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/MViTv2-L (IN-21K + Kinetics400 pretrain)

MViTv2-L (IN-21K + Kinetics400 pretrain)

Reported on 6 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.

Robots3 results

Activity RecognitiononSomething-Something V2
Parameters· 2021-12-02
213.1
best: 2131 (InternVideo2-6B)
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2021-12-02
73.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2021-12-02
94.1
best: 96.3 (DejaVid)
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526

Time Series3 results

Action RecognitiononSomething-Something V2
Parameters· 2021-12-02
213.1
best: 2131 (InternVideo2-6B)
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2021-12-02
73.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2021-12-02
94.1
best: 96.3 (DejaVid)
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526