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/TubeViT-L

TubeViT-L

Reported on 7 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Computer Vision3 results

VideoonKinetics-700
Top-5 Accuracy· 2022-12-06
96.6
best: 96.7 (UMT-L (ViT-L/16))
SOTA
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229
VideoonKinetics-700
Top-1 Accuracy· 2022-12-06
83.8
best: 85.9 (InternVideo2-6B)
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229
VideoonCharades
MAP· 2022-12-06
66.2
best: 66.3 (TokenLearner)
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229

Robots2 results

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2022-12-06
76.1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2022-12-06
95.2
best: 96.3 (DejaVid)
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229

Time Series2 results

Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2022-12-06
76.1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2022-12-06
95.2
best: 96.3 (DejaVid)
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning arXiv:2212.03229