InternVideo combines masked video modeling and video-language contrastive learning into a single foundation model that reaches state-of-the-art results on 39 video datasets including 91.1% top-1 on Kinetics-400.
VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
InternVideo combines masked video modeling and video-language contrastive learning into a single foundation model that reaches state-of-the-art results on 39 video datasets including 91.1% top-1 on Kinetics-400.