| 2026 | HRI | GeoSACS: Geometric Shared Autonomy via Canal Surfaces. | Shalutha Rajapakshe, Atharva Dastenavar, Michael Hagenow, Jean-Marc Odobez, Emmanuel Senft |
| 2025 | CVPR | Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels. | Pierre Vuillecard, Jean-Marc Odobez |
| 2025 | HRI | Giving Sense to Inputs: Toward an Accessible Control Framework for Shared Autonomy. | Shalutha Rajapakshe, Jean-Marc Odobez, Emmanuel Senft |
| 2025 | WACV | Loose Social-Interaction Recognition in Real-World Therapy Scenarios. | Abid Ali, Rui Dai, Ashish Marisetty, Guillaume Astruc, Monique Thonnat, Jean-Marc Odobez, Susanne Thmmler, Franois Brmond |
| 2024 | CBMI | Weakly-Supervised Autism Severity Assessment in Long Videos. | Abid Ali, Mahmoud Ali, Camilla Barbini, Sverine Dubuisson, Jean-Marc Odobez, Franois Brmond, Susanne Thmmler |
| 2024 | CVPR | Exploring the Zero-Shot Capabilities of Vision-Language Models for Improving Gaze Following. | Anshul Gupta, Pierre Vuillecard, Arya Farkhondeh, Jean-Marc Odobez |
| 2024 | CVPR | Sharingan: A Transformer Architecture for Multi-Person Gaze Following. | Samy Tafasca, Anshul Gupta, Jean-Marc Odobez |
| 2024 | ECCV | ChildPlay-Hand: A Dataset of Hand Manipulations in the Wild. | Arya Farkhondeh, Samy Tafasca, Jean-Marc Odobez |
| 2023 | ICCV | ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour. | Samy Tafasca, Anshul Gupta, Jean-Marc Odobez |
| 2023 | ICMI | The AI4Autism Project: A Multimodal and Interdisciplinary Approach to Autism Diagnosis and Stratification. | Samy Tafasca, Anshul Gupta, Nada Kojovic, Mirko Gelsomini, Thomas Maillart, Michela Papandrea, Marie Schaer, Jean-Marc Odobez |
| 2023 | IROS | A Multitask and Kernel Approach for Learning to Push Objects with a Target-Parameterized Deep Q-Network. | Marco Ewerton, Michael Villamizar, Julius Jankowski, Sylvain Calinon, Jean-Marc Odobez |
| 2022 | CVPR | A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings. | Anshul Gupta, Samy Tafasca, Jean-Marc Odobez |
| 2021 | CVPR | Visual Focus of Attention Estimation in 3D Scene With an Arbitrary Number of Targets. | Rmy Siegfried, Jean-Marc Odobez |
| 2021 | Interspeech | Multi-Task Neural Network for Robust Multiple Speaker Embedding Extraction. | Weipeng He, Petr Motlcek, Jean-Marc Odobez |
| 2021 | IROS | An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning. | Marco Ewerton, ngel Martnez-Gonzlez, Jean-Marc Odobez |
| 2020 | CVPR | Unsupervised Representation Learning for Gaze Estimation. | Yu Yu, Jean-Marc Odobez |
| 2020 | ETRA | ManiGaze: a Dataset for Evaluating Remote Gaze Estimator in Object Manipulation Situations. | Rmy Siegfried, Bozorgmehr Aminian, Jean-Marc Odobez |
| 2020 | IROS | Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation. | ngel Martnez-Gonzlez, Michael Villamizar, Olivier Canvet, Jean-Marc Odobez |
| 2020 | RO-MAN | The MuMMER Data Set for Robot Perception in Multi-party HRI Scenarios. | Olivier Canvet, Weipeng He, Petr Motlcek, Jean-Marc Odobez |
| 2019 | CVPR | Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis. | Yu Yu, Gang Liu, Jean-Marc Odobez |
| 2019 | ETRA | A deep learning approach for robust head pose independent eye movements recognition from videos. | Rmy Siegfried, Yu Yu, Jean-Marc Odobez |
| 2019 | ICASSP | Adaptation of Multiple Sound Source Localization Neural Networks with Weak Supervision and Domain-adversarial Training. | Weipeng He, Petr Motlcek, Jean-Marc Odobez |
| 2018 | AVSS | UNICITY: A depth maps database for people detection in security airlocks. | Jol Dumoulin, Olivier Canvet, Michael Villamizar, Hugo Nunes, Omar Abou Khaled, Elena Mugellini, Fabrice Moscheni, Jean-Marc Odobez |
| 2018 | AVSS | WatchNet: Efficient and Depth-based Network for People Detection in Video Surveillance Systems. | Michael Villamizar, ngel Martnez-Gonzlez, Olivier Canvet, Jean-Marc Odobez |
| 2018 | BMVC | A Differential Approach for Gaze Estimation with Calibration. | Gang Liu, Yu Yu, Kenneth Alberto Funes Mora, Jean-Marc Odobez |
| 2018 | ECCV | Investigating Depth Domain Adaptation for Efficient Human Pose Estimation. | ngel Martnez-Gonzlez, Michael Villamizar, Olivier Canvet, Jean-Marc Odobez |
| 2018 | ECCV | Deep Multitask Gaze Estimation with a Constrained Landmark-Gaze Model. | Yu Yu, Gang Liu, Jean-Marc Odobez |
| 2018 | ICRA | Deep Neural Networks for Multiple Speaker Detection and Localization. | Weipeng He, Petr Motlcek, Jean-Marc Odobez |
| 2018 | Interspeech | Joint Localization and Classification of Multiple Sound Sources Using a Multi-task Neural Network. | Weipeng He, Petr Motlcek, Jean-Marc Odobez |
| 2018 | Interspeech | Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization. | Nam Le, Jean-Marc Odobez |
| 2018 | IROS | Leveraging Convolutional Pose Machines for Fast and Accurate Head Pose Estimation. | Yuanzhouhan Cao, Olivier Canvet, Jean-Marc Odobez |
| 2018 | IROS | Real-time Convolutional Networks for Depth-based Human Pose Estimation. | ngel Martnez-Gonzlez, Michael Villamizar, Olivier Canvet, Jean-Marc Odobez |
| 2018 | MUM | Facing Employers and Customers: What Do Gaze and Expressions Tell About Soft Skills? | Skanda Muralidhar, Rmy Siegfried, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2017 | CBMI | Shape Representations for Maya Codical Glyphs: Knowledge-driven or Deep? | Glcan Can, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2017 | CBMI | Towards large scale multimedia indexing: A case study on person discovery in broadcast news. | Nam Le, Herv Bredin, Gabriel Sargent, Miquel India, Paula Lopez-Otero, Claude Barras, Camille Guinaudeau, Guillaume Gravier, Gabriel Barbosa da Fonseca, Izabela Lyon Freire, Zenilton K. G. Patrocnio Jr., Silvio Jamil Ferzoli Guimares, Gerard Mart, Josep Ramon Morros, Javier Hernando, Laura Doco Fernndez, Carmen Garca-Mateo, Sylvain Meignier, Jean-Marc Odobez |
| 2017 | ICMI | A domain adaptation approach to improve speaker turn embedding using face representation. | Nam Le, Jean-Marc Odobez |
| 2017 | ICMI | Towards the use of social interaction conventions as prior for gaze model adaptation. | Rmy Siegfried, Yu Yu, Jean-Marc Odobez |
| 2017 | WACV | Active Online Anomaly Detection Using Dirichlet Process Mixture Model and Gaussian Process Classification. | Jagannadan Varadarajan, Ramanathan Subramanian, Narendra Ahuja, Pierre Moulin, Jean-Marc Odobez |
| 2016 | ECAI | The EUMSSI Project - Event Understanding through Multimodal Social Stream Interpretation. | Jens Grivolla, Yannick Estve, Eelco Herder, Nam Le, Kay Macquarrie, Ral Marn, Sylvain Meignier, Maite Melero, Jean-Marc Odobez, Susanne Preu |
| 2016 | ECCV | Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection. | Nam Le, Alexandre Heili, Jean-Marc Odobez |
| 2016 | ECCV | Transferring Neural Representations for Low-Dimensional Indexing of Maya Hieroglyphic Art. | Edgar Roman-Rangel, Gulcan Can, Stphane Marchand-Maillet, Rui Hu, Carlos Pallan Gayol, Guido Krempel, Jakub Spotak, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2016 | ICMI | Training on the job: behavioral analysis of job interviews in hospitality. | Skanda Muralidhar, Laurent Son Nguyen, Denise Frauendorfer, Jean-Marc Odobez, Marianne Schmid Mast, Daniel Gatica-Perez |
| 2016 | ICMI | Towards building an attentive artificial listener: on the perception of attentiveness in audio-visual feedback tokens. | Catharine Oertel, Jos Lopes, Yu Yu, Kenneth Alberto Funes Mora, Joakim Gustafson, Alan W. Black, Jean-Marc Odobez |
| 2016 | ICPR | Temporally subsampled detection for accurate and efficient face tracking and diarization. | Nam Le, Alexandre Heili, Di Wu, Jean-Marc Odobez |
| 2016 | SSPR | Unsupervised Interpretable Pattern Discovery in Time Series Using Autoencoders. | Kevin Bascol, Rmi Emonet, lisa Fromont, Jean-Marc Odobez |
| 2015 | ICMI | Deciphering the Silent Participant: On the Use of Audio-Visual Cues for the Classification of Listener Categories in Group Discussions. | Catharine Oertel, Kenneth Alberto Funes Mora, Joakim Gustafson, Jean-Marc Odobez |
| 2014 | CBMI | Comparison of two methods for unsupervised person identification in TV shows. | Paul Gay, Grgor Dupuy, Carole Lailler, Jean-Marc Odobez, Sylvain Meignier, Paul Delglise |
| 2014 | COLING | EUMSSI: a Platform for Multimodal Analysis and Recommendation using UIMA. | Jens Grivolla, Maite Melero, Toni Badia, Cosmin Cabulea, Yannick Estve, Eelco Herder, Jean-Marc Odobez, Susanne Preu, Ral Marn |
| 2014 | CVPR | Geometric Generative Gaze Estimation (G3E) for Remote RGB-D Cameras. | Kenneth Alberto Funes Mora, Jean-Marc Odobez |
| 2014 | ETRA | EYEDIAP: a database for the development and evaluation of gaze estimation algorithms from RGB and RGB-D cameras. | Kenneth Alberto Funes Mora, Florent Monay, Jean-Marc Odobez |
| 2014 | ICASSP | A conditional random field approach for audio-visual people diarization. | Paul Gay, Elie Khoury, Sylvain Meignier, Jean-Marc Odobez, Paul Delglise |
| 2014 | ICIP | A conditional random field approach for face identification in broadcast news using overlaid text. | Paul Gay, Elie Khoury, Sylvain Meignier, Jean-Marc Odobez, Paul Delglise |
| 2014 | ICIP | Improving head and body pose estimation through semi-supervised manifold alignment. | Alexandre Heili, Jagannadan Varadarajan, Bernard Ghanem, Narendra Ahuja, Jean-Marc Odobez |
| 2014 | ICIP | Automated bobbing and phase analysis to measure walking entrainment to music. | Adolfo Lpez-Mendez, Carina Westling, Rmi Emonet, M. Easteal, L. Lavia, Harry J. Witchel, Jean-Marc Odobez |
| 2014 | ICMI | Who Will Get the Grant?: A Multimodal Corpus for the Analysis of Conversational Behaviours in Group Interviews. | Catharine Oertel, Kenneth Alberto Funes Mora, Samira Sheikhi, Jean-Marc Odobez, Joakim Gustafson |
| 2013 | AVSS | Localized anomaly detection via hierarchical integrated activity discovery. | Thiyagarajan Chockalingam, Rmi Emonet, Jean-Marc Odobez |
| 2013 | HRI | Given that, should i respond?: contextual addressee estimation in multi-party human-robot interactions. | Dinesh Babu Jayagopi, Jean-Marc Odobez |
| 2013 | HRI | The vernissage corpus: a conversational human-robot-interaction dataset. | Dinesh Babu Jayagopi, Samira Sheikhi, David Klotz, Johannes Wienke, Jean-Marc Odobez, Sebastian Wrede, Vasil Khalidov, Laurent Nyugen, Britta Wrede, Daniel Gatica-Perez |
| 2013 | ICIP | Person independent 3D gaze estimation from remote RGB-D cameras. | Kenneth Alberto Funes Mora, Jean-Marc Odobez |
| 2013 | ICIP | Time-sensitive topic models for action recognition in videos. | Romain Tavenard, Rmi Emonet, Jean-Marc Odobez |
| 2013 | ICMI | A semi-automated system for accurate gaze coding in natural dyadic interactions. | Kenneth Alberto Funes Mora, Laurent Son Nguyen, Daniel Gatica-Perez, Jean-Marc Odobez |
| 2013 | ICMI | Context aware addressee estimation for human robot interaction. | Samira Sheikhi, Dinesh Babu Jayagopi, Vasil Khalidov, Jean-Marc Odobez |
| 2013 | ICMI | Leveraging the robot dialog state for visual focus of attention recognition. | Samira Sheikhi, Vasil Khalidov, David Klotz, Britta Wrede, Jean-Marc Odobez |
| 2012 | CVPR | We are not contortionists: Coupled adaptive learning for head and body orientation estimation in surveillance video. | Cheng Chen, Jean-Marc Odobez |
| 2012 | CVPR | Gaze estimation from multimodal Kinect data. | Kenneth Alberto Funes Mora, Jean-Marc Odobez |
| 2012 | CVPR | Bridging the past, present and future: Modeling scene activities from event relationships and global rules. | Jagannadan Varadarajan, Rmi Emonet, Jean-Marc Odobez |
| 2012 | ECCV | Unsupervised Activity Analysis and Monitoring Algorithms for Effective Surveillance Systems. | Jean-Marc Odobez, Cyril Carincotte, Rmi Emonet, Erwan Jouneau, Sofia Zaidenberg, Bertrand Ravera, Franois Brmond, Andrea Grifoni |
| 2012 | ICMI | Using self-context for multimodal detection of head nods in face-to-face interactions. | Laurent Son Nguyen, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2012 | ICMI | Investigating the midline effect for visual focus of attention recognition. | Samira Sheikhi, Jean-Marc Odobez |
| 2011 | AVSS | Combined estimation of location and body pose in surveillance video. | Cheng Chen, Alexandre Heili, Jean-Marc Odobez |
| 2011 | AVSS | Multi-camera open space human activity discovery for anomaly detection. | Rmi Emonet, Jagannadan Varadarajan, Jean-Marc Odobez |
| 2011 | BMVC | Joint Adaptive Colour Modelling and Skin, Hair and Clothes Segmentation using Coherent Probabilistic Index Maps. | Carl Scheffler, Jean-Marc Odobez |
| 2011 | CVPR | Extracting and locating temporal motifs in video scenes using a hierarchical non parametric Bayesian model. | Rmi Emonet, Jagannadan Varadarajan, Jean-Marc Odobez |
| 2011 | SIGdial | Engagement-based Multi-party Dialog with a Humanoid Robot. | David Klotz, Johannes Wienke, Julia Peltason, Britta Wrede, Sebastian Wrede, Vasil Khalidov, Jean-Marc Odobez |
| 2010 | BMVC | Probabilistic Latent Sequential Motifs: Discovering Temporal Activity Patterns in Video Scenes. | Jagannadan Varadarajan, Rmi Emonet, Jean-Marc Odobez |
| 2009 | BMVC | Dynamic Partitioned Sampling For Tracking With Discriminative Features. | Stefan Duffner, Jean-Marc Odobez, Elisa Ricci |
| 2009 | ICIP | Learning large margin likelihoods for realtime head pose tracking. | Elisa Ricci, Jean-Marc Odobez |
| 2008 | ICASSP | Multi-party focus of attention recognition in meetings from head pose and multimodal contextual cues. | Sileye O. Ba, Jean-Marc Odobez |
| 2008 | ICMI | Investigating automatic dominance estimation in groups from visual attention and speaking activity. | Hayley Hung, Dinesh Babu Jayagopi, Sileye O. Ba, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2008 | ICMI | Predicting two facets of social verticality in meetings from five-minute time slices and nonverbal cues. | Dinesh Babu Jayagopi, Sileye O. Ba, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2008 | ICPR | Detecting queues at vending machines: A statistical layered approach. | Xavier Naturel, Jean-Marc Odobez |
| 2007 | CVPR | Multi-Layer Background Subtraction Based on Color and Texture. | Jian Yao, Jean-Marc Odobez |
| 2006 | CVPR | Integrating Co-Occurrence and Spatial Contexts on PatchBased Scene Segmentation. | Florent Monay, Pedro Quelhas, Jean-Marc Odobez, Daniel Gatica-Perez |
| 2006 | ICMI | Tracking the multi person wandering visual focus of attention. | Kevin Smith, Sileye O. Ba, Daniel Gatica-Perez, Jean-Marc Odobez |
| 2005 | CVPR | Using Particles to Track Varying Numbers of Interacting People. | Kevin Smith, Daniel Gatica-Perez, Jean-Marc Odobez |
| 2005 | CVPR | Evaluating Multi-Object Tracking. | Kevin Smith, Daniel Gatica-Perez, Jean-Marc Odobez, Sileye O. Ba |
| 2005 | ICCV | Modeling Scenes with Local Descriptors and Latent Aspects. | Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Daniel Gatica-Perez, Tinne Tuytelaars, Luc Van Gool |
| 2005 | ICDAR | OCR Based Slide Retrieval. | N. Daddaoua, Jean-Marc Odobez, Alessandro Vinciarelli |
| 2005 | ICMI | Multimodal multispeaker probabilistic tracking in meetings. | Daniel Gatica-Perez, Guillaume Lathoud, Jean-Marc Odobez, Iain McCowan |
| 2004 | ICPR | A Probabilistic Framework for Joint Head Tracking and Pose Estimation. | Sileye O. Ba, Jean-Marc Odobez |
| 2004 | ICPR | Robust Playfield Segmentation using MAP Adaptation. | Mark Barnard, Jean-Marc Odobez |
| 2004 | ICPR | Embedding Motion in Model-Based Stochastic Tracking. | Jean-Marc Odobez, Daniel Gatica-Perez |
| 2003 | BMVC | An implicit motion likelihood for tracking with particle filters. | Jean-Marc Odobez, Sileye O. Ba, Daniel Gatica-Perez |
| 2003 | ICIP | Sequential Monte Carlo video text segmentation. | Datong Chen, Jean-Marc Odobez |
| 2003 | ICIP | Audio-visual speaker tracking with importance particle filters. | Daniel Gatica-Perez, Guillaume Lathoud, Iain McCowan, Jean-Marc Odobez, Darren Moore |
| 2003 | Interact | A Hierarchical Keyframe User Interface for Browsing Video over the Internet. | Mal Guillemot, Pierre Wellner, Daniel Gatica-Perez, Jean-Marc Odobez |
| 2002 | ICIP | Robust video text segmentation and recognition with multiple hypotheses. | Jean-Marc Odobez, Datong Chen |
| 2002 | ICPR | Text Segmentation and Recognition in Complex Background Based on Markov Random Field. | Datong Chen, Jean-Marc Odobez, Herv Bourlard |
| 2000 | ICIP | Analysis of Doppler Ultrasound Time Frequency Images Using Deformable Models. | Jean-Marc Odobez, Emmanuel Roy, Pierre Abraham |
| 1995 | ACCV | Direct Model-Based Image Motion Segmentation for Dynamic Scene Analysis. | Jean-Marc Odobez, Patrick Bouthemy |
| 1995 | ICASSP | Motion-compensated adaptive wavelet filtering for image sequence processing. | Jean-Pierre Leduc, Jean-Marc Odobez, Claude Labit |
| 1995 | ICIP | Determination of singular points in 2D deformable flow fields. | Mariette Maurizot, Patrick Bouthemy, Bernard Delyon, Anatoli B. Juditsky, Jean-Marc Odobez |
| 1995 | ICIP | MRF-based motion segmentation exploiting a 2D motion model robust estimation. | Jean-Marc Odobez, Patrick Bouthemy |
| 1994 | ICIP | A | Eric Nguyen, Claude Labit, Jean-Marc Odobez |
| 1994 | ICIP | Detection of Multiple Moving Objects using Multiscale MRF with Camera Motion Compensation. | Jean-Marc Odobez, Patrick Bouthemy |