X3D-L

Reported on 3 benchmarks across 1 task · 2 papers

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· 2021-05-31
69.29
best: 93.6 (OmniVec2)
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos arXiv:2106.00050
VideoonKinetics-400
Parameters (M)· 2021-05-31
6.15
best: 632 (TubeViT-H (ImageNet-1k))
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos arXiv:2106.00050
VideoonKinetics-400
Acc@1· 2020-04-09
77.5
best: 93.6 (OmniVec2)
X3D: Expanding Architectures for Efficient Video Recognition arXiv:2004.04730
VideoonKinetics-400
Acc@5· 2020-04-09
92.9
best: 98.9 (TubeViT-H (ImageNet-1k))
X3D: Expanding Architectures for Efficient Video Recognition arXiv:2004.04730