COMPOSER

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 RecognitiononCollective Activity
Accuracy· 2021-12-11
96.2
best: 96.5 (Tamura et al.)
SOTA
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality arXiv:2112.05892
Activity RecognitiononVolleyball
Accuracy· 2021-12-11
94.69
best: 96 (Tamura et al.)
SOTA
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality arXiv:2112.05892