Motion & Appearance (C3D)

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· 2019-04-07
58.8
best: 99.7 (FTP-UniFormerV2-L/14)
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics arXiv:1904.03597
Activity RecognitiononHMDB51
Top-1 Accuracy· 2019-04-07
20.3
best: 79.7 (MVD (ViT-B))
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics arXiv:1904.03597

Time Series2 results

Action RecognitiononUCF101
3-fold Accuracy· 2019-04-07
58.8
best: 99.7 (FTP-UniFormerV2-L/14)
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics arXiv:1904.03597
Action RecognitiononHMDB51
Top-1 Accuracy· 2019-04-07
20.3
best: 79.7 (MVD (ViT-B))
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics arXiv:1904.03597