ViViT-L/16x2

Reported on 3 benchmarks across 1 task · 1 paper

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

Computer Vision3 results

VideoonMiT
Top 5 Accuracy· uses extra data· 2021-03-29
64.9
best: 78.2 (UMT-L (ViT-L/16))
ViViT: A Video Vision Transformer arXiv:2103.15691
VideoonKinetics-600
Top-1 Accuracy· 2021-03-29
84.3
best: 91.9 (InternVideo2-6B)
ViViT: A Video Vision Transformer arXiv:2103.15691
VideoonKinetics-600
Top-5 Accuracy· 2021-03-29
95.6
best: 98.9 (TubeVit-H)
ViViT: A Video Vision Transformer arXiv:2103.15691