HATNet (32 frames)
Reported on 5 benchmarks across 3 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Robots2 results
- Average accuracy of 3 splits· 2019-04-2576.5best: 88.7 (VideoMAE V2-g)
- 3-fold Accuracy· 2019-04-2597.8best: 99.7 (FTP-UniFormerV2-L/14)
Time Series2 results
- Average accuracy of 3 splits· 2019-04-2576.5best: 88.7 (VideoMAE V2-g)
- 3-fold Accuracy· 2019-04-2597.8best: 99.7 (FTP-UniFormerV2-L/14)
Computer Vision1 result
- Acc@1· 2019-04-2577.6best: 93.6 (OmniVec2)