AURL

Reported on 2 benchmarks across 1 task · 1 paper · 1 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· 2022-03-29
58
best: 92.8 (OTI(ViT-L/14))
SOTA
Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification arXiv:2203.15381
Zero-Shot Action RecognitiononHMDB51
Top-1 Accuracy· 2022-03-29
39
best: 64.7 (MOV (ViT-L/14))
Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification arXiv:2203.15381