StructVit-B-4-1

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Robots3 results

Activity RecognitiononDiving-48
Accuracy· 2024-04-05
88.3
best: 94.9 (LVMAE)
Learning Correlation Structures for Vision Transformers arXiv:2404.03924
Activity RecognitiononSomething-Something V1
Top 1 Accuracy· 2024-04-05
61.3
best: 70 (InternVideo)
Learning Correlation Structures for Vision Transformers arXiv:2404.03924
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2024-04-05
71.5
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Learning Correlation Structures for Vision Transformers arXiv:2404.03924

Time Series3 results

Action RecognitiononDiving-48
Accuracy· 2024-04-05
88.3
best: 94.9 (LVMAE)
Learning Correlation Structures for Vision Transformers arXiv:2404.03924
Action RecognitiononSomething-Something V1
Top 1 Accuracy· 2024-04-05
61.3
best: 70 (InternVideo)
Learning Correlation Structures for Vision Transformers arXiv:2404.03924
Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2024-04-05
71.5
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Learning Correlation Structures for Vision Transformers arXiv:2404.03924