Min et al.

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Robots2 results

Activity RecognitiononEGTEA
Average Accuracy· 2020-11-08
69.58
best: 81.75 (LaViLa (Finetuned, TimeSformer-L))
SOTA
Integrating Human Gaze into Attention for Egocentric Activity Recognition arXiv:2011.03920
Activity RecognitiononEGTEA
Mean class accuracy· 2020-11-08
62.84
best: 76 (LaViLa (Finetuned, TimeSformer-L))
SOTA
Integrating Human Gaze into Attention for Egocentric Activity Recognition arXiv:2011.03920