TVNet+IDT

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots2 results

Activity RecognitiononHMDB-51
Average accuracy of 3 splits· 2018-04-02
72.6
best: 88.7 (VideoMAE V2-g)
End-to-End Learning of Motion Representation for Video Understanding arXiv:1804.00413
Activity RecognitiononUCF101
3-fold Accuracy· 2018-04-02
95.4
best: 99.7 (FTP-UniFormerV2-L/14)
End-to-End Learning of Motion Representation for Video Understanding arXiv:1804.00413

Time Series2 results

Action RecognitiononHMDB-51
Average accuracy of 3 splits· 2018-04-02
72.6
best: 88.7 (VideoMAE V2-g)
End-to-End Learning of Motion Representation for Video Understanding arXiv:1804.00413
Action RecognitiononUCF101
3-fold Accuracy· 2018-04-02
95.4
best: 99.7 (FTP-UniFormerV2-L/14)
End-to-End Learning of Motion Representation for Video Understanding arXiv:1804.00413