O2A

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· 2015-10-23
30.3
best: 92.8 (OTI(ViT-L/14))
SOTA
Objects2action: Classifying and localizing actions without any video example arXiv:1510.06939
Zero-Shot Action RecognitiononHMDB51
Top-1 Accuracy· 2015-10-23
15.6
best: 64.7 (MOV (ViT-L/14))
SOTA
Objects2action: Classifying and localizing actions without any video example arXiv:1510.06939