Boutaleb et al.

Reported on 8 benchmarks across 8 tasks

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

Computer Vision3 results

VideoonFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17
Temporal Action LocalizationonFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17
Action LocalizationonFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17

Robots2 results

Activity RecognitiononFirst-Person Hand Action Benchmark
1:1 Accuracy
97.91
Activity RecognitiononFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17
best: 97.91

Time Series2 results

Action DetectiononFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17
Action RecognitiononFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17

Methodology1 result

Zero-Shot LearningonFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17

Natural Language Processing1 result

3D Action RecognitiononFirst-Person Hand Action Benchmark
1:1 Accuracy
96.17