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/AMD(ViT-B/16)

AMD(ViT-B/16)

Reported on 15 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.

Robots6 results

Activity RecognitiononHMDB-51
Average accuracy of 3 splits· uses extra data· 2023-11-06
79.6
best: 88.7 (VideoMAE V2-g)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Activity RecognitiononSomething-Something V2
Parameters· 2023-11-06
87
best: 2131 (InternVideo2-6B)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-11-06
73.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-11-06
94
best: 96.3 (DejaVid)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Activity RecognitiononUCF101
3-fold Accuracy· uses extra data· 2023-11-06
97.1
best: 99.7 (FTP-UniFormerV2-L/14)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Activity RecognitiononAVA v2.2
mAP· uses extra data· 2023-11-06
33.5
best: 45.1 (LART (Hiera-H, K700 PT+FT))
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149

Time Series6 results

Action RecognitiononHMDB-51
Average accuracy of 3 splits· uses extra data· 2023-11-06
79.6
best: 88.7 (VideoMAE V2-g)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Action RecognitiononSomething-Something V2
Parameters· 2023-11-06
87
best: 2131 (InternVideo2-6B)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-11-06
73.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-11-06
94
best: 96.3 (DejaVid)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Action RecognitiononUCF101
3-fold Accuracy· uses extra data· 2023-11-06
97.1
best: 99.7 (FTP-UniFormerV2-L/14)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
Action RecognitiononAVA v2.2
mAP· uses extra data· 2023-11-06
33.5
best: 45.1 (LART (Hiera-H, K700 PT+FT))
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149

Computer Vision3 results

VideoonKinetics-400
Acc@1· 2023-11-06
82.2
best: 93.6 (OmniVec2)
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
VideoonKinetics-400
Acc@5· 2023-11-06
95.3
best: 98.9 (TubeViT-H (ImageNet-1k))
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149
VideoonKinetics-400
Parameters (M)· 2023-11-06
87
best: 632 (TubeViT-H (ImageNet-1k))
Asymmetric Masked Distillation for Pre-Training Small Foundation Models arXiv:2311.03149