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/ST-Adapter (ViT-L, CLIP)

ST-Adapter (ViT-L, CLIP)

Reported on 8 benchmarks across 3 tasks · 1 paper · 2 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
GFLOPs· uses extra data· 2022-06-27
8248
best: 13321 (InternVideo2-6B)
SOTA
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2022-06-27
72.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2022-06-27
93.9
best: 96.3 (DejaVid)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559

Time Series3 results

Action RecognitiononSomething-Something V2
GFLOPs· uses extra data· 2022-06-27
8248
best: 13321 (InternVideo2-6B)
SOTA
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2022-06-27
72.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2022-06-27
93.9
best: 96.3 (DejaVid)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559

Computer Vision2 results

VideoonKinetics-400
Acc@1· 2022-06-27
87.2
best: 93.6 (OmniVec2)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559
VideoonKinetics-400
Acc@5· 2022-06-27
97.6
best: 98.9 (TubeViT-H (ImageNet-1k))
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning arXiv:2206.13559