TRN-Multiscale

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

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

Computer Vision2 results

VideoonMiT
Top 1 Accuracy· 2018-01-09
28.27
best: 53.1 (OmniVec2)
SOTA
Moments in Time Dataset: one million videos for event understanding arXiv:1801.03150
VideoonMiT
Top 5 Accuracy· 2018-01-09
53.87
best: 78.2 (UMT-L (ViT-L/16))
SOTA
Moments in Time Dataset: one million videos for event understanding arXiv:1801.03150

Robots2 results

Activity RecognitiononMoments in Time Dataset
Top-1 (%)· 2018-01-09
28.27
best: 34.27 (AssembleNet)
Moments in Time Dataset: one million videos for event understanding arXiv:1801.03150
Activity RecognitiononMoments in Time Dataset
Top-5 (%)· 2018-01-09
53.87
best: 62.71 (AssembleNet)
Moments in Time Dataset: one million videos for event understanding arXiv:1801.03150