MOV (ViT-L/14)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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
87.1
best: 92.8 (OTI(ViT-L/14))
SOTA
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
64.7
SOTA
Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models arXiv:2207.07646