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/BraVe:V-FA (TSM-50x2)

BraVe:V-FA (TSM-50x2)

Reported on 10 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots5 results

Activity RecognitiononUCF101 (finetuned)
3-fold Accuracy· 2021-03-30
95.7
SOTA
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Activity RecognitiononHMDB51
Top-1 Accuracy· 2021-03-30
70.5
best: 79.7 (MVD (ViT-B))
SOTA
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Activity RecognitiononHMDB51 (finetuned)
Top-1 Accuracy· 2021-03-30
77.8
SOTA
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Activity RecognitiononUCF101
3-fold Accuracy· 2021-03-30
93.1
best: 99.7 (FTP-UniFormerV2-L/14)
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Activity RecognitiononKinetics-600
Top-1 Accuracy· 2021-03-30
71.4
best: 87.8 (Florence)
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559

Time Series5 results

Action RecognitiononUCF101 (finetuned)
3-fold Accuracy· 2021-03-30
95.7
SOTA
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Action RecognitiononHMDB51
Top-1 Accuracy· 2021-03-30
70.5
best: 79.7 (MVD (ViT-B))
SOTA
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Action RecognitiononHMDB51 (finetuned)
Top-1 Accuracy· 2021-03-30
77.8
SOTA
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Action RecognitiononUCF101
3-fold Accuracy· 2021-03-30
93.1
best: 99.7 (FTP-UniFormerV2-L/14)
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559
Action RecognitiononKinetics-600
Top-1 Accuracy· 2021-03-30
71.4
best: 87.8 (Florence)
Broaden Your Views for Self-Supervised Video Learning arXiv:2103.16559