S3D-G (ImageNet pretrained)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Robots2 results

Activity RecognitiononSomething-Something V1
Top 1 Accuracy· uses extra data· 2017-12-13
48.2
best: 70 (InternVideo)
SOTA
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification arXiv:1712.04851
Activity RecognitiononSomething-Something V1
Top 5 Accuracy· uses extra data· 2017-12-13
78.7
best: 91.9 (VideoMAE V2-g)
SOTA
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification arXiv:1712.04851

Time Series2 results

Action RecognitiononSomething-Something V1
Top 1 Accuracy· uses extra data· 2017-12-13
48.2
best: 70 (InternVideo)
SOTA
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification arXiv:1712.04851
Action RecognitiononSomething-Something V1
Top 5 Accuracy· uses extra data· 2017-12-13
78.7
best: 91.9 (VideoMAE V2-g)
SOTA
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification arXiv:1712.04851