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 (ImageNet-21k pretrain)

MViTv2-L (ImageNet-21k pretrain)

Reported on 6 benchmarks across 1 task · 1 paper · 3 SOTA

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

Computer Vision6 results

VideoonKinetics-700
Top-1 Accuracy· uses extra data· 2021-12-02
79.4
best: 85.9 (InternVideo2-6B)
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
VideoonKinetics-700
Top-5 Accuracy· uses extra data· 2021-12-02
94.9
best: 96.7 (UMT-L (ViT-L/16))
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
VideoonKinetics-600
Top-1 Accuracy· 2021-12-02
87.9
best: 91.9 (InternVideo2-6B)
SOTA
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
VideoonKinetics-400
Acc@1· uses extra data· 2021-12-02
86.1
best: 93.6 (OmniVec2)
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
VideoonKinetics-400
Acc@5· uses extra data· 2021-12-02
97
best: 98.9 (TubeViT-H (ImageNet-1k))
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526
VideoonKinetics-600
Top-5 Accuracy· 2021-12-02
97.9
best: 98.9 (TubeVit-H)
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection arXiv:2112.01526