Research

Keywords: Machine Learning, Deep Learning, Computer Vision, …

List of publications:

  • Hamed Benazha, Stéphane Ayache, Thierry Artières. Measuring Hallucination in Disentangled Representations. International Joint Conference on Neural Networks (IJCNN), IEEE, Jun 2024, Yokohama, Japan. ⟨hal-04532666⟩
  • Felipe Torres, Hanwei Zhang, Ronan Sicre, Stéphane Ayache, Yannis Avrithis. CA-Stream: Attention-based pooling for interpretable image recognition. XAI4CV workshop (CVPR), Jun 2024, Seatle, WA, United States. ⟨hal-04551613⟩ pdf
  • Kais Hariz, Hachem Kadri, Stéphane Ayache, Maher Moakher, Thierry Artières. Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity. International Conference on Artificial Intelligence and Statistics (AISTATS), May 2024, Valencia (Espagne), Spain. ⟨hal-04523934⟩ pdf
  • Charly Lamothe, Etienne Thoret, Regis Trapeau, Bruno Giordano, Julien Sein, et al.. Reconstructing Voice Identity from Noninvasive Auditory Cortex Recordings. BioRxiv, 2024, ⟨10.1101/2024.02.27.582302⟩. ⟨hal-04483262⟩
  • Felipe Torres Figueroa, Hanwei Zhang, Ronan Sicre, Yannis Avrithis, Stephane Ayache. A Learning Paradigm for Interpretable Gradients. VISAPP 2024, Feb 2024, Rome, Italy. ⟨hal-04533137⟩ pdf
  • Alice Delbosc, Magalie Ochs, Nicolas Sabouret, Brian Ravenet, Stéphane Ayache. Towards the generation of synchronized and believable non-verbal facial behaviors of a talking virtual agent. GENEA : GENERATION AND EVALUATION OF NON-VERBAL BEHAVIOUR FOR EMBODIED AGENTS during ICMI ’23 Companion, Oct 2023, Paris, France. ⟨hal-04206768⟩ pdf
  • Emmanuelle Salin, Stéphane Ayache, Benoit Favre. Towards an Exhaustive Evaluation of Vision-Language Foundation Models. ICCV workshop on Multimodal Foundation Models (MMFM), Oct 2023, Paris, France. ⟨hal-04181190⟩ pdf
  • Rémi Eyraud, Stéphane Ayache, Philipp O Tsvetkov, Shanmugha Sri Kalidindi, Viktoriia E Baksheeva, et al.. Plasma nanoDSF Denaturation Profile at Baseline Is Predictive of Glioblastoma EGFR Status. Cancers, 2023, ⟨10.3390/cancers15030760⟩. ⟨hal-03957563⟩ pdf
  • Alice Delbosc, Magalie Ochs, Stéphane Ayache. Automatic facial expressions, gaze direction and head movements generation of a virtual agent. GENEA : GENERATION AND EVALUATION OF NON-VERBAL BEHAVIOUR FOR EMBODIED AGENTS, Nov 2022, Bengaluru, India. ⟨10.1145/3536220.3558806⟩. ⟨hal-03794365⟩ pdf
  • Kais Hariz, Hachem Kadri, Stéphane Ayache, Maher Moakher, Thierry Artières. Implicit Regularization with Polynomial Growth in Deep Tensor Factorization. International Conference on Machine Learning, Jul 2022, Baltimore, United States. ⟨hal-03726808⟩ pdf
  • Badreddine Farah, Stéphane Ayache, Benoit Favre, Emmanuelle Salin. Are Vision-Language Transformers Learning Multimodal Representations? A Probing Perspective. AAAI 2022, Feb 2022, Vancouver, Canada. ⟨hal-03521715v2⟩ pdf
  • Mitja Nikolaus, Emmanuelle Salin, Stéphane Ayache, Abdellah Fourtassi, Benoît Favre. Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing., 2022, Abu Dhabi, United Arab Emirates. ⟨hal-03823490⟩ pdf
  • Luc Giffon, Stéphane Ayache, Hachem Kadri, Thierry Artières, Ronan Sicre. PSM-nets: Compressing Neural Networks with Product of Sparse Matrices. IJCNN, Jul 2021, Virtual Event, United States. ⟨hal-03151539⟩ pdf
  • Paolo Milanesi, Hachem Kadri, Stéphane Ayache, Thierry Artières. Implicit Regularization in Deep Tensor Factorization. International Joint Conference on Neural Networks (IJCNN), Jul 2021, Online, China. ⟨hal-03211964⟩ pdf
  • Philipp A Tsvetkov, Rémi Eyraud, Stéphane Ayache, Anton A Bougaev, Soazig Malesinski, et al.. An AI-Powered Blood Test to Detect Cancer Using NanoDSF. Cancers, 2021, 13 (6), pp.1294. ⟨10.3390/cancers13061294⟩. ⟨hal-03169412⟩ pdf
  • Rémi Eyraud, Stéphane Ayache. Distillation of Weighted Automata from Recurrent Neural Networks using a Spectral Approach *. Machine Learning, 2020, ⟨10.1007/s10994-021-05948-1⟩. ⟨hal-03270667⟩ pdf
  • Akrem Sellami, François-Xavier Dupé, Bastien Cagna, Hachem Kadri, Stéphane Ayache, et al.. Mapping individual differences in cortical architecture using multi-view representation learning. IJCNN 2020 - International Joint Conference on Neural Networks, Jul 2020, Glasgow, United Kingdom. ⟨hal-02520673⟩ pdf
  • Hachem Kadri, Stéphane Ayache, Riikka Huusari, Alain Rakotomamonjy, Liva Ralaivola. Partial Trace Regression and Low-Rank Kraus Decomposition. International Conference on Machine Learning, Jul 2020, Vienne (Online), Austria. ⟨hal-02885339v2⟩ pdf
  • Sergio Escalera, Hugo Jair Escalante, Xavier Baró, Isabelle Guyon, Meysam Madadi, et al.. Guest Editorial: Image and Video Inpainting and Denoising. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (5), pp.1021-1024. ⟨10.1109/TPAMI.2020.2971291⟩. ⟨hal-03159859⟩ pdf
  • Stéphane Ayache, Ronan Sicre, Thierry Artières. Transfer Learning by Weighting Convolution. International Joint Conference on Neural Networks (IJCNN), 2020, Glasgow, United Kingdom. ⟨hal-02544099⟩ pdf
  • Hugo Jair Escalante, Heysem Kaya, Albert Ali Salah, Sergio Escalera, Yagmur Gucluturk, et al.. Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos. IEEE Transactions on Affective Computing, 2020. ⟨hal-01991652⟩
  • Luc Giffon, Stéphane Ayache, Thierry Artières, Hachem Kadri. Deep Networks with Adaptive Nyström Approximation. IJCNN 2019 - International Joint Conference on Neural Networks, Jul 2019, Budapest, Hungary. ⟨hal-02091661v2⟩ pdf
  • Sergio Escalera, Stéphane Ayache, Jun Wan, Meysam Madadi, Umut Güçlü, et al.. ChaLearn Looking at People: Inpainting and Denoising Challenges. Inpainting and Denoising Challenges, 2019. ⟨hal-02443492⟩
  • Sergio Escalera, Stéphane Ayache, Jun Wan, Meysam Madadi, Umut Güçlü, et al.. Inpainting and Denoising Challenges. Springer, 2019, 978-3-030-25614-2. ⟨hal-02443511⟩
  • Stéphane Ayache, Rémi Eyraud, Noé Goudian. Explaining Black Boxes on Sequential Data using Weighted Automata. 14th International Conference on Grammatical Inference, Sep 2018, Wrocław,, Poland. ⟨hal-01888514⟩ pdf
  • Luc Giffon, Stéphane Ayache, Hachem Kadri, Thierry Artières. Deepström: ´ Emulsion de noyaux et d'apprentissage profond. CAp 2018 - Conférence sur l'Apprentissage Automatique, Jun 2018, Rouen, France. ⟨hal-02091648v2⟩ pdf
  • Hugo Jair Escalante, Isabelle Guyon, Sergio Escalera, Julio Jacques, Meysam Madadi, et al.. Design of an Explainable Machine Learning Challenge for Video Interviews. IJCNN 2017 - 30th International Joint Conference on Neural Networks, May 2017, Anchorage, AK, United States. pp.1-8, ⟨10.1109/IJCNN.2017.7966320⟩. ⟨hal-01668386⟩ pdf
  • Florin Popescu, Stéphane Ayache, Sergio Escalera, Xavier Baró Solé, Cécile Capponi, et al.. From geospatial observations of ocean currents to causal predictors of spatio-economic activity using computer vision and machine learning. EGU General Assembly Conference Abstracts, 2016, Vienna, Austria. ⟨hal-01381147⟩
  • Hervé Le Borgne, Philippe Gosselin, David Picard, Miriam Redi, Bernard Mérialdo, et al.. IRIM at TRECVID 2015: Semantic Indexing. Proceedings of TRECVid, Nov 2015, Gaithersburg, MD, United States. ⟨hal-01233398⟩ pdf
  • Nicolas Ballas, Benjamin Labbé, Hervé Le Borgne, Philippe Gosselin, David Picard, et al.. IRIM at TRECVID 2014: Semantic Indexing and Instance Search. Proceedings of TRECVID, Nov 2014, Orlando, United States. ⟨hal-01132491⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. Majority Vote of Diverse Classifiers for Late Fusion. IAPR Joint International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recignition, Aug 2014, Joensuu, Finland. pp.20. ⟨hal-00985839v2⟩ pdf
  • Hachem Kadri, Stéphane Ayache, Cécile Capponi, Sokol Koço, François-Xavier Dupé, et al.. The Multi-Task Learning View of Multimodal Data. Asian Conference on Machine Learning (ACML), Nov 2013, Canberra, Australia. pp.261--276. ⟨hal-01070601⟩ pdf
  • Favre Benoit, Géraldine Damnati, Frédéric Béchet, Meriem Bendris, Delphine Charlet, et al.. PERCOLI: a person identification system for the 2013 REPERE challenge. SLAM 2013 : First Workshop on Speech, Language and Audio in Multimedia, Aug 2013, Marseille, France. pp.55-60. ⟨hal-00834204⟩
  • Nicolas Ballas, Benjamin Labbé, Hervé Le Borgne, Philippe Gosselin, Miriam Redi, et al.. IRIM at TRECVID 2013: Semantic Indexing and Instance Search. Proc. TRECVID Workshop, 2013, Gaithersburg, MD, United States. ⟨hal-00953092⟩ pdf
  • Nicolas Ballas, Benjamin Labbé, Aymen Shabou, Hervé Le Borgne, Philippe-Henri Gosselin, et al.. IRIM at TRECVID 2012: Semantic Indexing and Instance Search. TRECVID - TREC Video Retrieval Evaluation workshop, Nov 2012, Gaithersburg, MD, United States. 12p. ⟨hal-00770258⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. Étude de la généralisation de DASF à l'adaptation de domaine semi-supervisée. Conférence Francophone sur l'Apprentissage Automatique - CAp 2012, May 2012, Nancy, France. pp.111-126. ⟨hal-00685524⟩ pdf
  • Bahjat Safadi, Stéphane Ayache, Georges Quénot. Active Cleaning for Video Corpus Annotation. MMM 2012 - International MultiMedia Modeling Conference, Jan 2012, Klagenfurt, Austria. pp.518-528, ⟨10.1007/978-3-642-27355-1_48⟩. ⟨hal-00767345⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. PAC-Bayesian Majority Vote for Late Classifier Fusion. [Research Report] LIF Marseille; LaHC Saint-Etienne. 2012. ⟨hal-00714483⟩ pdf
  • Frédéric Béchet, Rémi Auguste, Stéphane Ayache, Delphine Charlet, Géraldine Damnati, et al.. Percol0 - un système multimodal de détection de personnes dans des documents vidéo (Percol0 - A multimodal person detection system in video documents) [in French]. Actes de la conférence conjointe JEP-TALN-RECITAL 2012, volume 1: JEP, 2012, Grenoble, France. pp.553--560. ⟨hal-01194254⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. Parsimonious Unsupervised and Semi-Supervised Domain Adaptation with Good Similarity Functions. Knowledge and Information Systems (KAIS), 2012, 33 (2), pp.309-349. ⟨10.1007/s10115-012-0516-7⟩. ⟨hal-00686205⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. Sparse Domain Adaptation in a Good Similarity-Based Projection Space. Workshop at NIPS 2011: Domain Adaptation Workshop: Theory and Application, Dec 2011, Grenade, Spain. ⟨hal-00654227⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. Sparse Domain Adaptation in Projection Spaces based on Good Similarity Functions. IEEE International Conference on Data Mining series (ICDM), Dec 2011, Vancouver, Canada. pp.457-466. ⟨hal-00629207⟩ pdf
  • Bertrand Delezoide, Frédéric Precioso, Philippe-Henri Gosselin, Miriam Redi, Bernard Merialdo, et al.. IRIM at TRECVID 2011: Semantic Indexing and Instance Search. TRECVID 2011 - TREC Video Retrieval Evaluation Online, Nov 2011, Gaithersburg, MD, United States. 12p. ⟨hal-00677651⟩ pdf
  • Emilie Morvant, Stéphane Ayache, Amaury Habrard, Miriam Redi, Claudiu Tanase, et al.. VideoSense at TRECVID 2011 : Semantic Indexing from Light Similarity Functions-based Domain Adaptation with Stacking. TRECVID 2011 - TREC Video Retrieval Evaluation workshop, Nov 2011, Gaithersburg, MD, United States. 6p. ⟨hal-00685530⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. On the Usefulness of Similarity Based Projection Spaces for Transfer Learning. First International Workshop on Similarity-Based Pattern Recognition, Sep 2011, Venise, Italy. pp.1-16. ⟨hal-00628991⟩ pdf
  • Emilie Morvant, Stéphane Ayache, Amaury Habrard. Adaptation de domaine parcimonieuse par pondération de bonnes fonctions de similarité. Conférence Francophone d'Apprentissage (CAp), May 2011, Chambéry, France. pp.295-310. ⟨hal-00630300⟩ pdf
  • Emilie Morvant, Amaury Habrard, Stéphane Ayache. Flexible Domain Adaptation for Multimedia Indexing. 2011. ⟨hal-00634881⟩ pdf
  • David Gorisse, Frédéric Precioso, Philippe-Henri Gosselin, Lionel Granjon, Denis Pellerin, et al.. IRIM at TRECVID 2010: Semantic Indexing and Instance Search. TRECVID 2010 - TREC Video Retrieval Evaluation workshop, Nov 2010, Gaithersburg, MD, United States. ⟨hal-00591099⟩ pdf
  • David Gorisse, Frédéric Precioso, Philippe Gosselin, Lionel Granjon, Denis Pellerin, et al.. IRIM at TRECVID 2010: High Level Feature Extraction and Instance Search. TREC Video Retrieval Evaluation workshop, 2010, Gaithersburg, MD, United States. ⟨hal-00953839⟩
  • Georges Quénot, Tien-Ping Tan, Viet-Bac Le, Stéphane Ayache, Laurent Besacier, et al.. Content-based search in multilingual audiovisual documents using the International Phonetic Alphabet. Multimedia Tools and Applications, 2010, 48 (1), pp.123-140. ⟨10.1007/s11042-009-0377-6⟩. ⟨hal-00953696⟩
  • Stéphane Ayache, Georges Quénot, Andy Tseng. The LIGVID System for Video Retrieval and Concept Annotation. 11th ACM SIGMM International Conference on Multimedia Information Retrieval (demo session), 2010, Philadelphia, Pennsylvania, United States. ⟨hal-00953840⟩
  • Georges Quénot, Tien-Ping Tan, Viet-Bac Le, Stéphane Ayache, Laurent Besacier, et al.. Recherche par le contenu dans des documents audiovisuels multilingues. Document numérique - Revue des sciences et technologies de l'information. Série Document numérique, 2010, 13 (1), pp.229-246. ⟨hal-00953796⟩
  • Stéphane Ayache, Georges Quénot, Andy Tseng. The LIGVID System for Video Retrieval and Concept Annotation. 8th International workshop on Content-Based Multimedia Indexing (demo session), 2010, Grenoble, France. ⟨hal-00953841⟩
  • Stéphane Ayache, Bahjat Safadi, Andy Tseng, Franck Thollard, Georges Quénot, et al.. Quaero at TRECVID 2010: Semantic Indexing. TREC Video Retrieval Evaluation workshop, 2010, Gaithersburg, MD, United States. ⟨hal-00953842⟩
  • Bertrand Delezoide, Hervé Le Borgne, Pierre-Alain Moëllic, David Gorisse, Frédéric Precioso, et al.. IRIM at TRECVID2009: High Level Feature Extraction. TRECVID 2009 - TREC Video Retrieval Evaluation, Nov 2009, Gaithersburg, MD, United States. ⟨hal-00468199⟩ pdf
  • Georges Quénot, Tien-Ping Tan, Viet-Bac Le, Stéphane Ayache, Laurent Besacier, et al.. Recherche par le contenu dans des documents audiovisuels multilingues. Actes de la conférence CORIA, 2009, Giens, France. pp.67-82. ⟨hal-00954025⟩
  • Georges Quénot, Tien-Ping Tan, Viet-Bac Le, Stéphane Ayache, Laurent Besacier, et al.. Content-Based Search in Multilingual Audiovisual Documents using the International Phonetic Alphabet. 7th International Workshop on Content-Based Multimedia Indexing (CBMI 2009), 2009, Chania, Crete. 3-5 June 2009. ⟨hal-00953855⟩
  • Stéphane Ayache, Georges Quénot, Laurent Besacier. The LIG Multi-Criteria System for Video Retrieval. International Conference on Image and Video Retrieval (demo session, VideOlympics), 2009, Santorini, Greece. ⟨hal-00953858⟩ pdf
  • Georges Quénot, Jenny Benois-Pineau, Boris Mansencal, Eliana Rossi, Matthieu Cord, et al.. Rushes summarization by IRIM consortium: redundancy removal and multi-feature fusion. TRECVID BBC Rushes Summarization Workshop at ACM Multimedia'08, Oct 2008, Vancouver, BC, Canada. pp.80-84, ⟨10.1145/1463563.1463577⟩. ⟨hal-00347902⟩ pdf
  • Stéphane Ayache, Georges Quénot. Video Corpus Annotation using Active Learning. European Conference on Information Retrieval (ECIR), 2008, Glasgow, United Kingdom. ⟨hal-01089795⟩
  • Stéphane Ayache, Georges Quénot. LIG and LIRIS at TRECVID 2008: High Level Feature Extraction and Collaborative Annotation. TRECVID Workshop, 2008, Gaithersburg, MD, United States. ⟨hal-01089427⟩ pdf
  • Stéphane Ayache, Georges Quénot. The LIG Multi-Criteria System for Video Retrieval.. International Conference on Image and Video Retrieval (demo session, ViedOlympics), 2008, Niagara Falls, Canada. ⟨hal-01089817⟩
  • Hervé Glotin, Zhongqiu Zhao, Stéphane Ayache, Georges Quénot. IRIM at TRECVID 2008: High Level Feature Extraction. TRECVID Workshop, 2008, Gaithersburg, MD, United States. ⟨hal-01089878⟩
  • Stéphane Ayache, Georges Quénot. TRECVID 2007 Collaborative Annotation using Active Learning. TRECVID Workshop, 2007, Gaithersburg, MD, United States. ⟨hal-00953889⟩
  • Stéphane Ayache, Georges Quénot, Jérôme Gensel. Classifier Fusion for SVM-Based Multimedia Semantic Indexing. ECIR 2007, 2007, Rome, Italy. ⟨hal-00953886⟩ pdf
  • Stéphane Ayache, Georges Quénot. Indexation de documents multimédias par réseaux d'opérateurs. Quatrième conférence francophone en Recherche d'Information et Applications (CORIA), 2007, Saint Etienne. ⟨hal-00954036⟩
  • Stéphane Ayache, Georges Quénot. Evaluation of active learning strategies for video indexing. Signal Processing: Image Communication, 2007, 22 (7-8), pp.692--704. ⟨hal-00953800⟩
  • Stéphane Ayache, Georges Quénot. Evaluation of Active Learning Strategies for Video Indexing. IEEE International Workshop on Content-Based Multimedia Indexing, 2007, Bordeaux, France. ⟨hal-00953887⟩ pdf
  • Stéphane Ayache, Georges Quénot. Image and Video Indexing using Networks of Operators. EURASIP Journal on Image and Video Processing, 2007. ⟨hal-00953803⟩
  • Stéphane Ayache, Georges Quénot, Jérôme Gensel, Shin'Ichi Satoh. Using Topic Concepts for Semantic Video Shots Classification. International Conference on Image and Video Retrieval CIVR'06, 2006, Tempe, United States. ⟨hal-00953902⟩ pdf
  • Stéphane Ayache, Georges Quénot, Shin'Ichi Satoh. Context-based conceptual image indexing. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2006, Toulouse. ⟨hal-00953903⟩ pdf
  • Stéphane Ayache, Jérôme Gensel, Georges Quénot. CLIPS-LSR Experiments at TRECVID 2006. TREC Workshop on Video Retrieval Evaluation, 2006, Gaithersburg, United States. ⟨hal-00954114⟩
  • Daniel Moraru, Laurent Besacier, Georges Quénot, Stéphane Ayache. Speaker and Story Segmentation Using Audio-Video Information. The 3rd Conference on Speech Technology and Human-Computer Dialogue (SpeD 2005), 2005, Cluj-Napoca, Romania. ⟨hal-00953915⟩
  • Stéphane Ayache, Georges Quénot, Jérôme Gensel, Shin'Ichi Satoh. CLIPS and NII at TRECvid: Shot segmentation and feature extraction. TREC Workshop on Video Retrieval Evaluation, 2005, Gaithersburg, MD, United States. ⟨hal-00953918⟩ pdf
  • Mbarek Charhad, Daniel Moraru, Stéphane Ayache, Georges Quénot. Speaker Identity Indexing In Audio-Visual Documents. Content-Based Multimedia Indexing (CBMI2005), 2005, Riga, Latvia. ⟨hal-00953917⟩ pdf
  • Laurent Besacier, Georges Quénot, Stéphane Ayache, Daniel Moraru. Video Story Segmentation with Multi-Modal Features: Experiments on TRECvid 2003. 6th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR'04), 2004, New York, NY, United States. ⟨hal-00953929⟩
  • Stéphane Ayache. Modèle d'interaction pour un système de recherche d'images par le contenu. [Research Report] 2003. ⟨hal-00954137⟩
  • Anne Guérin-Dugué, Stéphane Ayache, Catherine Berrut. Image retrieval : a first step for a human centered approach. Fourth Pacific-Rim Conference on Multimedia (ICICS-PCM 2003), 2003, Unknown, Singapore. ⟨hal-00953936⟩ pdf