R[2+1]D (VideoMoCo)

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· 2021-03-10
49.2
best: 88.7 (VideoMAE V2-g)
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples arXiv:2103.05905
Activity RecognitiononUCF101
3-fold Accuracy· 2021-03-10
78.7
best: 99.7 (FTP-UniFormerV2-L/14)
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples arXiv:2103.05905

Time Series2 results

Action RecognitiononHMDB-51
Average accuracy of 3 splits· 2021-03-10
49.2
best: 88.7 (VideoMAE V2-g)
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples arXiv:2103.05905
Action RecognitiononUCF101
3-fold Accuracy· 2021-03-10
78.7
best: 99.7 (FTP-UniFormerV2-L/14)
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples arXiv:2103.05905