TrajTok: Learning Trajectory Tokens enables better Video Understanding 事件

TrajTok: Learning Trajectory Tokens enables better Video Understanding arXiv:2602.22779v3 Announce Type: replace Abstract: Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and tas