ResT

Reported on 3 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 Vision3 results

Zero-Shot Action RecognitiononUCF101
Top-1 Accuracy· 2022-05-03
58.7
best: 92.8 (OTI(ViT-L/14))
SOTA
Cross-modal Representation Learning for Zero-shot Action Recognition arXiv:2205.01657
Zero-Shot Action RecognitiononActivityNet
Top-1 Accuracy· 2022-05-03
32.5
best: 86.2 (BIKE)
SOTA
Cross-modal Representation Learning for Zero-shot Action Recognition arXiv:2205.01657
Zero-Shot Action RecognitiononHMDB51
Top-1 Accuracy· 2022-05-03
41.1
best: 64.7 (MOV (ViT-L/14))
Cross-modal Representation Learning for Zero-shot Action Recognition arXiv:2205.01657