MOV (ViT-B/16)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Zero-Shot Action RecognitiononUCF101
Top-1 Accuracy· 2022-07-15
82.6
best: 92.8 (OTI(ViT-L/14))
Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models arXiv:2207.07646
Zero-Shot Action RecognitiononHMDB51
Top-1 Accuracy· 2022-07-15
60.8
best: 64.7 (MOV (ViT-L/14))
Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models arXiv:2207.07646