Side4Video (EVA ViT-E/14)

Reported on 4 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.

Robots2 results

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-11-27
75.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning arXiv:2311.15769
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-11-27
94
best: 96.3 (DejaVid)
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning arXiv:2311.15769

Time Series2 results

Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-11-27
75.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning arXiv:2311.15769
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-11-27
94
best: 96.3 (DejaVid)
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning arXiv:2311.15769