X-CLIP(ViT-L/14, CLIP)

Reported on 4 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 Vision4 results

VideoonKinetics-400
Acc@1· 2022-08-04
87.7
best: 93.6 (OmniVec2)
Expanding Language-Image Pretrained Models for General Video Recognition arXiv:2208.02816
VideoonKinetics-400
Acc@5· 2022-08-04
97.4
best: 98.9 (TubeViT-H (ImageNet-1k))
Expanding Language-Image Pretrained Models for General Video Recognition arXiv:2208.02816
VideoonKinetics-600
Top-1 Accuracy· uses extra data· 2022-08-04
88.3
best: 91.9 (InternVideo2-6B)
Expanding Language-Image Pretrained Models for General Video Recognition arXiv:2208.02816
VideoonKinetics-600
Top-5 Accuracy· uses extra data· 2022-08-04
97.7
best: 98.9 (TubeVit-H)
Expanding Language-Image Pretrained Models for General Video Recognition arXiv:2208.02816