Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CVRL (R3D-50; K400)

CVRL (R3D-50; K400)

Reported on 8 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.

Robots4 results

Activity RecognitiononUCF101 (finetuned)
3-fold Accuracy· 2020-08-09
92.2
best: 95.7 (BraVe:V-FA (TSM-50x2))
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800
Activity RecognitiononUCF101
3-fold Accuracy· 2020-08-09
92.2
best: 99.7 (FTP-UniFormerV2-L/14)
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800
Activity RecognitiononHMDB51
Top-1 Accuracy· 2020-08-09
66.7
best: 79.7 (MVD (ViT-B))
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800
Activity RecognitiononHMDB51 (finetuned)
Top-1 Accuracy· 2020-08-09
66.7
best: 77.8 (BraVe:V-FA (TSM-50x2))
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800

Time Series4 results

Action RecognitiononUCF101 (finetuned)
3-fold Accuracy· 2020-08-09
92.2
best: 95.7 (BraVe:V-FA (TSM-50x2))
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800
Action RecognitiononUCF101
3-fold Accuracy· 2020-08-09
92.2
best: 99.7 (FTP-UniFormerV2-L/14)
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800
Action RecognitiononHMDB51
Top-1 Accuracy· 2020-08-09
66.7
best: 79.7 (MVD (ViT-B))
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800
Action RecognitiononHMDB51 (finetuned)
Top-1 Accuracy· 2020-08-09
66.7
best: 77.8 (BraVe:V-FA (TSM-50x2))
Spatiotemporal Contrastive Video Representation Learning arXiv:2008.03800