Multi-view action recognition using contrastive learning K Shah, A Shah, CP Lau, CM de Melo, R Chellappa Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2023 | 25 | 2023 |
Felmi: Few shot learning with hard mixup A Roy, A Shah, K Shah, P Dhar, A Cherian, R Chellappa Advances in Neural Information Processing Systems 35, 24474-24486, 2022 | 22 | 2022 |
Synthetic-to-real domain adaptation for action recognition: A dataset and baseline performances AV Reddy, K Shah, W Paul, R Mocharla, J Hoffman, KD Katyal, ... 2023 IEEE International Conference on Robotics and Automation (ICRA), 11374 …, 2023 | 16 | 2023 |
Diffalign: Few-shot learning using diffusion based synthesis and alignment A Roy, A Shah, K Shah, A Roy, R Chellappa arXiv preprint arXiv:2212.05404 3, 2022 | 12 | 2022 |
Halp: Hallucinating latent positives for skeleton-based self-supervised learning of actions A Shah, A Roy, K Shah, S Mishra, D Jacobs, A Cherian, R Chellappa Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 11 | 2023 |
Improved modeling of 3D shapes with multi-view depth maps K Gupta, S Jabbireddy, K Shah, A Shrivastava, M Zwicker 2020 International Conference on 3D Vision (3DV), 71-80, 2020 | 7 | 2020 |
Diffnat: Improving diffusion image quality using natural image statistics A Roy, M Suin, A Shah, K Shah, J Liu, R Chellappa arXiv preprint arXiv:2311.09753, 2023 | 2 | 2023 |
Cap2aug: Caption guided image to image data augmentation A Roy, A Shah, K Shah, A Roy, R Chellappa arXiv preprint arXiv:2212.05404, 2022 | 2 | 2022 |
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training A Reddy, W Paul, C Rivera, K Shah, CM de Melo, R Chellappa Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 1 | 2024 |
Leveraging synthetic data for robust gesture recognition K Katyal, R Chellappa, K Shah, A Reddy, J Hoffman, W Paul, R Mocharla, ... Synthetic Data for Artificial Intelligence and Machine Learning: Tools …, 2023 | 1 | 2023 |
An evaluation of large pre-trained models for gesture recognition using synthetic videos A Reddy, K Shah, C Rivera, W Paul, CM De Melo, R Chellappa Synthetic Data for Artificial Intelligence and Machine Learning: Tools …, 2024 | | 2024 |
MV2MAE: Multi-View Video Masked Autoencoders K Shah, R Crandall, J Xu, P Zhou, M George, M Bansal, R Chellappa arXiv preprint arXiv:2401.15900, 2024 | | 2024 |
A proposal-based solution to spatio-temporal action detection in untrimmed videos K Shah, J Gleason, R Chellappa | | |