HyperAIHyperAI초신경
홈뉴스연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Group Activity Recognition On Volleyball

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Accuracy
Paper TitleRepository
Tamura et al.96.0Hunting Group Clues with Transformers for Social Group Activity Recognition-
DIN (VGG16)93.6Spatio-Temporal Dynamic Inference Network for Group Activity Recognition
PoseC3D (Pose-Only)91.3Revisiting Skeleton-based Action Recognition
H-LSTCM88.4Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition-
COMPOSER94.69COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
CHASE(CTR-GCN)92.89CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
Zappardino et al.91.0Learning Group Activities from Skeletons without Individual Action Labels
Zappardino et al. (SSAL)89.4Learning Group Activities from Skeletons without Individual Action Labels
Shu et al.83.6CERN: Confidence-Energy Recurrent Network for Group Activity Recognition-
D. Xu et al.93.49Group Activity Recognition by Using Effective Multiple Modality Relation Representation With Temporal-Spatial Attention-
POGARS93.2Pose is all you need: The pose only group activity recognition system (POGARS)-
Joint learning (5-fusion)93.3Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping-
0 of 12 row(s) selected.