 Temporal Action Localization with Cross Layer Task Decoupling and
RefinementAAAI Conference on Artificial Intelligence (AAAI), 2024 |
 A Challenging Multimodal Video Summary: Simultaneously Extracting and
Generating Keyframe-Caption Pairs from VideoConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 SVCNet: Scribble-based Video Colorization Network with Temporal
AggregationIEEE Transactions on Image Processing (IEEE TIP), 2023 |
 Pose is all you need: The pose only group activity recognition system
(POGARS)Machine Vision and Applications (MVA), 2021 |
 U-LanD: Uncertainty-Driven Video Landmark DetectionIEEE Transactions on Medical Imaging (IEEE TMI), 2021 |
