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/SRTG r3d-34

SRTG r3d-34

Reported on 8 benchmarks across 3 tasks · 1 paper

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

Computer Vision4 results

VideoonKinetics-700
Top-1 Accuracy· 2020-06-15
49.15
best: 85.9 (InternVideo2-6B)
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247
VideoonKinetics-700
Top-5 Accuracy· 2020-06-15
72.68
best: 96.7 (UMT-L (ViT-L/16))
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247
VideoonMiT
Top 1 Accuracy· 2020-06-15
28.55
best: 53.1 (OmniVec2)
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247
VideoonMiT
Top 5 Accuracy· 2020-06-15
52.35
best: 78.2 (UMT-L (ViT-L/16))
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247

Robots2 results

Activity RecognitiononHACS
Top 1 Accuracy· 2020-06-15
78.6
best: 97 (InternVideo2-6B)
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247
Activity RecognitiononHACS
Top 5 Accuracy· 2020-06-15
93.57
best: 99.8 (UniFormerV2-L)
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247

Time Series2 results

Action RecognitiononHACS
Top 1 Accuracy· 2020-06-15
78.6
best: 97 (InternVideo2-6B)
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247
Action RecognitiononHACS
Top 5 Accuracy· 2020-06-15
93.57
best: 99.8 (UniFormerV2-L)
Learn to cycle: Time-consistent feature discovery for action recognition arXiv:2006.08247