video-understanding-dataset topic

A Large Short-video Recommendation Dataset with Raw Text/Audio/Image/Videos (Talk Invited by DeepMind).

westlake-repl

A benchmark that focuses on the sampling dilemma in long-video tasks. Through well-designed tasks, it evaluates the sampling efficiency of long-video VLMs. (ICCV2025)

dvlab-research

🔥 Omni large models and datasets for understanding and generating multi-modalities.

LJungang