| Harnessing Temporal Causality for Advanced Temporal Action Detection | Jul 25, 2024 | Action DetectionAction Recognition | CodeCode Available | 3 |
| Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge | Nov 16, 2022 | Action LocalizationMoment Queries | CodeCode Available | 2 |
| UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection | Apr 7, 2024 | Action DetectionMoment Queries | CodeCode Available | 2 |
| NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023 | Jul 5, 2023 | Action LocalizationMoment Queries | CodeCode Available | 2 |
| Egocentric Video-Language Pretraining | Jun 3, 2022 | Action RecognitionContrastive Learning | CodeCode Available | 2 |
| EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation | Jun 26, 2024 | Action AnticipationAction Recognition | CodeCode Available | 2 |
| InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges | Nov 17, 2022 | Future Hand PredictionMoment Queries | CodeCode Available | 1 |
| EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone | Jul 11, 2023 | Action RecognitionMoment Queries | CodeCode Available | 1 |
| Knowing Where to Focus: Event-aware Transformer for Video Grounding | Aug 14, 2023 | Moment QueriesSentence | CodeCode Available | 1 |
| OSGNet @ Ego4D Episodic Memory Challenge 2025 | Jun 4, 2025 | Moment QueriesNatural Language Queries | CodeCode Available | 1 |
