LGD-3D RGB (ResNet-101)

Reported on 2 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 Vision2 results

VideoonKinetics-400
Acc@1· 2019-06-13
79.4
best: 93.6 (OmniVec2)
Learning Spatio-Temporal Representation with Local and Global Diffusion arXiv:1906.05571
VideoonKinetics-400
Acc@5· 2019-06-13
94.4
best: 98.9 (TubeViT-H (ImageNet-1k))
Learning Spatio-Temporal Representation with Local and Global Diffusion arXiv:1906.05571