InternVid supplies 7M videos and LLM captions to train ViCLIP, which reaches leading zero-shot action recognition and competitive retrieval performance.
Howto100m: Learning a text-video embedding by watching hundred million narrated video clips
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
InternVid supplies 7M videos and LLM captions to train ViCLIP, which reaches leading zero-shot action recognition and competitive retrieval performance.