الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Group Activity Recognition On Volleyball

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy	Paper Title	Repository
Tamura et al.	96.0	Hunting Group Clues with Transformers for Social Group Activity Recognition	-
DIN (VGG16)	93.6	Spatio-Temporal Dynamic Inference Network for Group Activity Recognition
PoseC3D (Pose-Only)	91.3	Revisiting Skeleton-based Action Recognition
H-LSTCM	88.4	Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition	-
COMPOSER	94.69	COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
CHASE(CTR-GCN)	92.89	CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
Zappardino et al.	91.0	Learning Group Activities from Skeletons without Individual Action Labels	-
Zappardino et al. (SSAL)	89.4	Learning Group Activities from Skeletons without Individual Action Labels	-
Shu et al.	83.6	CERN: Confidence-Energy Recurrent Network for Group Activity Recognition	-
D. Xu et al.	93.49	Group Activity Recognition by Using Effective Multiple Modality Relation Representation With Temporal-Spatial Attention	-
POGARS	93.2	Pose is all you need: The pose only group activity recognition system (POGARS)	-
Joint learning (5-fusion)	93.3	Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping

0 of 12 row(s) selected.