| Areas of attention for image captioning M Pedersoli, T Lucas, C Schmid, J Verbeek International Conference on Computer Vision (ICCV), 2017 | 255 | 2017 |
| CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow P Weinzaepfel, T Lucas, V Leroy, Y Cabon, V Arora, R Bregier, G Csurka, ... International Conference on Computer Vision (ICCV), 2023 | 65 | 2023 |
| PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting T Lucas*, F Baradel*, P Weinzaepfel, G Rogez European Conference on Computer Vision (ECCV), 2022 | 62 | 2022 |
| CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion P Weinzaepfel, V Leroy, T Lucas, R Brégier, Y Cabon, V Arora, L Antsfeld, ... Neural Information Processing Systems (NeurIPS), 2022 | 53 | 2022 |
| PoseScript: 3D Human Poses from Natural Language G Delmas, P Weinzaepfel, T Lucas, MN Francesc, G Rogez European Conference on Computer Vision (ECCV), 2022 | 52 | 2022 |
| Learning Super-Features for Image Retrieval P Weinzaepfel, T Lucas, D Larlus, Y Kalantidis International Conference on Learning Representations (ICLR), 2022 | 48 | 2022 |
| Mixed batches and symmetric discriminators for GAN training T Lucas, C Tallec, J Verbeek, Y Ollivier International Conference on Machine Learning (ICML), 2018 | 44 | 2018 |
| Adaptive density estimation for generative models T Lucas, K Shmelkov, K Alahari, C Schmid, J Verbeek Advances in Neural Information Processing Systems (NeurIPS), 2019 | 37* | 2019 |
| Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images T Lucas, P Weinzaepfel, G Rogez Conference on artificial intelligence (AAAI), 2021 | 28 | 2021 |
| Auxiliary guided autoregressive variational autoencoder T Lucas, J Verbeek European Conference on Machine Learning (ECML-PKDD), 2018 | 19 | 2018 |
| Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot F Baradel*, M Armando, R Brégier, P Weinzaepfel, G Rogez, T Lucas* European Conference in Computer Vision (ECCV), 2024 | 8 | 2024 |
| T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences T Lee, F Baradel, T Lucas, KM Lee, G Rogez Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 2 | 2024 |
| Cross-view and Cross-pose Completion for 3D Human Understanding M Armando, S Galaaoui, F Baradel, T Lucas, V Leroy, R Brégier, ... Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | 2 | 2024 |
| Deep generative models: over-generalisation and mode-dropping T Lucas Thesis manuscript, 2020 | 2 | 2020 |
| UNIC: Universal classification models via multi-teacher distillation MB Sariyildiz, P Weinzaepfel, T Lucas, D Larlus, Y Kalantidis European Conference on Computer Vision (ECCV), 2024 | 1 | 2024 |
| Win-Win: Training High-Resolution Vision Transformers from Two Windows V Leroy, J Revaud, T Lucas, P Weinzaepfel International Conference on Learning Representations (ICLR), 2024 | 1 | 2024 |
| System and method of semi-supervised learning with few labeled images per class P Weinzaepfel, G Rogez, T Lucas US Patent App. 17/708,214, 2023 | 1 | 2023 |
| Unsupervised pre-training of geometric vision models R Brégier, Y Cabon, T Lucas, J Revaud, P Weinzaepfel, B Chidlovskii, ... US Patent App. 18/230,414, 2024 | | 2024 |
| Motion generation systems and methods T Lucas, F Baradel, P Weinzaepfel, G Rogez US Patent App. 17/956,022, 2024 | | 2024 |
| Purposer: Putting Human Motion Generation in Context N Ugrinovic, T Lucas, F Baradel, P Weinzaepfel, G Rogez, ... International Conference in 3D Vision (3DV), 2024 | | 2024 |
Philippe WeinzaepfelResearch Scientist, Naver Labs EuropeVerified email at naverlabs.com
