TAdaConvNeXtV2-B

Reported on 5 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.

Robots2 results

Activity RecognitiononSomething-Something V1
Top 1 Accuracy· uses extra data· 2023-08-10
60.7
best: 70 (InternVideo)
Temporally-Adaptive Models for Efficient Video Understanding arXiv:2308.05787
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2023-08-10
71.1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Temporally-Adaptive Models for Efficient Video Understanding arXiv:2308.05787

Time Series2 results

Action RecognitiononSomething-Something V1
Top 1 Accuracy· uses extra data· 2023-08-10
60.7
best: 70 (InternVideo)
Temporally-Adaptive Models for Efficient Video Understanding arXiv:2308.05787
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2023-08-10
71.1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Temporally-Adaptive Models for Efficient Video Understanding arXiv:2308.05787

Computer Vision1 result

VideoonKinetics-400
Acc@1· 2023-08-10
86.4
best: 93.6 (OmniVec2)
Temporally-Adaptive Models for Efficient Video Understanding arXiv:2308.05787