UniFormerV2-L (ViT-L, 336)

Reported on 3 benchmarks across 1 task

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

Computer Vision3 results

VideoonKinetics-400
Acc@1· uses extra data
90
best: 93.6 (OmniVec2)
VideoonKinetics-400
Acc@5· uses extra data
98.4
best: 98.9 (TubeViT-H (ImageNet-1k))
VideoonKinetics-400
Parameters (M)· uses extra data
354
best: 632 (TubeViT-H (ImageNet-1k))