans: Expert Systems with Applications, Numéro 207, 2022, ISSN 0957-4174
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.eswa.2022.117929

Reassembling digital archives—strategies for counter-archiving

Auteurs: Tobias Blanke
Publié dans: Humanities and Social Sciences Communications, Numéro 11, 2024, ISSN 2662-9992
Éditeur: Springer Nature Limited
DOI: 10.1057/s41599-024-02668-4

Local and Global GANs With Semantic-Aware Upsampling for Image Generation

Auteurs: Hao Tang, Ling Shao, Philip H.S. Torr, Nicu Sebe
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 45, 2022, Page(s) 768 - 784, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2022.3155989

An annotated video dataset for computing video memorability

Auteurs: Rukiye Savran Kiziltepe, Lorin Sweeney, Mihai Gabriel Constantin, Faiyaz Doctor, Alba García Seco de Herrera, Claire-Héléne Demarty, Graham Healy, Bogdan Ionescu, Alan F. Smeaton
Publié dans: Data in Brief, Numéro 39, 2023, Page(s) 107671, ISSN 2352-3409
Éditeur: Elsevier BV
DOI: 10.1016/j.dib.2021.107671

solo-learn: A Library of Self-supervised Methods for Visual Representation Learning

Auteurs: Victor G. Turrisi da Costa; Enrico Fini; Moin Nabi; Niculae Sebe; Elisa Ricci
Publié dans: Journal of Machine Learning Research, Numéro 23, 2022, ISSN 1533-7928
Éditeur: JMLR, Inc.
DOI: 10.5281/zenodo.6363321

(Compress and Restore) N : a Robust Defense Against Adversarial Attacks on Image Classification

Auteurs: Claudio Ferrari; Federico Fecattini; Leonardo Galteri; Alberto Del Bimbo
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, 2022, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3524619

Source-Free Open Compound Domain Adaptation in Semantic Segmentation

Auteurs: Yuyang Zhao, Zhun Zhong, Zhiming Luo, Gim Hee Lee, Nicu Sebe
Publié dans: IEEE Transactions on Circuits and Systems for Video Technology, Numéro 32, 2022, Page(s) 7019 - 7032, ISSN 1051-8215
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcsvt.2022.3179021

Learning to count biological structures with raters’ uncertainty

Auteurs: Luca Ciampi, Fabio Carrara , Valentino Totaro, Raffaele Mazziotti Leonardo Lupori, Carlos Santiago, Giuseppe Amato, Tommaso Pizzorusso, Claudio Gennaro
Publié dans: Medical Image Analysis, Numéro 80, 2022, ISSN 1361-8415
Éditeur: Elsevier BV
DOI: 10.1016/j.media.2022.102500

CL2R: Compatible Lifelong Learning Representations

Auteurs: Niccoló Biondi, Federico Pernici, Matteo Bruni, Daniele Mugnai, Alberto Del Bimbo
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 18, 2022, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3564786

Graph Neural Networks for Graph Drawing

Auteurs: Matteo Tiezzi, Gabriele Ciravegna, Marco Gori
Publié dans: IEEE Transactions on Neural Networks and Learning Systems, 2022, ISSN 2162-237X
Éditeur: IEEE Computational Intelligence Society
DOI: 10.1109/tnnls.2022.3184967

ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation

Auteurs: Yahui Liu, Yajing Chen, Linchao Bao, Nicu Sebe, Bruno Lepri, Marco De Nadai
Publié dans: IEEE Transactions on Multimedia, Numéro 25, 2023, Page(s) 3343 - 3353, ISSN 1520-9210
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tmm.2022.3159115

Learning and Reasoning for Cultural Metadata Quality: Coupling symbolic AI and Machine Learning over a semantic Web knowledge graph to support museum curators in improving the quality of cultural metadata and information retrieval

Auteurs: Anna Bobasheva, Fabien Gandon, Frederic Precioso
Publié dans: Journal on Computing and Cultural Heritage, 2021, ISSN 1556-4673
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3485844

Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation

Auteurs: Hao Tang, Philip H.S. Torr, Nicu Sebe
Publié dans: EEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 45, 2023, Page(s) 6055-6071, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2022.3212915

MeVer NetworkX: Network Analysis and Visualization for Tracing Disinformation

Auteurs: Olga Papadopoulou; Themistoklis Makedas; Lazaros Apostolidis; Francesco Poldi; Symeon Papadopoulos; Ioannis Kompatsiaris
Publié dans: Future Internet, Numéro 14, 2022, ISSN 1999-5903
Éditeur: MDPI
DOI: 10.3390/fi14050147

A full data augmentation pipeline for small object detection based on generative adversarial networks

Auteurs: Brais Bosquet, Daniel Cores, Lorenzo Seidenari, Víctor M. Brea, Manuel Mucientes, Alberto Del Bimbo
Publié dans: Pattern Recognition, Numéro 133, 2024, Page(s) 108998, ISSN 0031-3203
Éditeur: Pergamon Press
DOI: 10.1016/j.patcog.2022.108998

Playing Against the Board: Rolling Horizon Evolutionary Algorithms Against Pandemic

Auteurs: Sfikas, Konstantinos; Liapis, Antonios
Publié dans: IEEE Transactions on Games, 2021, ISSN 2475-1510
Éditeur: IEEE
DOI: 10.1109/TG.2021.3069766

Induced permutations for approximate metric search

Auteurs: Lucia Vadicamo, Giuseppe Amato, Claudio Gennaro
Publié dans: Information Systems, Numéro 119, 2024, Page(s) 102286, ISSN 0306-4379
Éditeur: Elsevier Science & Technology
DOI: 10.1016/j.is.2023.102286

Deep Unsupervised Key Frame Extraction for Eficient Video Classification

Auteurs: Hao Tang, Lei Ding, Songsong Wu, Bin Ren, Nicu Sebe, Paolo Rota
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 19, 2023, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3571735

Hyperspherical class prototypes for adversarial robustness

Auteurs: Vasileios Mygdalis, Ioannis Pitas
Publié dans: Pattern Recognition, Numéro 125, 2022, ISSN 0031-3203
Éditeur: Pergamon Press
DOI: 10.1016/j.patcog.2022.108527

p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks

Auteurs: Emmanouil Krasanakis; Symeon Papadopoulos; Ioannis Kompatsiaris
Publié dans: IEEE Access, 2022, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/ACCESS.2022.3159688

Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling

Auteurs: Yue Song, Hao Tang, Nicu Sebe, Wei Wang
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 19, 2023, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3513134

Orthogonal SVD Covariance Conditioning and Latent Disentanglement

Auteurs: Yue Song, Nicu Sebe, Wei Wang
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 45, 2023, Page(s) 8773 - 8786, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2022.3228979

AUTOLYCUS: Exploiting Explainable Artificial Intelligence (XAI) for Model Extraction Attacks against Interpretable Models

Auteurs: Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday
Publié dans: Proceedings on Privacy Enhancing Technologies, Numéro 2024, 2024, Page(s) 684-699, ISSN 2299-0984
Éditeur: Privacy Enhancing Technologies Symposium
DOI: 10.56553/popets-2024-0137

When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition With Limited Data

Auteurs: Hao Tang; Hong Liu; Wei Xiao; Nicu Sebe
Publié dans: IEEE Transactions on Neural Networks and Learning Systems, Numéro 32, 2021, Page(s) 2129-2141, ISSN 2162-2388
Éditeur: IEEE
DOI: 10.1109/tnnls.2020.2997289

MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection

Auteurs: Davide Alessandro Coccomini, Giorgos Kordopatis Zilos, Giuseppe Amato, Roberto Caldelli, Fabrizio Falchi, Symeon Papadopoulos, Claudio Gennaro
Publié dans: IEEE Transactions on Information Forensics and Security, Numéro 19, 2024, Page(s) 6084-6096, ISSN 1556-6013
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tifs.2024.3409054

Behavioral impulsivity is associated with pupillary alterations and hyperactivity in CDKL5 mutant mice

Auteurs: Aurelia Viglione, Giulia Sagona, Fabio Carrara, Giuseppe Amato, Valentino Totaro, Leonardo Lupori, Elena Putignano, Tommaso Pizzorusso, Raffaele Mazziotti
Publié dans: Human Molecular Genetics, Numéro 31, 2023, Page(s) 4107–4120, ISSN 0964-6906
Éditeur: Oxford University Press
DOI: 10.1093/hmg/ddac164

MEYE: Web App for Translational and Real-Time Pupillometry

Auteurs: Raffaele Mazziotti; Fabio Carrara; Aurelia Viglione; Leonardo Lupori; Luca Lo Verde; Alessandro Benedetto; Giulia Ricci; Giulia Sagona; Giuseppe Amato; Tommaso Pizzorusso; Tommaso Pizzorusso
Publié dans: eNeuro, Numéro 8, 2021, ISSN 2373-2822
Éditeur: Society for Neuroscience
DOI: 10.1523/eneuro.0122-21.2021

TweepFake: About detecting deepfake tweets

Auteurs: Tiziano Fagni, Fabrizio Falchi,Margherita Gambini, Antonio Martella, Maurizio Tesconi
Publié dans: PLoS ONE, Numéro 16, 2021, ISSN 1932-6203
Éditeur: Public Library of Science
DOI: 10.1371/journal.pone.0251415

Fine-Grained Adversarial Semi-supervised Learning

Auteurs: Daniele Mugnai; Federico Pernici; Francesco Turchini; Alberto del Bimbo
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 18, 2022, Page(s) 1-19, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3485473

Deep Networks for Behavioral Variant Frontotemporal Dementia Identification from Multiple Acquisition Sources

Auteurs: Marco Di Benedetto, Fabio Carrara, Benedetta Tafuri, Salvatore Nigro, Roberto De Blasi, Fabrizio Falchi, Claudio Gennaro, Giuseppe Gigli, Giancarlo Logroscino, Giuseppe Amato
Publié dans: Computers in Biology and Medicine, Numéro 148, 2022, ISSN 0010-4825
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.compbiomed.2022.105937

pygrank: A python package for graph node ranking

Auteurs: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris, Andreas L. Symeonidis
Publié dans: SoftwareX, Numéro 20, 2022, ISSN 2352-7110
Éditeur: Elsevier BV
DOI: 10.1016/j.softx.2022.101227

Report on the 1st International Workshop on Learning to Quantify (LQ 2021)

Auteurs: Juan Jose del Coz, Pablo Gonzalez, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: ACM SIGKDD Explorations Newsletter, Numéro 24, 2022, ISSN 1931-0153
Éditeur: Association for Computing Machinery
DOI: 10.1145/3544903.3544910

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

Auteurs: Juanjuan Weng, Zhiming Luo, Shaozi Li, Nicu Sebe, Zhun Zhong
Publié dans: IEEE Transactions on Information Forensics and Security, Numéro 18, 2023, Page(s) 3561 - 3574, ISSN 1556-6013
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tifs.2023.3284649

Data-driven personalisation of Television Content: A Survey

Auteurs: Lyndon Nixon, Jeremy Foss, Konstantinos Apostolidis, Vasileios Mezaris
Publié dans: Multimedia Systems, Numéro 28, 2022, Page(s) 2193–2225, ISSN 1432-1882
Éditeur: Springer-Verlag GmbH
DOI: 10.1007/s00530-022-00926-6

Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis

Auteurs: Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe
Publié dans: International Journal of Computer Vision, Numéro 131, 2023, Page(s) 644–658, ISSN 0920-5691
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s11263-022-01722-5

Dungeons & Replicants II: Automated Game Balancing Across Multiple Difficulty Dimensions via Deep Player Behavior Modeling

Auteurs: Johannes Pfau, Antonios Liapis, Georgios N. Yannakakis, Rainer Malaka
Publié dans: IEEE Transactions on Games, Numéro 15, 2023, Page(s) 217 - 227, ISSN 2475-1510
Éditeur: IEEE
DOI: 10.1109/tg.2022.3167728

Logic Explained Networks

Auteurs: Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Marco Gori, Pietro Liò, Marco Maggini, Stefano Melacci
Publié dans: Artificial Intelligence, Numéro 314, 2023, ISSN 0004-3702
Éditeur: Elsevier BV
DOI: 10.1016/j.artint.2022.103822

Comparing the performance of Hebbian against backpropagation learning using convolutional neural networks

Auteurs: Gabriele Lagani; Fabrizio Falchi; Claudio Gennaro; Giuseppe Amato
Publié dans: Neural Computing and Applications, Numéro 34, 2022, Page(s) 6503–6519, ISSN 0941-0643
Éditeur: Springer Verlag
DOI: 10.1007/s00521-021-06701-4

Joint-Based Action Progress Prediction

Auteurs: Davide Pucci, Federico Becattini, Alberto Del Bimbo
Publié dans: Sensors, Numéro 23, 2024, Page(s) 520, ISSN 1424-8220
Éditeur: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/s23010520

Layout-to-Image Translation With Double Pooling Generative Adversarial Networks

Auteurs: Tang, Hao; Sebe, Nicu
Publié dans: IEEE Transactions on Image Processing, Numéro 30, 2021, Page(s) 7903 - 7913, ISSN 1057-7149
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TIP.2021.3109531

A leap among quantum computing and quantum neural networks: a survey

Auteurs: Fabio Valerio Massoli, Lucia Vadicamo, Giuseppe Amato, Fabrizio Falchi
Publié dans: ACM Computing Surveys, Numéro 55, 2022, Page(s) 1–37, ISSN 0360-0300
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3529756

Low-Budget Label Query through Domain Alignment Enforcement

Auteurs: Cristiano Saltori , Paolo Rota, Nicu Sebe, Jurandy Almeida
Publié dans: Computer Vision and Image Understanding, Numéro 222, 2022, ISSN 1077-3142
Éditeur: Academic Press
DOI: 10.1016/j.cviu.2022.103485

Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN

Auteurs: Lorenzo Agnolucci; Leonardo Galteri; Marco Bertini; Alberto Del Bimbo
Publié dans: IEEE Transactions on Multimedia, 2023, ISSN 1520-9210
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tmm.2023.3264882

CoReS: Compatible Representations via Stationarity

Auteurs: Niccolò Biondi;, Federico Pernici, Matteo Bruni, Alberto Del Bimbo
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 45, 2023, Page(s) 9567 - 9582, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2023.3259542

A comprehensive study of class incremental learning algorithms for visual tasks.

Auteurs: Eden Belouadah; Adrian Popescu; Ioannis Kanellos
Publié dans: Neural Networks, Numéro 135, 2021, Page(s) 38-54, ISSN 0893-6080
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.neunet.2020.12.003

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

Auteurs: Mara Graziani, Lidia Dutkiewicz, Davide Calvaresi, José Pereira Amorim, Katerina Yordanova, Mor Vered, Rahul Nair, Pedro Henriques Abreu, Tobias Blanke, Valeria Pulignano, John O. Prior, Lode Lauwaert, Wessel Reijers, Adrien Depeursinge, Vincent Andrearczyk, Henning Müller
Publié dans: Artificial Intelligence Review, Numéro 56, 2022, Page(s) 3473–3504, ISSN 1573-7462
Éditeur: Springer Nature
DOI: 10.1007/s10462-022-10256-8

Effective triplet mining improves training of multi-scale pooled CNN for image retrieval

Auteurs: Federico Vaccaro, Tiberio Uricchio, Marco Bertini, Alberto Del Bimbo
Publié dans: Machine Vision and Applications, Numéro 33, 2022, ISSN 1432-1769
Éditeur: Springer-Verlag GmbH
DOI: 10.1007/s00138-021-01260-z

Interactive multimodal video search: an extended post-evaluation for the VBS 2022 competition

Auteurs: Konstantin Schall, Werner Bailer, Kai-Uwe Barthel, Fabio Carrara, Jakub Lokoč, Ladislav Peška, Klaus Schoeffmann, Lucia Vadicamo, Claudio Vairo
Publié dans: International Journal of Multimedia Information Retrieval, Numéro 13, 2024, ISSN 2192-6611
Éditeur: Springer Nature
DOI: 10.1007/s13735-024-00325-9

Bus Violence: An Open Benchmark for Video Violence Detection on Public Transport

Auteurs: Luca Ciampi; Paweł Foszner; Nicola Messina; Michał Staniszewski; Claudio Gennaro; Fabrizio Falchi; Gianluca Serao; Michał Cogiel; Dominik Golba; Agnieszka Szczęsna; Giuseppe Amato
Publié dans: Sensors, Numéro 22, 2022, ISSN 1424-8220
Éditeur: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/s22218345

Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments

Auteurs: Xiao Bai, Xiang Wang, Xianglong Liu, Qiang Liu, Jingkuan Song, Nicu Sebe, Been Kim
Publié dans: Pattern Recognition, Numéro 120, 2021, ISSN 0031-3203
Éditeur: Pergamon Press
DOI: 10.1016/j.patcog.2021.108102

Same or Different? Diff-Vectors for Authorship Analysis

Auteurs: Silvia Corbara, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: ACM Transactions on Knowledge Discovery from Data, Numéro 18, 2023, ISSN 1556-4681
Éditeur: Special Interest Group on Computer Graphics, Association for Computing Machinery
DOI: 10.1145/3609226

Curriculum self-paced learning for cross-domain object detection

Auteurs: Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Niculae Sebe
Publié dans: Computer Vision and Image Understanding, Numéro 204, 2021, ISSN 1077-3142
Éditeur: Academic Press
DOI: 10.1016/j.cviu.2021.103166

<i>nSimplex</i> <i>Zen</i> : A Novel Dimensionality Reduction for Euclidean and Hilbert Spaces

Auteurs: Richard Connor, Lucia Vadicamo
Publié dans: ACM Transactions on Knowledge Discovery from Data, Numéro 18, 2024, Page(s) 1-44, ISSN 1556-4681
Éditeur: Special Interest Group on Computer Graphics, Association for Computing Machinery
DOI: 10.1145/3647642

Lost in Transduction: Transductive Transfer Learning in Text Classification

Auteurs: Alejandro Moreo, Andrea Esuli, Fabrizio Sebastiani
Publié dans: ACM Transactions on Knowledge Discovery from Data, Numéro 6, 2022, Page(s) 1-21, ISSN 1556-4681
Éditeur: Special Interest Group on Computer Graphics, Association for Computing Machinery
DOI: 10.1145/3453146

TRACK: A New Method from a Re-examination of Deep Architectures for Head Motion Prediction in 360-degree Videos

Auteurs: Miguel Fabian Romero Rondon, Lucile Sassatelli, Ramon Aparicio-Pardo, Frederic Precioso
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2021.3070520

LANBIQUE: LANguage-based Blind Image QUality Evaluation

Auteurs: Leonardo Galteri; Lorenzo Seidenari; Pietro Bongini; Marco Bertini; Alberto Del Bimbo
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, 2022, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3538649

Mitigating robust overfitting via self-residual-calibration regularization

Auteurs: Hong Liu, Zhun Zhong, Nicu Sebe, Shin'ichi Satoh
Publié dans: Artificial Intelligence, Numéro 317, 2023, ISSN 0004-3702
Éditeur: Elsevier BV
DOI: 10.1016/j.artint.2023.103877

Curriculum Learning: A Survey

Auteurs: Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe
Publié dans: International Journal of Computer Vision, Numéro 130, 2022, Page(s) 1526–1565, ISSN 0920-5691
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s11263-022-01611-x

Word-class embeddings for multiclass text classification

Auteurs: Alejandro Moreo, Andrea Esuli, Fabrizio Sebastiani
Publié dans: Data Mining and Knowledge Discovery, Numéro 35, 2022, Page(s) 911-963, ISSN 1384-5810
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10618-020-00735-3

One qubit as a universal approximant

Auteurs: Adrián Pérez-Salinas; Adrián Pérez-Salinas; David López-Núñez; David López-Núñez; Artur Garcia-Saez; P. Forn-Díaz; José I. Latorre
Publié dans: Physical Review A, Numéro 104, 2021, ISSN 1094-1622
Éditeur: American Physical Society
DOI: 10.1103/physreva.104.012405

From the Lab to the Wild: Affect Modeling Via Privileged Information

Auteurs: Konstantinos Makantasis, Kosmas Pinitas, Antonios Liapis, Georgios N. Yannakakis
Publié dans: IEEE Transactions on Affective Computing, 2023, ISSN 1949-3045
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TAFFC.2023.3265072

Total Generate: Cycle In Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes

Auteurs: Hao Tang; Nicu Sebe
Publié dans: IEEE Transactions on Multimedia, 2021, ISSN 1941-0077
Éditeur: IEEE
DOI: 10.1109/tmm.2021.3091847

AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks

Auteurs: Tang, Hao; Liu, Hong; Xu, Dan; Torr, Philip; Sebe, Nicu
Publié dans: IEEE Transactions on Neural Networks and Learning Systems, 2021, ISSN 2162-2388
Éditeur: IEEE
DOI: 10.1109/TNNLS.2021.3105725

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification

Auteurs: Alejandro Moreo, Andrea Pedrotti, Fabrizio Sebastian
Publié dans: ACM Transactions on Information Systems, Numéro 41, 2023, Page(s) 1–37, ISSN 1046-8188
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3544104

DDSP-Piano: A Neural Sound Synthesizer Informed by Instrument Knowledge

Auteurs: Lenny Renault, Rémi Mignot, Axel Roebel
Publié dans: Journal of the Audio Engineering Society (JAES), Numéro 71, 2023, Page(s) 552-565, ISSN 1549-4950
Éditeur: Audio Engineering Society
DOI: 10.17743/jaes.2022.0102

Improving the Adversarial Robustness of Neural ODE Image Classifiers by Tuning the Tolerance Parameter

Auteurs: Fabio Carrara, Roberto Caldelli, Fabrizio Falchi, Giuseppe Amato
Publié dans: Information, Numéro 13, 2022, ISSN 2078-2489
Éditeur: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/info13120555

Open-Ended Evolution for Minecraft Building Generation

Auteurs: Matthew Barthet, Antonios Liapis, Georgios N. Yannakakis
Publié dans: IEEE Transactions on Games, 2022, ISSN 2475-1510
Éditeur: IEEE
DOI: 10.1109/tg.2022.3189426

A Survey on Deep Learning for Skeleton-Based Human Animation

Auteurs: Lucas Mourot; Ludovic Hoyet; Francois Le Clerc; François Schnitzler; Pierre Hellier
Publié dans: Computer Graphics Forum, Numéro 41, 2021, Page(s) 122-157, ISSN 0167-7055
Éditeur: Blackwell Publishing Inc.
DOI: 10.1111/cgf.14426

Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach

Auteurs: Alessandro Fabris, Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: Journal of Artificial Intelligence Research (JAIR), Numéro 76, 2023, Page(s) 1117-1180, ISSN 1076-9757
Éditeur: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.14033

Universal Local Attractors on Graphs

Auteurs: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris
Publié dans: Applied Sciences, Numéro 14, 2024, Page(s) 4533, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app14114533

Unsupervised High-Resolution Portrait Gaze Correction and Animation

Auteurs: Jichao Zhang; Jingjing Chen; Hao Tang; Enver Sangineto; Peng Wu; Yan Yan; Nicu Sebe, Wei Wang
Publié dans: IEEE Transactions on Image Processing, Numéro 31, 2022, Page(s) 5272-5286, ISSN 1057-7149
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tip.2022.3191852

Regular Polytope Networks.

Auteurs: Federico Pernici; Matteo Bruni; Claudio Baecchi; Alberto Del Bimbo
Publié dans: IEEE Transactions on Neural Networks and Learning Systems, 2021, ISSN 2162-2388
Éditeur: IEEE
DOI: 10.1109/tnnls.2021.3056762

DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval

Auteurs: Giorgos Kordopatis-Zilos, Christos Tzelepis, Symeon Papadopoulos, Ioannis Kompatsiaris, Ioannis Patras
Publié dans: International Journal of Computer Vision, Numéro 130, 2022, Page(s) 2385–2407, ISSN 0920-5691
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s11263-022-01651-3

Scalable bio-inspired training of Deep Neural Networks with FastHebb

Auteurs: Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Hannes Fassold, Giuseppe Amato
Publié dans: Neurocomputing, Numéro 595, 2024, Page(s) 127867, ISSN 0925-2312
Éditeur: Elsevier BV
DOI: 10.1016/j.neucom.2024.127867

A network view on reliability: using machine learning to understand how we assess news websites

Auteurs: Tobias Blanke, Tommaso Venturini
Publié dans: Journal of Computational Social Science, 2021, ISSN 2432-2717
Éditeur: Springer Nature
DOI: 10.1007/s42001-021-00116-w

Tweet sentiment quantification: An experimental re-evaluation

Auteurs: Alejandro Moreo, Fabrizio Sebastiani
Publié dans: PLOS ONE, 2022, ISSN 1932-6203
Éditeur: Public Library of Science
DOI: 10.1371/journal.pone.0263449

Voicing challenges: GDPR and AI research

Auteurs: Katherine Quezada-Tavarez, Lidia Dutkiewicz, Noémie Krack
Publié dans: Open Research Europe - Artificial Intelligence and the Social Sciences and Humanities Collection, 2022, ISSN 2732-5121
Éditeur: European Commision
DOI: 10.12688/openreseurope.15145.1

An Embedded Toolset for Human Activity Monitoring in Critical Environments

Auteurs: Marco Di Benedetto, Fabio Carrara, Luca Ciampi, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Publié dans: Expert Systems with Applications, Numéro 199, 2022, ISSN 0957-4174
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.eswa.2022.117125

Video Summarization Using Deep Neural Networks: A Survey

Auteurs: Evlampios Apostolidis; Eleni Adamantidou; Alexandros I. Metsai; Vasileios Mezaris; Ioannis Patras
Publié dans: Video Summarization Using Deep Neural Networks: A Survey, Numéro 109, 2021, Page(s) 1838 - 1863, ISSN 1558-2256
Éditeur: IEEE
DOI: 10.1109/jproc.2021.3117472

Visual Interestingness Prediction: A Benchmark Framework and Literature Review

Auteurs: Mihai Gabriel Constantin; Liviu-Daniel Stefan; Bogdan Ionescu; Ngoc Q. K. Duong; Claire-Helene Demarty; Mats Sjöberg
Publié dans: International Journal of Computer Vision, Numéro 129, 2021, Page(s) 1526–1550, ISSN 1573-1405
Éditeur: Springer Science+Business Media, LLC
DOI: 10.1007/s11263-021-01443-1

Audio Splicing Detection and Localization Based on Acquisition Device Traces

Auteurs: Daniele Ugo Leonzio, Luca Cuccovillo, Paolo Bestagini, Marco Marcon, Patrick Aichroth, Stefano Tubaro
Publié dans: IEEE Transactions on Information Forensics and Security (, Numéro 18, 2023, Page(s) 4157 - 4172, ISSN 1556-6013
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tifs.2023.3293415

Multi-Attribute Balanced Sampling for Disentangled GAN Controls

Auteurs: Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
Publié dans: Pattern Recognition Letters, Numéro 162, 2022, Page(s) 56-62, ISSN 0167-8655
Éditeur: Elsevier BV
DOI: 10.1016/j.patrec.2022.08.012

Deep Variational Learning for 360° Adaptive Streaming

Auteurs: Quentin Guimard, Lucile Sassatelli, Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 20, 2024, Page(s) 1-25, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3643031

A peek inside two black boxes-an experiment with explainable artificial intelligence and IPCC leadership

Auteurs: Tobias Blanke, Tommaso Venturini, Kari De Pryck
Publié dans: International Journal of Digital Humanities, Numéro 6, 2024, Page(s) 45-69, ISSN 2524-7840
Éditeur: Springer Nature
DOI: 10.1007/s42803-023-00080-z

Public opinion monitoring through collective semantic analysis of tweets

Auteurs: Dionysios Karamouzas, Ioannis Mademlis, Ioannis Pitas
Publié dans: Social Network Analysis and Mining, Numéro 12, 2022, ISSN 1869-5469
Éditeur: Springer-Verlag GmbH
DOI: 10.1007/s13278-022-00922-8

In the Wild Video Violence Detection: An Unsupervised Domain Adaptation Approach

Auteurs: Luca Ciampi, Carlos Santiago, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Publié dans: SN Computer Science, Numéro 5, 2024, ISSN 2661-8907
Éditeur: Springer Nature
DOI: 10.1007/s42979-024-03126-3

Explaining autonomous driving with visual attention and end-to-end trainable region proposals

Auteurs: Luca Cultrera, Federico Becattini, Lorenzo Seidenari, Pietro Pala, Alberto Del Bimbo
Publié dans: Journal of Ambient Intelligence and Humanized Computing, 2023, Page(s) https://zenodo.org/records/8194594, ISSN 1868-5137
Éditeur: Springer Verlag
DOI: 10.1007/s12652-023-04550-8

ICS: Total Freedom in Manual Text Classification Supported by Unobtrusive Machine Learning

Auteurs: Andrea Esuli
Publié dans: IEEE Access, Numéro 10, 2022, Page(s) 64741 - 64760, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2022.3184009

Deep learning for procedural content generation

Auteurs: Jialin Liu; Sam Snodgrass; Ahmed Khalifa; Sebastian Risi; Georgios N. Yannakakis; Georgios N. Yannakakis; Julian Togelius
Publié dans: Neural Computing and Applications, Numéro 33, 2021, Page(s) 19-37, ISSN 0941-0643
Éditeur: Springer Verlag
DOI: 10.1007/s00521-020-05383-8

JGNN: Graph Neural Networks on Native Java

Auteurs: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris
Publié dans: SoftwareX, Numéro 23, 2023, ISSN 2352-7110
Éditeur: Elsevier B.V.
DOI: 10.1016/j.softx.2023.101459

Multi-Label Quantification

Auteurs: Alejandro Moreo, Manuel Francisco, Fabrizio Sebastiani
Publié dans: ACM Transactions on Knowledge Discovery from Data, Numéro 18, 2024, ISSN 1556-4681
Éditeur: Special Interest Group on Computer Graphics, Association for Computing Machinery
DOI: 10.1145/3606264

The Pixels and Sounds of Emotion: General-Purpose Representations of Arousal in Games

Auteurs: Konstantinos Makantasis; Antonios Liapis; Georgios N. Yannakakis
Publié dans: IEEE Transactions on Affective Computing, 2021, ISSN 1949-3045
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TAFFC.2021.3060877

Generation of Realistic Synthetic Financial Time-Series

Auteurs: Mihai Dogariu; Liviu-Daniel Ştefan; Bogdan Andrei Boteanu; Claudiu Lamba; Bomi Kim; Bogdan Ionescu
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 18, 2022, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3501305

Fine-Grained Visual Textual Alignment for Cross-Modal Retrieval Using Transformer Encoders

Auteurs: Nicola Messina; Giuseppe Amato; Andrea Esuli; Fabrizio Falchi; Claudio Gennaro; Stéphane Marchand-Maillet
Publié dans: ACM Transactions on Multimedia Computing, Communications, and Applications, Numéro 17, 2021, Page(s) 1-23, ISSN 1551-6857
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3451390

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval

Auteurs: Giuseppe Amato,Paolo Bolettieri,Fabio Carrara,Franca Debole,Fabrizio Falchi,Claudio Gennaro,Lucia Vadicamo, Claudio Vairo
Publié dans: Journal of Imaging, Numéro 7, 2021, ISSN 2313-433X
Éditeur: MDPI
DOI: 10.3390/jimaging7050076

Interactive video retrieval evaluation at a distance: comparing sixteen interactive video search systems in a remote setting at the 10th Video Browser Showdown

Auteurs: Silvan Heller, Viktor Gsteiger, Werner Bailer, Cathal Gurrin, Björn Þór Jónsson, Jakub Lokoč, Andreas Leibetseder, František Mejzlík, Ladislav Peška, Luca Rossetto, Konstantin Schall, Klaus Schoeffmann, Heiko Schuldt, Florian Spiess, Ly-Duyen Tran, Lucia Vadicamo, Patrik Veselý, Stefanos Vrochidis & Jiaxin Wu
Publié dans: International Journal of Multimedia Information Retrieval volume, 2022, Page(s) 1–18, ISSN 2192-6611
Éditeur: Springer-Verlag London Ltd
DOI: 10.1007/s13735-021-00225-2

A Critical Reassessment of the Saerens-Latinne-Decaestecker Algorithm for Posterior Probability Adjustment

Auteurs: Andrea Esuli, Alessio Molinari, Fabrizio Sebastiani
Publié dans: ACM Transactions on Information Systems, 2021, Page(s) 1-34, ISSN 1046-8188
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3433164

Latent Traversals in Generative Models as Potential Flows

Auteurs: Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling
Publié dans: Proceedings of the 40th International Conference on Machine Learning 2023, 2023, Page(s) 32288-32303
Éditeur: MLResearchPress

Sparse to Dense Dynamic 3D Facial Expression Generation

Auteurs: "Naima Otberdout, Claudio Ferrari, Mohamed Daoudi, Stefano Berretti, Alberto Del Bimbo, """
Publié dans: Proceedings 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Page(s) 20353-20362, ISBN 978-1-6654-6946-3
Éditeur: IEEE
DOI: 10.1109/cvpr52688.2022.01974

VISIONE at Video Browser Showdown 2023

Auteurs: Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Nicola Messina, Lucia Vadicamo, Claudio Vairo
Publié dans: Proceedings 29th International Conference on MultiMedia Modeling (MMM 2023), Numéro 1, 2023, Page(s) 615–621, ISBN 978-3-031-27076-5
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-27077-2_48

Tuning Neural ODE Networks to Increase Adversarial Robustness in Image Forensics

Auteurs: Roberto Caldelli, Fabio Carrara, Fabrizio Falchi
Publié dans: 2022 IEEE International Conference on Image Processing (ICIP), Numéro 31, 2024, Page(s) 1496-1500
Éditeur: IEEE
DOI: 10.1109/icip46576.2022.9897662

VISIONE at Video Browser Showdown 2021

Auteurs: Giuseppe Amato; Paolo Bolettieri; Fabrizio Falchi; Claudio Gennaro; Nicola Messina; Lucia Vadicamo; Claudio Vairo
Publié dans: International Conference on Multimedia Modeling MMM 2021, 2021, Page(s) 473-478
Éditeur: Springer
DOI: 10.1007/978-3-030-67835-7_47

Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection

Auteurs: Davide Alessandro Coccomini, Roberto Caldelli, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), 2022, Page(s) 52–58, ISBN 978-1-4503-9242-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533582

ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval

Auteurs: Nicola Messina, Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Giuseppe Amato, Rita Cucchiara
Publié dans: Proceedings of the 19th International Conference on Content-based Multimedia Indexing (CBMI '22), 2022, Page(s) 64-70, ISBN 978-1-4503-9720-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3549555.3549576

Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer

Auteurs: Haoyu Chen; Hao Tang; Henglin Shi; Wei Peng; Niculae Sebe; Guoying Zhao
Publié dans: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021, Page(s) 8610-8619
Éditeur: IEEE
DOI: 10.1109/iccv48922.2021.00851

Hateful meme detection with multimodal deep neural networks

Auteurs: Mihai Gabriel Constantin, Dan-Ștefan Pârvu, Cristian Stanciu, Denisa Ionaşcu, Bogdan Ionescu
Publié dans: 2021 International Symposium on Signals, Circuits and Systems (ISSCS), 2021
Éditeur: IEEE
DOI: 10.1109/isscs52333.2021.9497374

Differentiable Piano Model for MIDI-to-Audio Performance Synthesis

Auteurs: Lenny Renault, Rémi Mignot, Axel Roebe
Publié dans: Proceedings 25th International Conference on Digital Audio Effects (DAFx20in, 2022, ISBN 978-3-200-08599-2
Éditeur: DAFx

Spectral Denoising for Microphone Classification

Auteurs: Luca Cuccovillo, Antonio Giganti, Paolo Bestagini, Patrick Aichroth, Stefano Tubaro
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), Numéro 978-1-4503-9242-6, 2022, Page(s) 10–17
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533586

Batch-efficient EigenDecomposition for Small and Medium Matrices

Auteurs: Yue Song, Nicu Sebe, Wei Wang
Publié dans: Proceedings 17th European Conference on Computer Vision (ECCV 2022), 2022, Page(s) 583–599, ISBN 978-3-031-20050-2
Éditeur: Springer
DOI: 10.1007/978-3-031-20050-2_34

Overview of ImageCLEFfusion 2022 Task – Ensembling Methods for Media Interestingness Prediction and Result Diversification

Auteurs: Liviu-Daniel Ştefan, Mihai Gabriel Constantin,Mihai Dogariu, Bogdan Ionescu
Publié dans: Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum, 2022, Page(s) 1339-1346
Éditeur: CEUR-WS.org

Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation

Auteurs: Wei Wang, Zhun Zhong, Weijie Wang, Xi Chen, Charles Ling, Boyu Wang, Nicu Sebe
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Page(s) 24090-24099, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.02307

Expressive piano performance rendering from unpaired data

Auteurs: Lenny Renault, Remi Mignot, Axel Roebel
Publié dans: Proceedings 26th International Conference on Digital Audio Effects (DAFx23), 2023, ISSN 2413-6689
Éditeur: DafX

Geometry-Contrastive Transformer for Generalized 3D Pose Transfer

Auteurs: Haoyu Chen; Hao Tang; Zitong Yu; Niculae Sebe; Guoying Zhao
Publié dans: 36th AAAI Conference on Artificial Intelligence (AIAI-22), 2022
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.5281/zenodo.6363288

An Optimized Pipeline for Image-Based Localization in Museums from Egocentric Images

Auteurs: Nicola Messina, Fabrizio Falchi, Antonino Furnari, Claudio Gennaro, Giovanni Maria Farinella
Publié dans: Proceedings International Conference on Image Analysis and Processing, 2023, Page(s) 512–524, ISBN 978-3-031-43147-0
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-43148-7_43

Uncertainty-guided Source-free Domain Adaptation

Auteurs: Subhankar Roy, Martin Trapp, Andrea Pilzer, Juho Kannala, Nicu Sebe,Elisa Ricci, Arno Solin
Publié dans: Proceedings 17th European Conference on Computer Vision (ECCV 2022), 2022, Page(s) 537–555, ISBN 978-3-031-19783-3
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-19806-9_31

Escaping local minima in deep reinforcement learning for video summarization

Auteurs: Panagiota Alexoudi, Ioannis Mademlis, Ioannis Pitas
Publié dans: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval (ICMR '23), 2023, Page(s) 530–534, ISBN 979-8-4007-0178-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3591106.3592288

RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection

Auteurs: Yue Song, Nicu Sebe, Wei Wang
Publié dans: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), Numéro 35, 2022, ISBN 9781713871088
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

Challenges for Automatic Detection of Fake News Related to Migration: Invited paper

Auteurs: Werner Bailer; Georg Thallinger; Gerhard Backfried; Dorothea Thomas-Aniola
Publié dans: 2021 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), 2021, Page(s) 133-138
Éditeur: IEEE
DOI: 10.1109/cogsima51574.2021.9475929

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

Auteurs: Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna, Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Zohreh Shams, Frederic Precioso, Stefano Melacci, Adrian Weller, Pietro Lio, Mateja Jamnik
Publié dans: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022, ISBN 9781713871088
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

Playable Video Generation

Auteurs: Willi Menapace; Stéphane Lathuilière; Sergey Tulyakov; Aliaksandr Siarohin; Elisa Ricci
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Éditeur: IEEE
DOI: 10.1109/cvpr46437.2021.00993

Playable Environments: Video Manipulation in Space and Time

Auteurs: Willi Menapace, Aliaksandr Siarohin, Christian Theobalt, Vladislav Golyanik, Sergey Tulyakov, Stéphane Lathuilière, Elisa Ricci
Publié dans: Proceedings 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Page(s) 3574-3583,, ISBN 978-1-6654-6946-3
Éditeur: IEEE
DOI: 10.1109/cvpr52688.2022.00357

DiffDefense: Defending Against Adversarial Attacks via Diffusion Models

Auteurs: Hondamunige Prasanna Silva, Lorenzo Seidenari, Alberto Del Bimbo
Publié dans: Proceedings 22nd International Conference on Image Analysis and Processing (ICIAP 2023), Numéro 2, 2023, Page(s) 430–442, ISBN 978-3-031-43152-4
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-43153-1_36

Overview of The MediaEval 2021 Predicting Media Memorability Task

Auteurs: R.S. Kiziltepe; M.G. Constantin; C.H. Demarty; G. Healy; C. Fosco; A.G.S. de Herrera; S. Halder; B. Ionescu; A. Matran-Fernandez; A.F. Smeaton; L. Sweeney
Publié dans: MediaEval 2021 Workshop, 2021
Éditeur: MediaEval Multimedia Benchmark
DOI: 10.5281/zenodo.6366914

Active Learning and the Saerens-Latinne-Decaestecker Algorithm: An Evaluation

Auteurs: Alessio Molinari, Andrea Esuli, abrizio Sebastiani
Publié dans: Proceedings of the 2nd Joint Conference of the Information Retrieval Communities in Europe (CIRCLE 2022), 2022
Éditeur: CEUR-WS.org
DOI: 10.5281/zenodo.7090014

AIMultimediaLab at ImageCLEFfusion 2022: DeepFusion Methods for Ensembling in Diverse Scenarios

Auteurs: Mihai Gabriel Constantin, Liviu-Daniel Ștefan, Mihai Dogariu, Bogdan Ionescu
Publié dans: Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum, 2022, Page(s) 1374-1380
Éditeur: CEUR-WS.org

RankNEAT: Outperforming Stochastic Gradient Search in Preference Learning Tasks

Auteurs: Kosmas Pinitas, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '22), 2022, Page(s) 1084–1092, ISBN 978-1-4503-9237-2
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512290.3528744

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Auteurs: Jichao Zhang, Enver Sangineto, Hao Tang, Aliaksandr Siarohin, Zhun Zhong,Nicu Sebe, Wei Wang
Publié dans: Proceedings 17th European Conference on Computer Vision (ECCV 2022), 2022, Page(s) 339–356, ISBN 978-3-031-19783-3
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-19784-0_20

Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality

Auteurs: Yue Song, Nicu Sebe, Wei Wang
Publié dans: Proceedings 17th European Conference on Computer Vision (ECCV 2022), 2022, Page(s) 356–372, ISBN 978-3-031-19783-3
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-20053-3_21

Play with Emotion: Affect-Driven Reinforcement Learning

Auteurs: Matthew Barthet, Ahmed Khalifa, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings 2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII), 2022, ISBN 978-1-6654-5909-9
Éditeur: IEEE
DOI: 10.1109/acii55700.2022.9953887

4DSR-GCN: 4D Video Point Cloud Upsampling using Graph Convolutional Networks

Auteurs: Lorenzo Berlincioni,Stefano Berretti, Marco Bertini, Alberto Del Bimbo
Publié dans: Proceedings 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE '23), 2023, Page(s) 57–65, ISBN 979-8-4007-0278-5
Éditeur: Association for Computing Machinery
DOI: 10.1145/3607541.3616824

Fallacious Argument Classification in Political Debates

Auteurs: Pierpaolo Goffredo, Shohreh Haddadan, Vorakit Vorakitphan, Elena Cabrio, Serena Villata
Publié dans: Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022, Page(s) 4143-4149, ISBN 978-1-956792-03-4
Éditeur: IJCAI
DOI: 10.24963/ijcai.2022/575

HeMoG: A White-Box Model to Unveil the Connection Between Saliency Information and Human Head Motion in Virtual Reality

Auteurs: Miguel Fabian Romero Rondon, Dario Zanca, Stefano Melacci, Marco Gori, Lucile Sassatelli
Publié dans: IEEE International Conference on Artificial Intelligence and Virtual Reality (IEEE AIVR), 2021, Page(s) 10-18
Éditeur: IEEE
DOI: 10.1109/aivr52153.2021.00012

ImageCLEF 2022: Multimedia Retrieval in Medical, Nature, Fusion, and Internet Applications

Auteurs: Alba G. Seco de Herrera, Bogdan Ionescu, Henning Müller, Renaud Péteri, Asma Ben Abacha, Christoph M. Friedrich, Johannes Rückert, Louise Bloch, Raphael Brüngel, Ahmad Idrissi-Yaghir, Henning Schäfer, Serge Kozlovski, Yashin Dicente Cid, Vassili Kovalev, Jon Chamberlain, Adrian Clark, Antonio Campello, Hugo Schindler, Jérôme Deshayes, Adrian Popescu, Liviu-Daniel Ştefan, Mihai Gabriel Cons
Publié dans: Proceedings 44th European Conference on Information Retrieval Research (ECIR 2022), 2022, Page(s) 382–389, ISBN 978-3-030-99738-0
Éditeur: Springer, Cham
DOI: 10.1007/978-3-030-99739-7_48

RosneT: A Block Tensor Algebra Library for Out-of-Core Quantum Computing Simulation

Auteurs: Sergio Sanchez-Ramirez; Javier Conejero; Francesc Lordan; Anna Queralt; Toni Cortes; Rosa M Badia; Artur Garcia-Saez
Publié dans: Proceedings 2021 IEEE/ACM Second International Workshop on Quantum Computing Software (QCS), 2021, ISBN 978-1-7281-8674-0
Éditeur: IEEE
DOI: 10.1109/qcs54837.2021.00004

Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation

Auteurs: Gabriele Lagani; Raffaele Mazziotti; Fabrizio Falchi; Claudio Gennaro; Guido Marco Cicchini; Tommaso Pizzorusso ; Federico Cremisi; Giuseppe Amato
Publié dans: 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER), 2021, Page(s) 726-729
Éditeur: IEEE
DOI: 10.1109/ner49283.2021.9441166

Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers

Auteurs: Bin Ren, Yahui Liu,,Yue Song, Wei Bi, Rita Cucchiara, Nicu Sebe, Wei Wang
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Page(s) 20382-20391, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.01952

Multi-input Architecture and Disentangled Representation Learning for Multi-dimensional Modeling of Music Similarity

Auteurs: Sebastian Ribecky, Jakob Abeßer, Hanna Lukashevich
Publié dans: Proceedings of the 152nd International Audio Engineering Convention (AES), 2022
Éditeur: Audio Engineering Society

AI for the Media Industry: Application Potential and Automation Levels

Auteurs: Werner Bailer; Georg Thallinger; Verena Krawarik; Katharina Schell; Victoria Ertelthalner
Publié dans: MultiMedia Modeling 28th International Conference, MMM 2022, Numéro 1, 2022, Page(s) 109–118, ISBN 978-3-030-98358-1
Éditeur: Springer Nature
DOI: 10.1007/978-3-030-98358-1_9

Tensor Component Analysis for Interpreting the Latent Space of GANs

Auteurs: Oldfield, James; Georgopoulos Markos; Panagakis Yannis; Nicolaou Mihalis A; Patras Ioannis
Publié dans: 32nd British Machine Vision Conference, 2021
Éditeur: British Machine Vision Association
DOI: 10.5281/zenodo.6360719

Counting or Localizing? Evaluating Cell Counting and Detection in Microscopy Images

Auteurs: Luca Ciampi; Fabio Carrara; Giuseppe Amato; Claudio Gennaro
Publié dans: Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, Numéro 4, 2022, Page(s) 887-897, ISBN 978-989-758-555-5
Éditeur: SciTePress Digital Library
DOI: 10.5220/0010923000003124

Properties of Learning Multiplicative Universal Adversarial Perturbations in Image Data

Auteurs: Alexandros Zamichos, Vasileios Mygdalis, Ioannis Pitas
Publié dans: Proceedings 2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP), 2022, ISBN 978-1-6654-8548-7
Éditeur: IEEE
DOI: 10.1109/mlsp55214.2022.9943482

Few-shot Object Detection as a Semi-supervised Learning Problem

Auteurs: Werner Bailer, Hannes Fassold
Publié dans: Proceedings of the 19th International Conference on Content-based Multimedia Indexing (CBMI '22), 2022, Page(s) 131–135, ISBN 978-1-4503-9720-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3549555.3549599

A concise overview of LeQua 2022: Learning to quantify

Auteurs: Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani, Gianluca Sperduti.
Publié dans: 13th International Conference of the CLEF Association (CLEF 2022), 2022, Page(s) 362–381, ISBN 978-3-031-13642-9
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-13643-6_23

Improving Synthetically Generated Image Detection in Cross-Concept Settings

Auteurs: Pantelis Dogoulis, Giorgos Kordopatis-Zilos, Ioannis Kompatsiaris, Symeon Papadopoulos
Publié dans: Proceedings of the 2nd ACM International Workshop on Multimedia AI against (MAD '23), 2023, Page(s) 28-35, ISBN 979-8-4007-0187-0
Éditeur: Association for Computing Machinery
DOI: 10.1145/3592572.3592846

Deepfake Video Detection with Facial Features and Long-Short Term Memory Deep Networks

Auteurs: Dan-Cristian Stanciu; Bogdan Ionescu
Publié dans: 2021 International Symposium on Signals, Circuits and Systems (ISSCS), 2021
Éditeur: IEEE
DOI: 10.1109/isscs52333.2021.9497385

Attention-Based Interpretable Regression of Gene Expression in Histology

Auteurs: Mara Graziani, Niccolò Marini, Nicolas Deutschmann, Nikita Janakarajan, Henning Müller, María Rodríguez Martínez
Publié dans: Proceedings International Workshop on Interpretability of Machine Intelligence in Medical Image Computing (iMIMIC 2022), 2022, Page(s) 44–60, ISBN 978-3-031-17975-4
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-17976-1_5

Leader and breakaway detection in racing sports videos

Auteurs: Sotirios Papadopoulos; Charalampos Symeonidis; Ioannis Pitas
Publié dans: 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), 2021, Page(s) 1-5
Éditeur: IEEE
DOI: 10.1109/mmsp53017.2021.9733640

Overview of MediaEval 2020 Predicting Media Memorability Task: What Makes a Video Memorable?

Auteurs: De Herrera, A. G. S.; Kiziltepe, R. S.; Chamberlain, J.; Mihai Gabriel Constantin; Demarty, C. -H; Doctor, F.; Ionescu, B.; Smeaton, A. F.
Publié dans: Proceedings of the MediaEval 2020 Workshop, 2021
Éditeur: CEUR Workshop Proceedings
DOI: 10.5281/zenodo.5006058

Reinforced Damage Minimization in Critical Events for Self-driving Vehicles

Auteurs: Francesco Merola; Fabrizio Falchi; Claudio Gennaro; Marco Di Benedetto
Publié dans: 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, Numéro 5, 2022, Page(s) 258-266, ISBN 978-989-758-555-5
Éditeur: SciTePress
DOI: 10.5220/0010908000003124

Open Challenges in Synthetic Speech Detection

Auteurs: Luca Cuccovillo, Christoforos Papastergiopoulos, Anastasios Vafeiadis, Artem Yaroshchuk, Patrick Aichroth, Konstantinos Votis, Dimitrios Tzovaras
Publié dans: Proceedings 2022 IEEE International Workshop on Information Forensics and Security (WIFS), 2022, ISBN 979-8-3503-0967-6
Éditeur: IEEE
DOI: 10.1109/wifs55849.2022.9975433

Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model

Auteurs: Zipeng Xu, Tianwei Lin, Hao Tang, Fu Li, Dongliang He, Nicu Sebe, Radu Timofte, Luc Van Gool, Errui Ding
Publié dans: Proceedings 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Page(s) 18208-18217, ISBN 978-1-6654-6946-3
Éditeur: IEEE
DOI: 10.1109/cvpr52688.2022.01769

Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism

Auteurs: Ioanna Gkartzonika, Nikolaos Gkalelis, Vasileios Mezaris
Publié dans: Proccedings European Conference on Computer Vision (ECCV 2022), 2022, ISBN 978-3-031-25085-9
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-25085-9_23

On Generalizing Permutation-Based Representations for Approximate Search

Auteurs: Lucia Vadicamo; Claudio Gennaro; Giuseppe Amato
Publié dans: Similarity Search and Applications, 14th International Conference, SISAP 2021, 2021, Page(s) 66-80, ISBN 978-3-030-89656-0
Éditeur: Springer, Cham
DOI: 10.1007/978-3-030-89657-7_6

Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models

Auteurs: Myles Foley, Ambrish Rawat, Taesung Lee, Yufang Hou, Gabriele Picco, Giulio Zizzo
Publié dans: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Numéro 1, 2023, Page(s) 7423–7442
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-long.410

MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification

Auteurs: Evan Dufraisse, Adrian Popescu, Julien Tourille, Armelle Brun, and Jerome Deshayes
Publié dans: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, Page(s) 8286–8305
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-long.461

Neighborhood Contrastive Learning for Novel Class Discovery

Auteurs: Zhun Zhong; Enrico Fini; Subhankar Roy; Zhiming Luo; Elisa Ricci; Nicu Sebe
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Page(s) 10862-10870
Éditeur: IEEE
DOI: 10.1109/cvpr46437.2021.01072

FAST DIFFERENTIABLE MATRIX SQUARE ROOT

Auteurs: Yue Song; Nicu Sebe; Wei Wang
Publié dans: 10th International Conference on Learning Representations (ICLR 2022), 2022
Éditeur: OpenReview.net
DOI: 10.5281/zenodo.6396093

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation

Auteurs: Yahui Liu; Enver Sangineto; Yajing Chen; Linchao Bao; Haoxian Zhang; Nicu Sebe; Bruno Lepri; Wei Wang; Marco De Nadai
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Page(s) 10780-10789
Éditeur: IEEE
DOI: 10.1109/cvpr46437.2021.01064

Few-Shot Bayesian Optimization with Deep Kernel Surrogates

Auteurs: Wistuba, Martin; Grabocka, Josif
Publié dans: International Conference on Learning Representations ICLR 2021, 2021
Éditeur: OpenReview.net
DOI: 10.5281/zenodo.4556929

Procedural Terrain Generation Using Generative Adversarial Networks

Auteurs: George Voulgaris; Ioannis Mademlis; Ioannis Pitas
Publié dans: 2021 29th European Signal Processing Conference (EUSIPCO), 2021
Éditeur: EURASIP
DOI: 10.23919/eusipco54536.2021.9616151

DivClust: Controlling Diversity in Deep Clustering

Auteurs: Ioannis Maniadis Metaxas*, Georgios Tzimiropoulos, Ioannis Patras
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Page(s) 3418-3428, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.00333

Summarizing Videos using Concentrated Attention and Considering the Uniqueness and Diversity of the Video Frames

Auteurs: Evlampios Apostolidis, Georgios Balaouras, Vasileios Mezaris, Ioannis Patras
Publié dans: Proceedings of the 2022 International Conference on Multimedia Retrieval (ICMR '22), 2022, Page(s) 407–415
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512527.3531404

Referencing in YouTube Knowledge Communication Videos

Auteurs: HaeEun Kim, Daniel Gatica-Perez
Publié dans: Proceedings of the 2023 ACM International Conference on Interactive Media Experiences (IMX '23), 2023, Page(s) 60-70, ISBN 979-8-4007-0028-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3573381.3596163

Secure Random Sampling in Differential Privacy

Auteurs: Holohan, Naoise; Braghin, Stefano
Publié dans: Computer Security – ESORICS 2021: 26th European Symposium on Research in Computer Security,, Numéro 2, 2021, Page(s) 523-542
Éditeur: Springer Nature
DOI: 10.1007/978-3-030-88428-4_26

Generative Personas That Behave and Experience Like Humans

Auteurs: Matthew Barthet, Ahmed Khalifa, Antonios Liapis, Georgios Yannakakis
Publié dans: Proceedings of the 17th International Conference on the Foundations of Digital Games (FDG '22), 2022, ISBN 978-1-4503-9795-7
Éditeur: Association for Computing Machinery
DOI: 10.1145/3555858.3555879

Predicting Player Engagement in Tom Clancy's The Division 2: A Multimodal Approach via Pixels and Gamepad Actions

Auteurs: Kosmas Pinitas, David Renaudie, Mike Thomsen, Matthew Barthet, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings of the 25th International Conference on Multimodal Interaction (ICMI '23), 2023, Page(s) 488–497, ISBN 979-8-4007-0055-2
Éditeur: Association for Computing Machinery
DOI: 10.1145/3577190.3614203

Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis

Auteurs: Hao Tang, Xiaojuan Qi, Guolei Sun, Dan Xu, Nicu Sebe, Radu Timofte, Luc Van Gool
Publié dans: Proceedings Eleventh International Conference on Learning Representations (ICLR 2023), 2023
Éditeur: OpenReview.net
DOI: 10.5281/zenodo.7858509

Seeding Diversity into AI Art

Auteurs: Marvin Zammit, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings 13th International Conference on Computational Creativity (ICCC’22), 2022, Page(s) 210-219, ISBN 978-989-54160-4-2
Éditeur: Association for Computational Creativity (ACC)
DOI: 10.48550/arxiv.2205.00804

Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods

Auteurs: Paweł Foszner; Agnieszka Szczęsna; Luca Ciampi; Nicola Messina; Adam Cygan; Bartosz Bizoń; Michał Cogiel; Dominik Golba; Elżbieta Macioszek; Michał Staniszewski
Publié dans: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023), Numéro 1, 2023, Page(s) 222-229, ISBN 978-989-758-634-7
Éditeur: SciTePress
DOI: 10.5220/0011691500003417

Learning Task-Independent Game State Representations from Unlabeled Images

Auteurs: Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings 2022 IEEE Conference on Games (CoG), 2022, Page(s) 88–95, ISBN 978-1-6654-5990-7
Éditeur: IEEE
DOI: 10.1109/cog51982.2022.9893648

Estimating continuous affect with label uncertainty

Auteurs: Foteinopoulou, Niki Maria; Tzelepis, Christos; Patras, Ioannis
Publié dans: 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII), 2021
Éditeur: IEEE
DOI: 10.1109/acii52823.2021.9597425

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization

Auteurs: Simone Barattin, Christos Tzelepis, Ioannis Patras, Nicu Sebe
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.00773

SkipW: Resource Adaptable RNN with Strict Upper Computational Limit

Auteurs: Tsiry Mayet, Anne Lambert, Pascal Leguyadec, Francoise Le Bolzer, François Schnitzler
Publié dans: 9th International Conference on Learning Representations (ICLR), 2021, 2021
Éditeur: OpenReview.net
DOI: 10.5281/zenodo.4911371

Attention Meets Post-hoc Interpretability: A Mathematical Perspective

Auteurs: Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Publié dans: Proceedings of the 41st International Conference on Machine Learning, Numéro 235, 2024, Page(s) 32781-32800
Éditeur: MLResearchPress

Recurrent Vision Transformer for Solving Visual Reasoning Problems

Auteurs: Nicola Messina, Giuseppe Amato, Fabio Carrara, Claudio Gennaro, Fabrizio Falchi
Publié dans: Proceedings 21st International Conference on Image Analysis and Processing – ICIAP 2022, 2022, Page(s) 50-61, ISBN 978-3-031-06433-3
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-06433-3_5

Adaptive Soft Contrastive Learning

Auteurs: Chen Feng, Ioannis Patras
Publié dans: Proceedings 26th International Conference on Pattern Recognition (ICPR 2022), 2022, ISBN 978-1-6654-9063-4
Éditeur: IEEE
DOI: 10.1109/icpr56361.2022.9956660

VISIONE: a large-scale video retrieval system with advanced search functionalities

Auteurs: Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Nicola Messina, Lucia Vadicamo, Claudio Vairo
Publié dans: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval (ICMR '23), 2023, Page(s) 649–653, ISBN 979-8-4007-0178-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3591106.3592226

Conditioned Image Retrieval for Fashion using Contrastive Learning and CLIP-based Features

Auteurs: Alberto Baldrati; Marco Bertini; Tiberio Uricchio; Alberto Del Bimbo
Publié dans: MMAsia '21: ACM Multimedia Asia, 2021, ISBN 978-1-4503-8607-4
Éditeur: Association for Computing Machinery
DOI: 10.1145/3469877.3493593

Evaluating Hebbian Learning in a Semi-supervised Setting

Auteurs: Gabriele Lagani; Fabrizio Falchi; Claudio Gennaro; Giuseppe Amato
Publié dans: Machine Learning, Optimization, and Data Science 7th International Conference, LOD 2021, Numéro 2, 2022, Page(s) 365-379, ISBN 978-3-030-95470-3
Éditeur: Springer Nature
DOI: 10.1007/978-3-030-95470-3_28

Learning from Label Relationships in Human Affect

Auteurs: Niki Maria Foteinopoulou, Ioannis Patras
Publié dans: Proceedings of the 30th ACM International Conference on Multimedia (MM '22), 2022, Page(s) 80–89, ISBN 978-1-4503-9203-7
Éditeur: Association for Computing Machinery
DOI: 10.1145/3503161.3548373

Face Verification with Challenging Imposters and Diversified Demographics

Auteurs: Adrian Popescu; Liviu-Daniel Ştefan; Jérôme Deshayes-Chossart; Bogdan Ionescu
Publié dans: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022
Éditeur: IEEE
DOI: 10.1109/wacv51458.2022.00122

Dataset Knowledge Transfer for Class-Incremental Learning without Memory

Auteurs: Habib Slim; Eden Belouadah; Adrian Popescu; Darian Onchis
Publié dans: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, Page(s) 3311-3320
Éditeur: IEEE
DOI: 10.1109/wacv51458.2022.00337

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

Auteurs: Yuyang Zhao, Zhun Zhong, Na Zhao, Nicu Sebe, Gim Hee Lee
Publié dans: Proceedings 17th European Conference on Computer Vision (ECCV 2022, 2022, Page(s) 535–552, ISBN 978-3-031-19783-3
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-19815-1_31

Unsupervised Domain Adaptation for Video Violence Detection in the Wild

Auteurs: Luca Ciampi , Carlos Santiago, Joao Costeira, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Publié dans: Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - IMPROVE, Numéro 1, 2023, Page(s) 37-46, ISBN 978-989-758-642-2
Éditeur: SciTePres
DOI: 10.5220/0011965300003497

A Graph Diffusion Scheme for Decentralized Content Search based on Personalized PageRank

Auteurs: Nikolaos Giatsoglou; Emmanouil Krasanakis; Symeon Papadopoulos; Ioannis Kompatsiaris
Publié dans: Proceedings 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops (ICDCSW), 2022, ISBN 978-1-6654-8879-2
Éditeur: IEEE
DOI: 10.1109/icdcsw56584.2022.00019

DeepFusion: Deep Ensembles for Domain Independent System Fusion

Auteurs: Mihai Gabriel Constantin, Liviu-Daniel Ștefan, Bogdan Ionescu
Publié dans: 27th International Conference on Multimedia Modeling, MMM 2021, 2021
Éditeur: Springer Nature
DOI: 10.1007/978-3-030-67832-6_20

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

Auteurs: Fengxiang Yang; Zhun Zhong; Zhiming Luo; Yuanzheng Cai; Yaojin Lin; Shaozi Li; Nicu Sebe
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021, ISBN 978-1-6654-4509-2
Éditeur: IEEE

Raising User Awareness about the Consequences of Online Photo Sharing

Auteurs: Hugo Schindler, Adrian Popescu, Khoa Nguyen, Jerome Deshayes-Chossart
Publié dans: ICMR '23: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, 2023, Page(s) 10-19, ISBN 979-8-4007-0178-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3591106.3592290

PEM360: a dataset of 360° videos with continuous physiological measurements, subjective emotional ratings and motion traces

Auteurs: Quentin Guimard, Florent Robert, Camille Bauce, Aldric Ducreux, Lucile Sassatelli, Hui-Yin Wu, Marco Winckler, Auriane Gros
Publié dans: Proceedings of the 13th ACM Multimedia Systems Conference (MMSys '22), 2022, Page(s) 252–258, ISBN 978-1-4503-9283-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3524273.3532895

Visual Objectification in Films: Towards a New AI Task for Video Interpretation

Auteurs: Julie Tores, Lucile Sassatelli, Hui-Yin Wu, Clement Bergman, Léa Andolfi, Victor Ecrement, Frédéric Precioso, Thierry Devars, Magali Guaresi, Virginie Julliard, Sarah Lecossais
Publié dans: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Numéro 29, 2024, Page(s) 10864-10874
Éditeur: IEEE
DOI: 10.1109/cvpr52733.2024.01033

Improving Query and Assessment Quality in Text-Based Interactive Video Retrieval Evaluation

Auteurs: Werner Bailer, Rahel Arnold, Vera Benz, Davide Alessandro Coccomini, Anastasios Gkagkas, Gylfi Þór Guðmundsson, Silvan Heller, Björn Þór Jónsson, Jakub Lokoc, Nicola Messina, Nick Pantelidis, Jiaxin Wu
Publié dans: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval (ICMR '23), 2023, Page(s) 597–601, ISBN 979-8-4007-0178-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3591106.3592281

The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild

Auteurs: Spiros Baxevanakis, Giorgos Kordopatis-Zilos, Panagiotis Galopoulos, Lazaros Apostolidis, Killian Levacher, Ipek Baris Schlicht, Denis Teyssou, Ioannis Kompatsiaris, Symeon Papadopoulos
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), 2022, Page(s) 59–68, ISBN 978-1-4503-9242-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533587

Leveraging Visual Attention for out-of-distribution Detection

Auteurs: Luca Cultrera, Lorenzo Seidenari, Alberto Del Bimbo
Publié dans: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Numéro 34, 2024, Page(s) 4449-4458
Éditeur: IEEE
DOI: 10.1109/iccvw60793.2023.00479

Evaluation and Comparison of CNN Visual Explanations for Histopathology

Auteurs: Mara Graziani, Thomas Lompech, Henning Müller, Vincent Andrearczyk
Publié dans: Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021
Éditeur: AAAI Press
DOI: 10.5281/zenodo.4545761

On the Generalizability of Two-dimensional Convolutional Neural Networks for Fake Speech Detection

Auteurs: Christoforos Papastergiopoulos, Anastasios Vafeiadis, Ioannis Papadimitriou, Konstantinos Votis, Dimitrios Tzovaras
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), 2022, Page(s) 3-9, ISBN 978-1-4503-9242-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533585

Consistent Game Content Creation via Function Calling for Large Language Models

Auteurs: Roberto Gallotta, Antonios Liapis, Georgios Yannakakis
Publié dans: 2024 IEEE Conference on Games (CoG), Numéro 36, 2024, Page(s) 1-4
Éditeur: IEEE
DOI: 10.1109/cog60054.2024.10645599

Examining European Press Coverage of the Covid-19 No-Vax Movement: An NLP Framework

Auteurs: David Alonso del Barrio, Daniel Gatica-Perez
Publié dans: Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation (MAD '23), 2023, Page(s) 52–59
Éditeur: Association for Computing Machinery
DOI: 10.1145/3592572.3592845

Detecting speaking persons in video

Auteurs: Hannes Fassold
Publié dans: 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), 2021
Éditeur: IEEE
DOI: 10.1109/mmsp53017.2021.9733466

Unveiling Real-Life Effects of Online Photo Sharing

Auteurs: Van-Khoa Nguyen; Adrian Popescu; Jérôme Deshayes-Chossart
Publié dans: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022
Éditeur: IEEE
DOI: 10.1109/wacv51458.2022.00391

Uncovering the Strength of Capsule Networks in Deepfake Detection

Auteurs: Dan-Cristian Stanciu, Bogdan Ionescu
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), 2022, Page(s) 69–77
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533581

A Detailed Overview of LeQua@CLEF 2022: Learning to Quantify

Auteurs: Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani, Gianluca Sperduti
Publié dans: Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum, 2022, Page(s) 1849-1868
Éditeur: CEUR-WS.org
DOI: 10.5281/zenodo.7090030

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

Auteurs: Guofeng Mei, Cristiano Saltori, Fabio Poiesi, Jian Zhang, Elisa Ricci, Nicu Sebe, Qiang Wu
Publié dans: Proccedings 33rd British Machine Vision Conference (BMVC 2022), 2022
Éditeur: BMVA Press
DOI: 10.5281/zenodo.7566058

Class-incremental Novel Class Discovery

Auteurs: Subhankar Roy, Mingxuan Liu, Zhun Zhong, Nicu Sebe, Elisa Ricci
Publié dans: Proceedings 17th European Conference on Computer Vision (ECCV 2022), 2022, Page(s) 317–333, ISBN 978-3-031-19783-3
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-19827-4_19

A Sea of Words: An In-Depth Analysis of Anchors for Text Data

Auteurs: Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Publié dans: Proceedings 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), 2023, Page(s) 4848-4879
Éditeur: PMLR

Approximate Nearest Neighbor Search on Standard Search Engines

Auteurs: Fabio Carrara, Lucia Vadicamo, Claudio Gennaro, Giuseppe Amato
Publié dans: Proceedings 15th International Conference on Similarity Search and Applications (SISAP 2022), Numéro 214-221, 2022, ISBN 978-3-031-17848-1
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-17849-8_17

SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise

Auteurs: Chen Feng, Georgios Tzimiropoulos, Ioannis Patras
Publié dans: Proceedings 33rd British Machine Vision Conference 2022 (BMVC 2022), 2022
Éditeur: BMVA Press

Locally Private Graph Neural Network

Auteurs: Sina Sajadmanesh, Daniel Gatica-Perez
Publié dans: 2021 ACM SIGSAC Conference on Computer and Communications Security (CCS '21), 2021, Page(s) 2130–2145
Éditeur: Association for Computing Machinery
DOI: 10.1145/3460120.3484565

Selecting A Diverse Set Of Aesthetically-Pleasing and Representative Video Thumbnails Using Reinforcement Learning

Auteurs: Evlampios Apostolidis,Georgios Balaouras, Vasileios Mezaris, Ioannis Patras
Publié dans: Proceedings 2023 IEEE International Conference on Image Processing (ICIP), 2023, ISBN 978-1-7281-9836-1
Éditeur: IEEE
DOI: 10.1109/icip49359.2023.10222743

Training Convolutional Neural Networks with Competitive Hebbian Learning Approaches

Auteurs: Gabriele Lagani; Fabrizio Falchi; Claudio Gennaro; Giuseppe Amato
Publié dans: Machine Learning, Optimization, and Data Science 7th International Conference, LOD 2021, Numéro 1, 2022, ISBN 978-3-030-95467-3
Éditeur: Springer
DOI: 10.1007/978-3-030-95467-3_2

A Qualitative Investigation of Optical Flow Algorithms for Video Denoising

Auteurs: Hannes Fassold
Publié dans: Proceedings of the Future Technologies Conference (FTC) 2022, Numéro 2, 2022, Page(s) 765–775, ISBN 978-3-031-18457-4
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-18458-1_52

Inplace knowledge distillation with teacher assistant for improved training of flexible deep neural networks

Auteurs: Ozerov, Alexey; Duong, Ngoc,
Publié dans: 29th European Signal Processing Conference, EUSIPCO 2021, Aug 2021, Dublin, Ireland, 2021, Page(s) 1356-1360, ISBN 978-9-0827-9706-0
Éditeur: EURASIP
DOI: 10.5281/zenodo.5047247

Partially Fake it Till you Make It: Mixing Real and Fake Thermal Images for Improved Object Detection

Auteurs: Francesco Bongini; Lorenzo Berlincioni; Marco Bertini; Alberto Del Bimbo
Publié dans: MM '21: Proceedings of the 29th ACM International Conference on Multimedia, 2021, Page(s) 5482–5490, ISBN 978-1-4503-8651-7
Éditeur: Association for Computing Machinery
DOI: 10.1145/3474085.3475679

The Florence 4D Facial Expression Dataset

Auteurs: Filippo Principi; Stefano Berretti; Claudio Ferrari; Naima Otberdout; Mohamed Daoudi; Alberto Del Bimbo
Publié dans: Proceedings 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG), 2023, ISBN 979-8-3503-4544-5
Éditeur: IEEE
DOI: 10.1109/fg57933.2023.10042606

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

Auteurs: Nan Pu , Zhun Zhong, Nicu Sebe
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Page(s) 7579-7588, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.00732

How Did Europe's Press Cover Covid-19 Vaccination News? A Five-Country Analysis

Auteurs: David Alonso del Barrio, Daniel Gatica-Perez
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), 2022, ISBN 978-1-4503-9242-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533588

Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language

Auteurs: Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi, Tomás Rebok
Publié dans: Proceedings 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '23), 2023, Page(s) 2420–2425, ISBN 978-1-4503-9408-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3539618.3592069

Efficient Training of Visual Transformers with Small Datasets

Auteurs: Yahui Liu; Enver Sangineto; Wei Bi; Niculae Sebe; Bruno Lepri; Marco de Nadai
Publié dans: Advances in Neural Information Processing Systems 34 (NeurIPS 2021), Numéro 34, 2021
Éditeur: Curran Associates, Inc.
DOI: 10.5281/zenodo.6363240

Tackling Bias in the Dice Similarity Coefficient: Introducing NDSC for White Matter Lesion Segmentation

Auteurs: Vatsal Raina, Nataliia Molchanova, Mara Graziani, Andrey Malinin, Henning Muller, Meritxell Bach Cuadra, Mark Gales
Publié dans: Proceedings 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), 2023, ISBN 978-1-6654-7359-0
Éditeur: IEEE
DOI: 10.1109/isbi53787.2023.10230755

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

Auteurs: Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov, Nicu Sebe, Ivan Oseledets
Publié dans: Proceedings 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Page(s) 7399-7409, ISBN 978-1-6654-6946-3
Éditeur: New Orleans, LA, USA
DOI: 10.1109/cvpr52688.2022.00726

Deep Features for CBIR with Scarce Data using Hebbian Learning

Auteurs: Gabriele Lagani, Davide Bacciu, Claudio Gallicchio, Fabrizio Falchi, Claudio Gennaro, Giuseppe AMato
Publié dans: Proceedings of the 19th International Conference on Content-based Multimedia Indexing (CBMI '22), 2022, Page(s) 136–141, ISBN 978-1-4503-9720-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3549555.3549587

Controllable Exploration of a Design Space via Interactive Quality Diversity

Auteurs: Konstantinos Sfikas, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (GECCO '23 Companion), 2023, Page(s) 167–170, ISBN 979-8-4007-0120-7
Éditeur: Association for Computing Machinery
DOI: 10.1145/3583133.3590616

OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in an Open World

Auteurs: Zhun Zhong; Linchao Zhu; Zhiming Luo; Shaozi Li; Yi Yang; Nicu Sebe
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Page(s) 9457-9465
Éditeur: IEEE Computer Society
DOI: 10.1109/cvpr46437.2021.00934

Fast Video Visual Quality and Resolution Improvement using SR-UNet

Auteurs: Federico Vaccaro; Marco Bertini; Tiberio Uricchio; Alberto Del Bimbo
Publié dans: MM '21: Proceedings of the 29th ACM International Conference on Multimedia, 2021, Page(s) 1221-1229
Éditeur: Association for Computing Machinery
DOI: 10.1145/3474085.3475683

MC-GTA: A Synthetic Benchmark for Multi-Camera Vehicle Tracking

Auteurs: Luca Ciampi, Nicola Messina, Gaetano Emanuele Valenti, Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro
Publié dans: Proceedings International Conference on Image Analysis and Processing (ICIAP 2023), 2023, Page(s) 16–327, ISBN 978-3-031-43147-0
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-43148-7_27

The AI4Media Project: Use of Next-Generation Artificial Intelligence Technologies for Media Sector Applications

Auteurs: Filareti Tsalakanidou, Symeon Papadopoulos, Vasileios Mezaris, Ioannis Kompatsiaris, Birgit Gray, Danae Tsabouraki, Maritini Kalogerini, Fulvio Negro, Maurizio Montagnuolo, Jesse de Vos, Philo van Kemenade, Daniele Gravina, Rémi Mignot, Alexey Ozerov, Francois Schnitzler, Artur Garcia-Saez, Georgios N. Yannakakis, Antonios Liapis, Georgi Kostadinov
Publié dans: Artificial Intelligence Applications and Innovations. AIAI 2021. IFIP Advances in Information and Communication Technology, Numéro 627, 2021, Page(s) 81-93, ISBN 978-3-030-79149-0
Éditeur: Springer
DOI: 10.1007/978-3-030-79150-6_7

A Spatio- Temporal Attentive Network for Video-Based Crowd Counting

Auteurs: Marco Avvenuti; Marco Bongiovanni; Luca Ciampi; Fabrizio Falchi; Claudio Gennaro; Nicola Messina
Publié dans: Proceedings 2022 IEEE Symposium on Computers and Communications (ISCC), 2022, ISBN 978-1-6654-9793-0
Éditeur: IEEE
DOI: 10.1109/iscc55528.2022.9913019

AutoGF: Runtime Graph Filter Tuning for Community Node Ranking

Auteurs: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris
Publié dans: Proceedings of The Eleventh International Conference on Complex Networks and their Applications (COMPLEX NETWORKS 2022 ), Numéro 2, 2022, Page(s) 189–202, ISBN 978-3-031-21130-0
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-21131-7_15

Unsupervised Domain Adaptation for Video Transformers in Action Recognition

Auteurs: Victor G. Turrisi da Costa, Paolo Rota, Thiago Oliveira-Santos, Nicu Sebe, Vittorio Murino, Elisa Ricci
Publié dans: Proceedings 2022 26th International Conference on Pattern Recognition (ICPR), 2022, Page(s) 1258-1265, ISBN 978-1-6654-9062-7
Éditeur: IEEE Computer Society}
DOI: 10.1109/icpr56361.2022.9956679

The 2021 ImageCLEF Benchmark: Multimedia Retrieval in Medical, Nature, Internet and Social Media Applications

Auteurs: Bogdan Ionescu, Henning Müller, Renaud Péteri, Asma Ben Abacha, Dina Demner-Fushman, Sadid A. Hasan, Mourad Sarrouti, Obioma Pelka,Christoph M. Friedrich, Alba G. Seco de Herrera, Janadhip Jacutprakart, Vassili Kovalev, Serge Kozlovski, Vitali Liauchuk, Yashin Dicente Cid,Jon Chamberlain, Adrian Clark, Antonio Campello, Hassan Moustahfid, Thomas Oliver, Abigail Schulz, Paul Brie, Raul Berari, Di
Publié dans: European Conference on Information Retrieval - ECIR 2021: Advances in Information Retrieval, 2021, Page(s) 616-623, ISBN 978-3-030-72240-1
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-72240-1_72

Game State Learning via Game Scene Augmentation

Auteurs: Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings of the 17th International Conference on the Foundations of Digital Games (FDG '22), 2022, ISBN 978-1-4503-9795-7
Éditeur: Association for Computing Machinery
DOI: 10.1145/3555858.3555902

Exploiting One-class classification optimization objectives for increasing adversarial robustness

Auteurs: Vasileios Mygdalis, Ioannis Pitas
Publié dans: Proceedings 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/icassp49357.2023.10095088

AVAE: Adversarial Variational Auto Encoder

Auteurs: Plumerault, Antoine; Le Borgne, Hervé; Hudelot, Céline
Publié dans: 2020 25th International Conference on Pattern Recognition (ICPR), 2021
Éditeur: IEEE
DOI: 10.1109/icpr48806.2021.9412727

Sharpening Local Interpretable Model-agnostic Explanations for Histopathology: Improved Understandability and Reliability

Auteurs: Mara Graziani; Iam Palatnik de Sousa; Marley M.B.R. Vellasco; Eduardo Costa da Silva; Henning Müller; Vincent Andrearczyk
Publié dans: International Conference on Medical Image Computing and Computer Assisted Intervention - MICCAI 2021, 2021, Page(s) 540-549
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-87199-4_51

Towards General Models of Player Experience: A Study Within Genres

Auteurs: David Melhart; Antonios Liapis; Georgios N. Yannakakis
Publié dans: 2021 IEEE Conference on Games (CoG), 2021
Éditeur: IEEE
DOI: 10.1109/CoG52621.2021.9618902

AdvisIL - A Class-Incremental Learning Advisor

Auteurs: Eva Feillet, Grégoire Petit, Adrian Popescu, Marina Reyboz, Céline Hudelot
Publié dans: Proceedings 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, Page(s) 2399-2408, ISBN 978-1-6654-9346-8
Éditeur: IEEE
DOI: 10.1109/wacv56688.2023.00243

A Task Category Space for User-Centric Comparative Multimedia Search Evaluations

Auteurs: Jakub Lokoč; Werner Bailer; Kai Uwe Barthel; Cathal Gurrin; Silvan Heller; Björn Þór Jónsson; Ladislav Peška; Luca Rossetto; Klaus Schoeffmann; Lucia Vadicamo; Stefanos Vrochidis; Jiaxin Wu
Publié dans: MultiMedia Modeling 28th International Conference, MMM 2022, Numéro 1, 2022, Page(s) 193–204, ISBN 978-3-030-98358-1
Éditeur: Springer Nature
DOI: 10.1007/978-3-030-98358-1_16

CrowdSim2: An Open Synthetic Benchmark for Object Detectors

Auteurs: Paweł Foszner; Agnieszka Szczęsna; Luca Ciampi; Nicola Messina; Adam Cygan; Bartosz Bizoń; Michał Cogiel; Dominik Golba; Elżbieta Macioszek; Michał Staniszewski
Publié dans: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023), Numéro 3, 2023, Page(s) 676-683, ISBN 978-989-758-634-7
Éditeur: SciTePress
DOI: 10.5220/0011692500003417

Environment Classification via Blind Roomprints Estimation

Auteurs: Malte Baum, Luca Cuccovillo, Artem Yaroshchuk, Patrick Aichroth
Publié dans: Proceedings 2022 IEEE International Workshop on Information Forensics and Security (WIFS), 2022, ISBN 979-8-3503-0967-6
Éditeur: IEEE
DOI: 10.1109/wifs55849.2022.9975411

ObjectGraphs: Using Objects and a Graph Convolutional Network for the Bottom-up Recognition and Explanation of Events in Video

Auteurs: Gkalelis, Nikolaos; Goulas, Andreas; Galanopoulos, Damianos; Mezaris, Vasileios
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021, Page(s) 3370-3378, ISBN 978-1-6654-4899-4
Éditeur: IEEE
DOI: 10.1109/cvprw53098.2021.00376

FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Level

Auteurs: Gabriele Lagani, Claudio Gennaro, Hannes Fassold, Giuseppe Amato
Publié dans: Proceedings 15th International Conference on Similarity Search and Applications (SISAP 2022), 2022, Page(s) 251–264, ISBN 978-3-031-17848-1
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-17849-8_20

Disentangling Neuron Representations with Concept Vectors

Auteurs: Laura O' Mahony, Vincent Andrearczyk, Henning Müller, Mara Graziani
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, Page(s) 3770-3775, ISBN 979-8-3503-0249-3
Éditeur: IEEE
DOI: 10.1109/cvprw59228.2023.00390

Budget-Aware Pruning for Multi-domain Learning

Auteurs: Samuel Felipe dos Santos, Rodrigo Berriel, Thiago Oliveira-Santos, Nicu Sebe, Jurandy Almeida
Publié dans: 22nd International Conference on Image Analysis and Processing (ICIAP 2023), 2023, Page(s) 477–489, ISBN 978-3-031-43152-4
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-43153-1_40

Domain Adaptation for Traffic Density Estimation

Auteurs: Luca Ciampi, Carlos Santiago, Joao Costeira, Claudio Gennaro, Giuseppe Amato
Publié dans: Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, 2021, Page(s) 185-195, ISBN 978-989-758-488-6
Éditeur: SciTePress
DOI: 10.5220/0010303401850195

Forecasting Future Instance Segmentation with Learned Optical Flow and Warping

Auteurs: Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
Publié dans: Proceedings 21st International Conference on Image Analysis and Processing (ICIAP 2022), Numéro 3, 2022, ISBN 978-3-031-06432-6
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-06433-3_30

Multiple Future Prediction Leveraging Synthetic Trajectories

Auteurs: Lorenzo Berlincioni; Federico Becattini; Lorenzo Seidenari; Alberto Del Bimbo
Publié dans: 2020 25th International Conference on Pattern Recognition (ICPR), 2021, Page(s) 6081-6088, ISBN 978-1-7281-8808-9
Éditeur: IEEE
DOI: 10.1109/icpr48806.2021.9412158

Eliciting and Annotating Emotion in Virtual Spaces

Auteurs: Emmanouil Xylakis, Ali Najm, Despina Michael-Grigoriou, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023), 2023, Page(s) 841–850, ISBN 9789491207341
Éditeur: eCAADe (Education and research in Computer Aided Architectural Design in Europe)
DOI: 10.52842/conf.ecaade.2023.2.841

AIMH at SemEval-2021 Task 6: Multimodal Classification Using an Ensemble of Transformer Models

Auteurs: Nicola Messina, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Publié dans: Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), 2021, Page(s) 1020–1026
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.semeval-1.140

Framing the News: From Human Perception to Large Language Model Inferences

Auteurs: David Alonso del Barrio, Daniel Gatica-Perez
Publié dans: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval (ICMR '23), 2023, Page(s) 627–635, ISBN 979-8-4007-0178-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3591106.3592278

Neuromorphic Event-based Facial Expression Recognition

Auteurs: Lorenzo Berlincioni, Luca Cultrera, Chiara Albisani, Lisa Cresti, Andrea Leonardo, Sara Picchioni, Federico Becattini, Alberto Del Bimbo
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, Page(s) 4109-4119, ISBN 979-8-3503-0249-3
Éditeur: IEEE
DOI: 10.1109/cvprw59228.2023.00432

DISPUTool 2.0: A Modular Architecture for Multi-Layer Argumentative Analysis of Political Debates

Auteurs: Pierpaolo Goffredo, Elena Cabrio, Serena Villata, Shohreh Haddadan,Jhonatan Torres Sanchez
Publié dans: Proceedings 37th AAAI Conference on Artificial Intelligence (AAAI-23), 2023, Page(s) 16431-16433, ISBN 978-1-57735-880-0
Éditeur: AAAI Press
DOI: 10.1609/aaai.v37i13.27069

Dual-Head Contrastive Domain Adaptation for Video Action Recognition

Auteurs: Victor G. Turrisi da Costa; Giacomo Zara; Paolo Rota; Thiago Oliveira-Santos; Niculae Sebe; Vittorio Murino; Elisa Ricci
Publié dans: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, Page(s) 2234-2243, ISBN 978-1-6654-0915-5
Éditeur: IEEE
DOI: 10.1109/WACV51458.2022.00229

Using Vision Transformers and Memorable Moments for the Prediction of Video Memorability

Auteurs: M.G. Constantin; B. Ionescu
Publié dans: MediaEval 2021 Workshop, 2021
Éditeur: MediaEval Multimedia Benchmark
DOI: 10.5281/zenodo.6366900

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

Auteurs: Chen Feng, Ioannis Patras
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Page(s) 19913-19922, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.01907

Multiplayer Tension In the Wild: A Hearthstone Case

Auteurs: Paris Mavromoustakos-Blom, Dávid Melhárt, Antonios Liapis, Georgios N. Yannakakis, Sander Bakkes, Pieter Spronck
Publié dans: Proceedings of the 18th International Conference on the Foundations of Digital Games (FDG '23), 2023, ISBN 978-1-4503-9855-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3582437.3582440

The Devil Is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models

Auteurs: Ambrish Rawat, Killian Levacher, Mathieu Sinn
Publié dans: Proceedings 27th European Symposium on Research in Computer Security (ESORICS 2022), 2022, ISBN 978-3-031-17143-7
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-17143-7_41

Learning to Quantify: Methods and Applications (LQ 2021)

Auteurs: Juan José del Coz, Pablo González, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021, Page(s) 4874–4875, ISBN 978-1-4503-8446-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3459637.3482040

When & How to Transfer with Transfer Learning

Auteurs: Adrian Tormos, Dario Garcia-Gasulla, Victor Gimenez-Abalos, Sergio Alvarez-Napagao
Publié dans: Has it Trained Yet? HITY Workshop NeurIPS 2022, 2022
Éditeur: OpenReview.net

LeQua@CLEF2022: Learning to Quantify

Auteurs: Andrea Esuli, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: Advances in Information Retrieval: 44th European Conference on IR Research, ECIR 2022, Numéro 2, 2022, Page(s) 374–381, ISBN 978-3-030-99738-0
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-030-99739-7_47

AniFormer: Data-driven 3D Animation with Transformer

Auteurs: Chen, Haoyou; Tang, Hao; Sebe, Nicu; Zhao, Guoying
Publié dans: https://www.bmvc2021-virtualconference.com/assets/supp/0130_supp.pdf, 2021
Éditeur: British Machine Vision Association
DOI: 10.5281/zenodo.5901777

Explaining video summarization based on the focus of attention

Auteurs: Evlampios Apostolidis, Georgios Balaouras, Vasileios Mezaris, Ioannis Patras
Publié dans: Proceedings 2022 IEEE International Symposium on Multimedia (ISM), 2022, ISBN 978-1-6654-7173-2
Éditeur: IEEE
DOI: 10.1109/ism55400.2022.00029

Ordinal Quantification Through Regularization

Auteurs: Mirko Bunse, Alejandro Moreo, Fabrizio Sebastiani,Martin Senz
Publié dans: Proccedings Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2022), 2023, Page(s) 36-52, ISBN 978-3-031-26418-4
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-26419-1_3

Deep Reinforcement Learning with semi-expert distillation for autonomous UAV cinematography

Auteurs: Andreas Sochopoulos, Ioannis Mademlis, Evangelos Charalampakis, Sotirios Papadopoulos, Ioannis Pitas
Publié dans: Proceedings 2023 IEEE International Conference on Multimedia and Expo (ICME), 2023, ISBN 978-1-6654-6892-3
Éditeur: IEEE
DOI: 10.1109/icme55011.2023.00230

Heterogeneous document embeddings for cross-lingual text classification

Auteurs: Alejandro Moreo, Andrea Pedrotti, Fabrizio Sebastiani
Publié dans: SAC '21: Proceedings of the 36th Annual ACM Symposium on Applied Computing, 2021, Page(s) 685–688, ISBN 978-1-4503-8104-8
Éditeur: Association for Computing Machinery
DOI: 10.1145/3412841.3442093

On The Link Between Emotion, Attention And Content In Virtual Immersive Environments

Auteurs: Quentin Guimard, Florent Robert, Camille Bauce, Aldric Ducreux, Lucile Sassatelli, Hui-Yin Wu, Marco Winckler, Auriane Gros
Publié dans: Proceedings 2022 IEEE International Conference on Image Processing (ICIP), 2022, ISBN 978-1-6654-9621-6
Éditeur: IEEE
DOI: 10.1109/icip46576.2022.9897903

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning

Auteurs: Grégoire Petit; Adrian Popescu; Hugo Schindler; David Picard; Bertrand Delezoide
Publié dans: Proceedings 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, Page(s) 3911-3920, ISBN 978-1-6654-9347-5
Éditeur: IEEE
DOI: 10.1109/wacv56688.2023.00390

Contrastive Learning of Generalized Game Representations

Auteurs: Chintan Trivedi; Antonios Liapis; Georgios N. Yannakakis
Publié dans: 2021 IEEE Conference on Games (CoG), 2021
Éditeur: IEEE
DOI: 10.1109/CoG52621.2021.9619107

Pairwise Ranking Network for Affect Recognition

Auteurs: Georgios Zoumpourlis; Ioannis Patras
Publié dans: 2021 International Conference on Learning Representations (ICLR2021), 2021
Éditeur: OpenReview.net
DOI: 10.5281/zenodo.5550449

Making Few-shot Object Detection Simpler and Less Frustrating

Auteurs: Werner Bailer
Publié dans: MultiMedia Modeling 28th International Conference, MMM 2022, Numéro 2, 2022, ISBN 978-3-030-98355-0
Éditeur: Springer Nature
DOI: 10.1007/978-3-030-98355-0_37

Speaker-Independent Microphone Identification in Noisy Conditions

Auteurs: Antonio Giganti, Luca Cuccovillo, Paolo Bestagini, Patrick Aichroth, Stefano Tubaro
Publié dans: Proceedings 2022 30th European Signal Processing Conference (EUSIPCO), 2023, ISBN 978-1-6654-6799-5
Éditeur: European Association for Signal Processing (EURASIP)
DOI: 10.23919/eusipco55093.2022.9909800

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

Auteurs: Zhun Zhong, Yuyang Zhao, Gim Hee Lee, Nicu Sebe
Publié dans: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), Numéro 35, 2022, ISBN 9781713871088
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.5281/zenodo.7566090

SegmentCodeList: Unsupervised Representation Learning for Human Skeleton Data Retrieval

Auteurs: Jan Sedmidubsky, Fabio Carrara & Giuseppe Amato
Publié dans: Proceedings 45th European Conference on Information Retrieval (ECIR 2023), 2023, Page(s) 110–124, ISBN 978-3-031-28237-9
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-28238-6_8

Automatic Detection of Bot-generated Tweets

Auteurs: Julien Tourille, Babacar Sow, Adrian Popescu
Publié dans: Proceedings of the 1st International Workshop on Multimedia AI against Disinformation (MAD '22), 2022, Page(s) 44–51, ISBN 978-1-4503-9242-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3512732.3533584

Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning

Auteurs: Fengxiang Yang, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Shaozi Li, Nicu Sebe, Shin’ichi Satoh
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 35, 2021, Page(s) 3128-3135
Éditeur: PKP Publishing Services Network
DOI: 10.5281/zenodo.5018218

Health Talk: Understanding Practices of Popular Professional YouTubers

Auteurs: Thanh-Trung Phan, Chloé Michoud, Lucia Volpato, MaríA Del RíO Carral, Daniel Gatica-Perez
Publié dans: Proceedings of the 21st International Conference on Mobile and Ubiquitous Multimedia (MUM '22), 2022, Page(s) 218–230, ISBN 978-1-4503-9820-6
Éditeur: Association for Computing Machinery
DOI: 10.1145/3568444.3568453

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Auteurs: Yuyang Zhao; Zhun Zhong; Fengxiang Yang; Zhiming Luo; Yaojin Lin; Shaozi Li; Nicu Sebe
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Page(s) 6273-6282
Éditeur: IEEE Computer Society
DOI: 10.1109/cvpr46437.2021.00621

Self-Supervised Video Similarity Learning

Auteurs: Giorgos Kordopatis-Zilos, Giorgos Tolias, Christos Tzelepis, Ioannis Kompatsiaris, Ioannis Patras, Symeon Papadopoulos
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, ISBN 979-8-3503-0249-3
Éditeur: IEEE
DOI: 10.1109/cvprw59228.2023.00504

Transformer Reasoning Network for Image-Text Matching and Retrieval

Auteurs: Nicola Messina, Fabrizio Falchi, Andrea Esuli, Giuseppe Amato
Publié dans: 2020 25th International Conference on Pattern Recognition (ICPR), 2021, ISBN 978-1-7281-8808-9
Éditeur: IEEE
DOI: 10.1109/icpr48806.2021.9413172

Novel Class Discovery in Semantic Segmentation

Auteurs: Yuyang Zhao, Zhun Zhong, Nicu Sebe, Gim Hee Lee
Publié dans: Proceedings 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Page(s) 4330-4339, ISBN 978-1-6654-6946-3
Éditeur: IEEE
DOI: 10.1109/cvpr52688.2022.00430

PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

Auteurs: James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis Nicolaou, Ioannis Patras
Publié dans: Proceedings 11th International Conference on Learning Representations (ICLR2023), 2023
Éditeur: OpenReview.net

SMACE: A New Method for the Interpretability of Composite Decision Systems

Auteurs: Gianluigi Lopardo, Damien Garreau, Frédéric Precioso, Greger Ottosson
Publié dans: Proceedings Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2022), 2022, Page(s) 325–339, ISBN 978-3-031-26386-6
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-26387-3_20

Contrastive Supervised Distillation for Continual Representation Learning

Auteurs: Tommaso Barletti, Niccoló Biondi, Federico Pernici, Matteo Bruni, Alberto Del Bimbo
Publié dans: Proceedings 21st International Conference on Image Analysis and Processing (ICIAP 2022), 2022, Page(s) 597–609, ISBN 978-3-031-06426-5
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-06427-2_50

Neural Knowledge Transfer for Sentiment Analysis in Texts with Figurative Language

Auteurs: Dionysios Karamouzas; Ioannis Mademlis; Ioannis Pitas
Publié dans: Proceedings 2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP), 2022, ISBN 978-1-6654-8548-7
Éditeur: IEEE
DOI: 10.1109/mlsp55214.2022.9943314

Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?

Auteurs: Yue Song; Niculae Sebe; Wei Wang
Publié dans: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021, ISBN 978-1-6654-2812-5
Éditeur: IEEE
DOI: 10.1109/ICCV48922.2021.00115

Re-assessing the “Classify and Count” Quantification Method

Auteurs: Moreo, Alejandro; Sebastiani, Fabrizio
Publié dans: European Conference on Information Retrieval ECIR 2021: Advances in Information Retrieval, 2021, Page(s) 75-91, ISBN 978-3-030-72240-1
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-72240-1_6

Knowledge-Driven Active Learning

Auteurs: Gabriele Ciravegna, Frédéric Precioso, Alessandro Betti, Kevin Mottin, Marco Gori
Publié dans: Proceedings Joint European Conference on Machine Learning and Knowledge Discovery in Databases (CML PKDD 2023), 2023, Page(s) 38-54, ISBN 978-3-031-43411-2
Éditeur: Springer-Verlag
DOI: 10.1007/978-3-031-43412-9_3

Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction

Auteurs: Guanglei Yang; Hao Tang; Mingli Ding; Niculae Sebe; Elisa Ricci
Publié dans: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021, ISBN 978-1-6654-2812-5
Éditeur: IEEE
DOI: 10.1109/ICCV48922.2021.01596

StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment

Auteurs: Stella Bounareli, Christos Tzelepis, Vasileios Argyriou, Ioannis Patras, Georgios Tzimiropoulos
Publié dans: Proceedings 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG), 2023, ISBN 979-8-3503-4544-5
Éditeur: IEEE
DOI: 10.1109/fg57933.2023.10042744

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

Auteurs: Sina Sajadmanesh, Ali Shahin Shamsabadi, Aurélien Bellet, Daniel Gatica-Perez
Publié dans: Proceedings of the 32nd USENIX Security Symposium, 2023
Éditeur: USENIX
DOI: 10.5281/zenodo.7554787

Adversarial Unsupervised Video Summarization Augmented With Dictionary Loss

Auteurs: Michail Kaseris; Ioannis Mademlis; Ioannis Pitas
Publié dans: 2021 IEEE International Conference on Image Processing (ICIP), 2021, Page(s) 2683-2687
Éditeur: IEEE
DOI: 10.1109/icip42928.2021.9506088

Monte Carlo Elites: Quality-Diversity Selection as a Multi-Armed Bandit Problem

Auteurs: Sfikas, Konstantinos; Liapis, Antonios; Yannakakis, Georgios N.
Publié dans: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '21), 2021, Page(s) 180-188
Éditeur: Association for Computing Machinery (ACM)
DOI: 10.1145/3449639.3459321

People@Places and ToDY: Two Datasets for Scene Classification in Media Production and Archiving

Auteurs: Werner Bailer, Hannes Fassold
Publié dans: Proceedings 29th International Conference on Multimedia Modeling (MMM 2023), Numéro 489–501, 2022, ISBN 978-3-031-27076-5
Éditeur: Springer-Verlag, Berlin, Heidelberg
DOI: 10.1007/978-3-031-27077-2_38

Graph Transformer GANs for Graph-Constrained House Generation

Auteurs: Hao Tang, Zhenyu Zhang, Humphrey Shi, Bo Li,,Ling Shao, Nicu Sebe, Radu Timofte, Luc Van Gool
Publié dans: Proceedings 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Page(s) 2173-2182, ISBN 979-8-3503-0129-8
Éditeur: IEEE
DOI: 10.1109/cvpr52729.2023.00216

Learning to Detect Fallen People in Virtual Worlds

Auteurs: Fabio Carrara; Lorenzo Pasco; Claudio Gennaro; Fabrizio Falchi
Publié dans: Proceedings of the 19th International Conference on Content-based Multimedia Indexing (CBMI '22), 2022, Page(s) 126–130, ISBN 978-1-4503-9720-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3549555.3549573

Introducing K-Anonymity Principles to Adversarial Attacks for Privacy Protection in Image Classification Problems

Auteurs: Vasileios Mygdalis, Anastasios Tefas, Ioannis Pitas
Publié dans: 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), 2021, ISBN 9781665411844
Éditeur: IEEE
DOI: 10.1109/mlsp52302.2021.9596565

Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation

Auteurs: Ren, Bin; Tang, Hao; Sebe, Nicu
Publié dans: 32nd British Machine Vision Conference, 2021
Éditeur: British Machine Vision Association
DOI: 10.5281/zenodo.5901781

Go-Blend Behavior and Affect

Auteurs: Matthew Barthet; Antonios Liapis; Georgios N. Yannakakis
Publié dans: 2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), 2021
Éditeur: IEEE
DOI: 10.1109/ACIIW52867.2021.9666376

Supervised Contrastive Learning for Affect Modelling

Auteurs: Kosmas Pinitas, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
Publié dans: Proceedings of the 2022 International Conference on Multimodal Interaction (ICMI '22), 2022, Page(s) 531–539, ISBN 978-1-4503-9390-4
Éditeur: Association for Computing Machinery
DOI: 10.1145/3536221.3556584

Defending Neural ODE Image Classifiers from Adversarial Attacks with Tolerance Randomization

Auteurs: Fabio Carrara, Roberto Caldelli, Fabrizio Falchi, Giuseppe Amato
Publié dans: Pattern Recognition. ICPR International Workshops and Challenges, 2021, Page(s) 425-438, ISBN 978-3-030-68763-2
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-68780-9_35

Detic-Track: Robust Detection and Tracking of Objects in Video

Auteurs: Hannes Fassold
Publié dans: Proceedings 2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2022, ISBN 978-1-6654-7218-0
Éditeur: IEEE
DOI: 10.1109/icmew56448.2022.9859437

Autoencoder-based Data Augmentation for Deepfake Detection

Auteurs: Dan-Cristian Stanciu, Bogdan Ionescu
Publié dans: Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation (MAD '23), 2023, Page(s) 19-27, ISBN 979-8-4007-0187-0
Éditeur: Association for Computing Machinery
DOI: 10.1145/3592572.3592840

VISIONE at Video Browser Showdown 2022

Auteurs: Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Nicola Messina, Lucia Vadicamo, Claudio Vairo
Publié dans: Proceedings 28th International Conference on MultiMedia Modeling (MMM 2022), Numéro 2, 2022, Page(s) 543–548, ISBN 978-3-030-98355-0
Éditeur: Springer Cham
DOI: 10.1007/978-3-030-98355-0_52

QuaPy: A Python-Based Framework for Quantification

Auteurs: Alejandro Moreo, Andrea Esuli, and Fabrizio Sebastiani
Publié dans: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021, Page(s) 4534–4543
Éditeur: Association for Computing Machinery
DOI: 10.1145/3459637.3482015

WarpedGANSpace: Finding non-linear RBF paths in GAN latent space

Auteurs: Tzelepis, Christos; Tzimiropoulos, Georgios; Patras, Ioannis
Publié dans: 2021 IEEE/CVF International Conference on Computer Vision (ICCV2021), 2021, Page(s) 6373-6382, ISBN 978-1-6654-2812-5
Éditeur: IEEE
DOI: 10.1109/iccv48922.2021.00633

PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation

Auteurs: Bin Ren, Hao Tang, Yiming Wang, Xia Li, Wei Wang, Nicu Sebe
Publié dans: Proceedings ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/icassp49357.2023.10095449

AffectGAN: Affect-Based Generative Art Driven by Semantics

Auteurs: Theodoros Galanos; Antonios Liapis; Georgios N. Yannakakis
Publié dans: 2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), 2021, Page(s) 1-7, ISBN 978-1-6654-0021-3
Éditeur: IEEE
DOI: 10.1109/ACIIW52867.2021.9666317

Exploiting Caption Diversity for Unsupervised Video Summarization

Auteurs: Michail Kaseris, Ioannis Mademlis, Ioannis Pitas
Publié dans: Proceedings 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, ISBN 978-1-6654-0541-6
Éditeur: IEEE
DOI: 10.1109/icassp43922.2022.9747592

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

Auteurs: Subhankar Roy; Evgeny Krivosheev; Zhun Zhong; Nicu Sebe; Elisa Ricci
Publié dans: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Page(s) 5347-5356, ISSN 2575-7075
Éditeur: IEEE
DOI: 10.1109/cvpr46437.2021.00531

SMART360: Simulating Motion prediction and Adaptive bitRate sTrategies for 360° video streaming

Auteurs: Quentin Guimard, Lucile Sassatelli
Publié dans: Proceedings of the 14th Conference on ACM Multimedia Systems (MMSys '23), 2023, Page(s) 384–390, ISBN 979-8-4007-0148-1
Éditeur: Association for Computing Machinery
DOI: 10.1145/3587819.3592547

Deep variational learning for multiple trajectory prediction of 360° head movements

Auteurs: Quentin Guimard, Lucile Sassatelli, Francesco Marchetti, Federico Becattini, Lorenzo Seidenari
Publié dans: Proceedings of the 13th ACM Multimedia Systems Conference (MMSys '22), 2022, Page(s) 2–26, ISBN 978-1-4503-9283-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3524273.3528176

Effects of Emotions on Head Motion Predictability in 360° Videos

Auteurs: Quentin Guimard, Lucile Sassatelli
Publié dans: Proceedings of the 14th International Workshop on Immersive Mixed and Virtual Environment Systems (MMVE '22), 2022, Page(s) 37–43, ISBN 978-1-4503-9382-9
Éditeur: Association for Computing Machinery
DOI: 10.1145/3534086.3534335

Language Based Image Quality Assessment

Auteurs: Leonardo Galteri; Lorenzo Seidenari; Pietro Bongini; Marco Bertini; Alberto Del Bimbo
Publié dans: MMAsia '21: ACM Multimedia Asia, 2021, ISBN 978-1-4503-8607-4
Éditeur: Association for Computing Machinery
DOI: 10.1145/3469877.3490605

Whitening for Self-Supervised Representation Learning

Auteurs: Alexandr Ermolov; Aliaksandr Siarohin; Enver Sangineto; Niculae Sebe
Publié dans: 38th International Conference on Machine Learning, PMLR, Numéro 139, 2021, Page(s) 3015-3024
Éditeur: Proceedings of Machine Learning Research
DOI: 10.5281/zenodo.5543415

Exploring Deep Fusion Ensembling for Automatic Visual Interestingness Prediction

Auteurs: M.G. Constantin; L.D. Stefan; B. Ionescu
Publié dans: Human Perception of Visual Information Psychological and Computational Perspectives, 2022, Page(s) 33-58, ISBN 978-3-030-81465-6
Éditeur: Springer Nature Switzerland AG
DOI: 10.1007/978-3-030-81465-6_2

Explainable Video Summarization for Advancing Media Content Production

Auteurs: Evlampios Apostolidis, Georgios Balaouras, Ioannis Patras, Vasileios Mezaris
Publié dans: Encyclopedia of Information Science and Technology, Sixth Edition, 2025, ISBN 9781668473665
Éditeur: IGI Global
DOI: 10.4018/978-1-6684-7366-5.ch065

Proceedings of the 2nd International Workshop on Learning to Quantify (LQ 2022)

Auteurs: Juan Jose del Coz, Pablo Gonzalez, Alejandro Moreo, Fabrizio Sebastiani
Publié dans: Proceedings of the 2nd International Workshop on Learning to Quantify (LQ 2022), 2022
Éditeur: LQ 2022
DOI: 10.5281/zenodo.7093004

Learning to Quantify

Auteurs: Andrea Esuli , Alessandro Fabris , Alejandro Moreo , Fabrizio Sebastiani
Publié dans: Learning to Quantify, 2023, ISBN 978-3-031-20466-1
Éditeur: Springer Cham
DOI: 10.1007/978-3-031-20467-8

Recherche de données OpenAIRE...

Livrables

Publications

Partager cette page

Télécharger