This user has not added any information to their profile yet.
- Reliability in semantic segmentation: are we on the right track?
Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 18-22 June, 2023
- PoseBERT: a generic transformer module for temporal 3D human modeling
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), IEEE, Special issue on Transformer Models in Vision, 12 December, 2022
- Make some noise: reliable and efficient single-step adversarial training
Neural Information Processing Systems (NeurIPS), hybrid event, New Orleans, Louisiana, USA, 28 November – 9 December, 2022
- PoseGPT: quantization-based 3D human motion generation and forecasting
European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 23–27 October, 2022
- PoseScript: 3D human poses from natural language
European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 23–27 October, 2022
- MonoNHR: monocular neural human renderer
International Conference on 3D Vision 2022, Prague, Czechia, 12-15 September, 2022
- Make some noise: reliable and efficient single-step adversarial training
Workshop on New Frontiers in Adversarial Machine Learning (ADVML) at ICML 2022, Baltimore, Maryland, USA, 22 July 2022
- Catastrophic overfitting is a bug but also a feature
Workshop on New Frontiers in Adversarial Machine Learning (ADVML) at ICML 2022, 22 July 2022, Baltimore, Maryland, USA.
- Barely-supervised learning: semi-supervised learning with very few labeled images
36th Conference on Artificial Intelligence (AAAI-22), virtual event, 22 February - 1 March, 2022
- Leveraging MoCap data for human mesh recovery
Published on arXiv.org, 18 October, 2021. Accepted at 3DV 2021
- Learning in a changing environment: memory strategies for streaming learning under distributional shifts.
Findings of the Workshop on Continual Learning in Computer Vision (CLVISION) at the Conference on Computer Vision and Pattern Recognition (CVPR), virtual event, 25 June 2021
- Continual adaptation of visual representations via domain randomization and meta-learning
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 4443-4453.
- Multi-FinGAN: generative coarse-to-fine sampling of multi-finger grasps
IEEE International Conference on Robotics and Automation (ICRA), Xi’an, China, 30 May-5 June, 2021
- Progressive skeletonization: trimming more fat from a network at initialization
International Conference on Learning Representations (ICLR), virtual event, 4-8 May, 2021
- SMPLy benchmarking 3D human pose estimation in the wild
8th International Conference on 3D Vision, 25-28 November, 2020
- DOPE: distillation of part experts for whole-body 3D pose estimation in the wild
European Conference on Computer Vision (ECCV), Glasgow, UK (virtual event), 23-28 August, 2020
- GanHand: predicting human grasp affordances in multi-object scenes
Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, 16-18 June, 2020
- Mimetics: towards understanding human actions out of context
arXiv
- Moulding humans: non-parametric 3D human shape estimation from single images
International Conference on Computer Vision (ICCV), Seoul, South Korea, 27 October-2 November, 2019
- LCR-Net++: Multi-person 2D and 3D pose detection in natural images
IEEE Transactions on Pattern Analysis and Machine Intelligence
- LCR-Net: Localization-Classification-Regression for Human Pose
CVPR 17, Honolulu, US, 22-25 July, 2017
