https://github.com/bytedance/shot2story
A new multi-shot video understanding benchmark Shot2Story20K with detailed shot-level captions and comprehensive video summaries.
https://github.com/bytedance/shot2story
benchmark dataset large-language-models video-captioning video-language video-language-pretraining video-question-answering video-story video-story-generation video-summarization vision-language
Last synced: about 1 month ago
JSON representation
A new multi-shot video understanding benchmark Shot2Story20K with detailed shot-level captions and comprehensive video summaries.
- Host: GitHub
- URL: https://github.com/bytedance/shot2story
- Owner: bytedance
- Created: 2023-12-16T16:27:18.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-03-19T13:45:41.000Z (about 1 year ago)
- Last Synced: 2024-04-16T04:13:59.783Z (about 1 year ago)
- Topics: benchmark, dataset, large-language-models, video-captioning, video-language, video-language-pretraining, video-question-answering, video-story, video-story-generation, video-summarization, vision-language
- Language: Python
- Homepage: https://mingfei.info/shot2story
- Size: 153 MB
- Stars: 42
- Watchers: 6
- Forks: 2
- Open Issues: 3
-
Metadata Files:
- Readme: README.md