ActionCLIP (ViT-B/16)
Reported on 4 benchmarks across 4 tasks · 1 paper · 3 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision2 results
- Top-1 Accuracy· 2021-09-17SOTA83.8best: 86.5 (Florence)
Robots1 result
- Top-1 Accuracy· 2021-09-17SOTA83.8best: 86.5 (Florence)
Time Series1 result
- Top-1 Accuracy· 2021-09-17SOTA83.8best: 86.5 (Florence)