There are 3 repositories under long-video-understanding topic.
Multi-granularity Correspondence Learning from Long-term Noisy Videos [ICLR 2024, Oral]
[EMNLP 2023] TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
Winner solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2023 workshop)
Language Repository for Long Video Understanding