GTT (VGG19)

Reported on 2 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.

Robots1 result

Activity RecognitiononVolleyball
Accuracy· 2016-11-28
82.6
best: 96 (Tamura et al.)
SOTA
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition arXiv:1611.09078

Time Series1 result

Action RecognitiononVolleyball
Accuracy· 2016-11-28
82.6
best: 91.3 (PoseC3D (Pose Only))
SOTA
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition arXiv:1611.09078