RGB-I3D (Kinetics pre-training)

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· uses extra data· 2017-05-22
74.3
best: 88.7 (VideoMAE V2-g)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
Activity RecognitiononUCF101
3-fold Accuracy· uses extra data· 2017-05-22
95.1
best: 99.7 (FTP-UniFormerV2-L/14)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750

Time Series2 results

Action RecognitiononHMDB-51
Average accuracy of 3 splits· uses extra data· 2017-05-22
74.3
best: 88.7 (VideoMAE V2-g)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
Action RecognitiononUCF101
3-fold Accuracy· uses extra data· 2017-05-22
95.1
best: 99.7 (FTP-UniFormerV2-L/14)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750