AVID (Modified R2+1D-18 on Kinetics)

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 RecognitiononUCF101
3-fold Accuracy· 2020-04-27
86.9
best: 99.7 (FTP-UniFormerV2-L/14)
Audio-Visual Instance Discrimination with Cross-Modal Agreement arXiv:2004.12943
Activity RecognitiononHMDB51
Top-1 Accuracy· 2020-04-27
59.9
best: 79.7 (MVD (ViT-B))
Audio-Visual Instance Discrimination with Cross-Modal Agreement arXiv:2004.12943

Time Series2 results

Action RecognitiononUCF101
3-fold Accuracy· 2020-04-27
86.9
best: 99.7 (FTP-UniFormerV2-L/14)
Audio-Visual Instance Discrimination with Cross-Modal Agreement arXiv:2004.12943
Action RecognitiononHMDB51
Top-1 Accuracy· 2020-04-27
59.9
best: 79.7 (MVD (ViT-B))
Audio-Visual Instance Discrimination with Cross-Modal Agreement arXiv:2004.12943