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/RSANet-R50 (8 frames, ImageNet pretrained, a single clip)

RSANet-R50 (8 frames, ImageNet pretrained, a single clip)

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 RecognitiononSomething-Something V1
Top 1 Accuracy· 2021-11-02
51.9
best: 70 (InternVideo)
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673
Activity RecognitiononSomething-Something V1
Top 5 Accuracy· 2021-11-02
79.6
best: 91.9 (VideoMAE V2-g)
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-11-02
64.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-11-02
89.1
best: 96.3 (DejaVid)
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673

Time Series4 results

Action RecognitiononSomething-Something V1
Top 1 Accuracy· 2021-11-02
51.9
best: 70 (InternVideo)
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673
Action RecognitiononSomething-Something V1
Top 5 Accuracy· 2021-11-02
79.6
best: 91.9 (VideoMAE V2-g)
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-11-02
64.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-11-02
89.1
best: 96.3 (DejaVid)
Relational Self-Attention: What's Missing in Attention for Video Understanding arXiv:2111.01673