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/MViT-B, 16x4

MViT-B, 16x4

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-400
Acc@1· 2021-04-22
78.4
best: 93.6 (OmniVec2)
Multiscale Vision Transformers arXiv:2104.11227
VideoonKinetics-400
Acc@5· 2021-04-22
93.5
best: 98.9 (TubeViT-H (ImageNet-1k))
Multiscale Vision Transformers arXiv:2104.11227
VideoonKinetics-600
Top-1 Accuracy· 2021-04-22
82.1
best: 91.9 (InternVideo2-6B)
Multiscale Vision Transformers arXiv:2104.11227
VideoonKinetics-600
Top-5 Accuracy· 2021-04-22
95.7
best: 98.9 (TubeVit-H)
Multiscale Vision Transformers arXiv:2104.11227

Robots2 results

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-04-22
66.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Multiscale Vision Transformers arXiv:2104.11227
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-04-22
90.2
best: 96.3 (DejaVid)
Multiscale Vision Transformers arXiv:2104.11227

Time Series2 results

Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-04-22
66.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Multiscale Vision Transformers arXiv:2104.11227
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-04-22
90.2
best: 96.3 (DejaVid)
Multiscale Vision Transformers arXiv:2104.11227