-
Kévin Bailly
- Maître de conférences
- Équipe: MLIA
- Bureau: H17
- Telephone:0144276385
- Addresse: ISIR, Campus Pierre et Marie Curie, 4 place Jussieu, BC173, 75005 Paris
- Site web: https://sites.google.com/view/bailly/
Publications
-
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly. Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings. The International Conference on Learning Representations (ICLR'24), May 2024, Vienna, Austria. ⟨hal-04425825⟩
[ HTTP ]
-
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly. PowerQuant: Automorphism Search for Non-Uniform Quantization. The Eleventh International Conference on Learning Representations (ICLR'23), May 2023, Kigali, Rwanda. ⟨hal-04425756⟩
[ HTTP ]
- Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kevin Bailly. RULe: Relocalization-Uniformization-Landmark Estimation Network for Real-Time Face Alignment in Degraded Conditions. International Conference on Automatic Face and Gesture Recognition (FG 2023), Jan 2023, Waikoloa Beach, HI, United States. ⟨10.1109/FG57933.2023.10042577⟩. ⟨hal-04087202⟩
-
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly. SPIQ: Data-Free Per-Channel Static Input Quantization. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), Jan 2023, Waikoloa (Hawaii), United States. ⟨hal-03953685⟩
[ HTTP ]
-
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly. PowerQuant: Automorphism Search for Non-Uniform Quantization. The Eleventh International Conference on Learning Representations (ICLR 2023), 2023. ⟨hal-04201009⟩
[ HTTP ]
- Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kevin Bailly. Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction. 17th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2023), Jan 2023, Waikoloa Beach ,HI, United States. ⟨10.1109/FG57933.2023.10042750⟩. ⟨hal-04087207⟩
-
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly. SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance. Advances in Neural Information Processing Systems (NeurIPS 2022), Nov 2022, New Orleans, United States. ⟨hal-03953649⟩
[ HTTP ]
- Aloïs Pourchot, Kevin Bailly, Alexis Ducarouge, Olivier Sigaud. Neural Architecture Search for Fracture Classification. 29th IEEE International Conference on Image Processing (ICIP 2022), Oct 2022, Bordeaux, France. ⟨hal-03753702⟩
-
Jules Bonnard, Arnaud Dapogny, Ferdinand Dhombres, Kevin Bailly. Privileged Attribution Constrained Deep Networks for Facial Expression Recognition. 26th International Conference on Pattern Recognition (ICPR 2022), Aug 2022, Montreal, Canada. pp.1055-1061, ⟨10.1109/ICPR56361.2022.9956496⟩. ⟨hal-03953623⟩
[ HTTP ]
- Aloïs Pourchot, Kévin Bailly, Alexis Ducarouge, Olivier Sigaud. An extensive appraisal of weight-sharing on the NAS-Bench-101 benchmark. Neurocomputing, 2022, 498, pp.28-42. ⟨10.1016/j.neucom.2022.04.108⟩. ⟨hal-03706214⟩
-
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly. To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding. Thirty-First International Joint Conference on Artificial Intelligence (IJCAI 22), Jul 2022, Vienna, Austria. pp.1601-1607, ⟨10.24963/ijcai.2022/223⟩. ⟨hal-03953581⟩
[ HTTP ]
-
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly. RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45 (3), pp.3664 - 3676. ⟨10.1109/TPAMI.2022.3179616⟩. ⟨hal-03706162⟩
[ HTTP ]
-
Estephe Arnaud, Arnaud Dapogny, Kevin Bailly. THIN: THrowable Information Networks and Application for Facial Expression Recognition In The Wild. IEEE Transactions on Affective Computing, In press, pp.1-1. ⟨10.1109/TAFFC.2022.3144439⟩. ⟨hal-03612596⟩
[ HTTP ]
-
Edouard Yvinec, Arnaud Dapgony, Matthieu Cord, Kevin Bailly. REx: Data-Free Residual Quantization Error Expansion. the Thirty-seventh Annual Conference on Neural Information (NeurIPS'23), Dec 2023, New Orleans (Louisiana), United States. ⟨10.48550/arXiv.2203.14645⟩. ⟨hal-04425863⟩
[ HTTP ]
-
Ferdinand Dhombres, Jules Bonnard, Kevin Bailly, Paul Maurice, Aris Papageorghiou, et al.. Contributions of Artificial Intelligence Reported in Obstetrics and Gynecology Journals: Systematic Review. Journal of Medical Internet Research, 2022, 24 (4), pp.e35465. ⟨10.2196/35465⟩. ⟨hal-03648171⟩
[ HTTP ]
-
Gauthier Tallec, Arnaud Dapogny, Kevin Bailly. Multi-Order Networks for Action Unit Detection. IEEE Transactions on Affective Computing, In press, pp.1-1. ⟨10.1109/TAFFC.2022.3178524⟩. ⟨hal-03687210⟩
[ HTTP ]
-
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kévin Bailly. RED: Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks. Advances in Neural Information Processing Systems (NeurIPS 2021), Dec 2021, Virtual, France. ⟨hal-03610457⟩
[ HTTP ]
-
Arnaud Dapogny, Kevin Bailly, Matthieu Cord. Deep Entwined Learning Head Pose and Face Alignment Inside an Attentional Cascade with Doubly-Conditional fusion. 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), Nov 2020, Buenos Aires, Argentina. pp.192-198, ⟨10.1109/FG47880.2020.00038⟩. ⟨hal-03174162⟩
[ HTTP ]
- Lisa Ouss, Giuseppe Palestra, Catherine Saint-Georges, Marluce Leitgel Gille, Mohamed Afshar, et al.. Behavior and interaction imaging at 9 months of age predict autism/intellectual disability in high-risk infants with West syndrome. Translational Psychiatry, 2020, 10 (1), pp.54. ⟨10.1038/s41398-020-0743-8⟩. ⟨hal-02553787⟩
-
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly. DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation. 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), Nov 2020, Buenos Aires, France. pp.146-152, ⟨10.1109/FG47880.2020.00039⟩. ⟨hal-03181865⟩
[ HTTP ]
- Sacha Bernheim, Estephe Arnaud, Arnaud Dapogny, Kevin Bailly. MoDuL: Deep Modal and Dual Landmark-wise Gated Network for Facial Expression Recognition. 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), Nov 2020, Buenos Aires, Argentina. pp.153-159, ⟨10.1109/FG47880.2020.00081⟩. ⟨hal-03181868⟩
-
Zakia Hammal, Di Huang, Kevin Bailly, Liming Chen, Mohamed Daoudi. Face and Gesture Analysis for Health Informatics (FGAHI). ACM International Conference on Multimodal Interaction (ICMI 2020), ACM, pp.874-875, 2020, ⟨10.1145/3382507.3419747⟩. ⟨hal-03186285⟩
[ HTTP ]
- Charline Grossard, Arnaud Dapogny, David Cohen, Sacha Bernheim, Estelle Juillet, et al.. Children with autism spectrum disorder produce more ambiguous and less socially meaningful facial expressions: an experimental study using random forest classifiers. Molecular Autism, 2020, 11, pp.5. ⟨10.1186/s13229-020-0312-2⟩. ⟨hal-02484406⟩
- Thomas Janssoone, Kevin Bailly, Gael Richard, Chloé Clavel. The POTUS Corpus, a database of weekly addresses for the study of stance in politics and virtual agents. Conference on Language Resources and Evaluation (LREC 2020), 2020, Marseille, France. pp.11 - 16. ⟨hal-02873020⟩
- Étienne de Montalivet, Kevin Bailly, Amélie Touillet, Noël Martinet, Jean Paysant, et al.. Guiding the training of users with a pattern similarity biofeedback to improve the performance of myoelectric pattern recognition.. IEEE Transactions on Neural Systems and Rehabilitation Engineering, In press, pp.1-11. ⟨10.1109/TNSRE.2020.3003077⟩. ⟨hal-02884543⟩
-
Arnaud Dapogny, Bailly Kevin, Matthieu Cord. DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild. The IEEE International Conference on Computer Vision (ICCV), Oct 2019, Seoul, South Korea. ⟨hal-02450430⟩
[ HTTP ]
- Kevin Bailly. Apprentissage automatique pour l'analyse des expressions faciales. Intelligence artificielle [cs.AI]. Sorbonne Université, 2019. ⟨tel-02489704⟩
- Arnaud Dapogny, Kevin Bailly, Séverine Dubuisson. Dynamic pose-robust facial expression recognition by multi-view pairwise conditional random forests. IEEE Transactions on Affective Computing, 2019, 10 (2), ⟨10.1109/TAFFC.2017.2708106⟩. ⟨hal-03181853⟩
-
Estephe Arnaud, Arnaud Dapogny, Kevin Bailly. Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignment. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2019, pp.1-1. ⟨10.1109/TBIOM.2019.2950032⟩. ⟨hal-02450422⟩
[ HTTP ]
-
Estephe Arnaud, Arnaud Dapogny, Kevin Bailly. Tree-gated deep regressor ensemble for face alignment in the wild. 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), May 2019, Lille, France. pp.1-7, ⟨10.1109/FG.2019.8756538⟩. ⟨hal-03181843⟩
[ HTTP ]
-
Arnaud Dapogny, Charline Grossard, Stephanie Hun, Sylvie Serret, Jérémy Bourgeois, et al.. JEMImE: A Serious Game to Teach Children with ASD How to Adequately Produce Facial Expressions. 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), May 2018, Xi'an, France. pp.723-730, ⟨10.1109/FG.2018.00114⟩. ⟨hal-02076870⟩
[ HTTP ]
- Arnaud Dapogny, Kevin Bailly, Séverine Dubuisson. Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit detection. International Journal of Computer Vision, 2018, 126, pp.255-271. ⟨10.1007/s11263-017-1010-1⟩. ⟨hal-01509850⟩
-
Charline Grossard, Laurence Chaby, Stephanie Hun, Hugues Pellerin, Jérémy Bourgeois, et al.. Children Facial Expression Production: Influence of Age, Gender, Emotion Subtype, Elicitation Condition and Culture. Frontiers in Psychology, 2018, 9, pp.446. ⟨10.3389/fpsyg.2018.00446⟩. ⟨hal-02422897⟩
[ HTTP ]
- Lisa Ouss, Marie-Thérèse Le Normand, Kevin Bailly, Marluce Leitgel Gille, Christelle Gosme, et al.. Developmental Trajectories of Hand Movements in Typical Infants and Those at Risk of Developmental Disorders: An Observational Study of Kinematics during the First Year of Life. Frontiers in Psychology, 2018, 9 (83 ), ⟨10.3389/fpsyg.2018.00083⟩. ⟨inserm-01807609⟩
-
Arnaud Dapogny, Kevin Bailly. Face alignment with cascaded semi-parametric deep greedy neural forests. Pattern Recognition Letters, 2018, 102, pp.75-81. ⟨10.1016/j.patrec.2017.12.010⟩. ⟨hal-03181852⟩
[ HTTP ]
-
Thomas Janssoone, Chloé Clavel, Kevin Bailly, Gael Richard. Règles d'Associations Temporelles de signaux sociaux pour la synthèse d'Agents Conversationnels Animés : Application aux attitudes sociales. Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2017, ⟨10.3166/RIA.31.511-537⟩. ⟨hal-02704911⟩
[ HTTP ]
-
Alex Vasquez, Arnaud Dapogny, Kevin Bailly, Véronique Perdereau. Sequential recognition of in-hand object shape using a collection of neural forests. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017, Vancouver, Canada. ⟨hal-03181845⟩
[ HTTP ]
-
Arnaud Dapogny, Kevin Bailly, Séverine Dubuisson. Multi-output random forests for facial action unit detection. International Conference on Automatic Face and Gesture Recognition (FG 2017), 2017, Washington, United States. pp.1-8. ⟨hal-03181844⟩
[ HTTP ]
- Charline Grossard, Ouriel Grynszpan, Sylvie Serret, Anne-Lise Jouen, Kevin Bailly, et al.. Serious games to teach social interactions and emotions to individuals with autism spectrum disorders (ASD). Computers and Education, 2017, 113, pp.195-211. ⟨10.1016/j.compedu.2017.05.002⟩. ⟨hal-01525828⟩
-
Jonathan Aigrain, Arnaud Dapogny, Kevin Bailly, Séverine Dubuisson, Marcin Detyniecki, et al.. On leveraging crowdsourced data for automatic perceived stress detection. ICMI 2016 - 18th ACM International Conference on Multimodal Interaction, Nov 2016, Tokyo, Japan. pp.113-120, ⟨10.1145/2993148.2993200⟩. ⟨hal-02422960⟩
[ HTTP ]
- Jérémie Nicolle, Kevin Bailly, Mohamed Chetouani. Real-Time Facial Action Unit Intensity Prediction with Regularized Metric Learning. Image and Vision Computing, 2016, 52, pp.1-14. ⟨10.1016/j.imavis.2016.03.004⟩. ⟨hal-01318177⟩
- Thomas Janssoone, Chloé Clavel, Kevin Bailly, Gael Richard. Using temporal association rules for the synthesis of embodied conversational agents with a specific stance. The Sixteenth International Conference on Intelligent Virtual Agents (IVA 2016), 2016, Los Angeles, United States. pp.1-14, ⟨10.1007/978-3-319-47665-0_16⟩. ⟨hal-03181846⟩
-
Jérémie Nicolle, Kevin Bailly, Mohamed Chetouani. Facial Action Unit intensity prediction via Hard Multi-Task Metric Learning for Kernel Regression. 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), May 2015, Ljubljana, France. pp.1-6, ⟨10.1109/FG.2015.7284868⟩. ⟨hal-02423008⟩
[ HTTP ]
- Arnaud Dapogny, Kevin Bailly, Séverine Dubuisson. Pairwise conditional random forests for facial expression recognition. International Conference on Computer Vision (ICCV 2015), 2015, Santiago, Chile. pp.1-8. ⟨hal-03181848⟩
- Arnaud Dapogny, Kevin Bailly, Séverine Dubuisson. Dynamic facial expression recognition by joint static and multi-time gap transition classification. International Conference on Automatic Face and Gesture Recognition, 2015, Ljubljana, Slovenia. ⟨10.1109/FG.2015.7163111⟩. ⟨hal-03181847⟩
- Jérémie Nicolle, Vincent Rapp, Kevin Bailly, Lionel Prevost, Mohamed Chetouani. Audio-visual emotion recognition: A dynamic, multimodal approach. IHM'14, 26e conférence francophone sur l'Interaction Homme-Machine, Oct 2014, Lille, France. pp.44-51, 2014. ⟨hal-01089628⟩
-
Thibaud Sénéchal, Kevin Bailly, Lionel Prevost. Impact of action unit detection in automatic emotion recognition. Pattern Analysis and Applications, 2014, 17 (1), pp.51-67. ⟨hal-01279720⟩
[ HTTP ]
- Lucas Zamuner, Kevin Bailly, Erwan Bigorgne. A Pose-adaptive constrained local model for accurate head pose tracking. International Conference on Pattern Recognition (ICPR 2014), 2014, Stockholm, Sweden. pp.1-6, ⟨10.1109/ICPR.2014.436⟩. ⟨hal-03181849⟩
-
Jérémie Nicolle, Kevin Bailly, Vincent Rapp, Mohamed Chetouani. Locating facial landmarks with binary map cross-correlations. 2013 20th IEEE International Conference on Image Processing (ICIP), Sep 2013, Melbourne, Australia. pp.2978-2982, ⟨10.1109/ICIP.2013.6738613⟩. ⟨hal-02423139⟩
[ HTTP ]
-
Rapp Vincent, Kevin Bailly, Thibaud Sénéchal, Lionel Prevost. Multi-kernel appearance model. Image and Vision Computing, 2013, 31 (8), pp.542-554. ⟨hal-01279721⟩
[ HTTP ]