ALE

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 RecognitiononKinetics
Top-1 Accuracy· 2015-03-30
23.4
best: 78.1 (TC-CLIP)
SOTA
Label-Embedding for Image Classification arXiv:1503.08677
Zero-Shot Action RecognitiononKinetics
Top-5 Accuracy· 2015-03-30
50.3
best: 95.7 (TC-CLIP)
SOTA
Label-Embedding for Image Classification arXiv:1503.08677