bytedance/Shot2Story

A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.

语言：Python · GitHub 星标：181 · Fork：10

话题：benchmark · dataset · large-language-models · research · video-captioning · video-language · video-language-pretraining · video-question-answering

在 GitHub 上查看原仓库