STM + TRNMultiscale

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Robots1 result

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2019-09-11
47.73
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos arXiv:1909.05165

Time Series1 result

Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2019-09-11
47.73
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos arXiv:1909.05165