Learning by Aligning Videos in Time S Haresh, S Kumar, H Coskun, SN Syed, A Konin, MZ Zia, QH Tran IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 | 64 | 2021 |
Unsupervised Activity Segmentation by Joint Representation Learning and Online Clustering S Kumar, S Haresh, A Ahmed, A Konin, MZ Zia, QH Tran IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 | 49 | 2022 |
Graph Inverse Reinforcement Learning from Diverse Videos S Kumar, J Zamora, N Hansen, R Jangir, X Wang Conference on Robot Learning (CoRL) 2022, 2022 | 33 | 2022 |
Towards Anomaly Detection in Dashcam Videos S Haresh, S Kumar, MZ Zia, QH Tran IEEE Intelligent Vehicles Symposium (IV), 2020 | 29 | 2020 |
Focused anchors loss: Cost-sensitive learning of discriminative features for imbalanced classification BK Baloch, S Kumar, S Haresh, A Rehman, T Syed Asian Conference on Machine Learning, 822-835, 2019 | 12 | 2019 |
System and method for building computational models of a goal-driven task from demonstration MZ Zia, QH Tran, A Konin, S Haresh, S Kumar US Patent 11,017,690, 2021 | 8 | 2021 |
The devil is in the details: A deep dive into the rabbit hole of data filtering H Yu, Y Tian, S Kumar, L Yang, H Wang arXiv preprint arXiv:2309.15954, 2023 | 5 | 2023 |
Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters W Wang, K Mrini, L Yang, S Kumar, Y Tian, X Yan, H Wang arXiv preprint arXiv:2403.02677, 2024 | 2 | 2024 |
Improving Explanations of Image Classifiers: Ensembles and Multitask Learning A Ahamed, K Alipour, S Kumar, S Soltani, M Pazzani International Journal of Artificial Intelligence and Applications, 2022 | 2* | 2022 |
System and method for determining sub-activities in videos and segmenting the videos with little to no annotation QH Tran, MZ Zia, A Konin, S Kumar, S Haresh, A Ahmed, H Khan, ... US Patent App. 17/752,946, 2022 | 1 | 2022 |
System and method for learning human activities from video demonstrations using video augmentation QH Tran, MZ Zia, A Konin, S Haresh, S Kumar US Patent 11,941,080, 2024 | | 2024 |
System and method for correlating video frames in a computing environment QH Tran, MZ Zia, A Konin, S Haresh, S Kumar, SN Syed US Patent 11,368,756, 2022 | | 2022 |
De-correlating learned weights for improving generalization performance in deep neural networks S Haresh, BK Baloch, S Kumar, A Thomas, T Syed 23rd Iberoamerican Congress Late Breaking Works Proceedings, 34-36, 2018 | | 2018 |
Supplementary Material: Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering S Kumar, S Haresh, A Ahmed, A Konin, MZ Zia, QH Tran | | |
Supplementary Material: Learning by Aligning Videos in Time S Haresh, S Kumar, HCSN Syed, AKMZZ Quoc, H Tran | | |