Effective Action Recognition with Embedded Key Point Shifts
원문 초록
Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require costly key point annotation. In this paper, we propose a novel temporal feature extraction module, named Key Point Shifts Embedding Module ($KPSEM$), to adaptively extract channel-wise key point shifts across video frames without key point annotation for temporal feature extraction. Key points are adaptively extracted as feature points with maximum feature values at split regions, while key point shifts are the spatial displacements of corresponding key points. The key point shifts are encoded as the overall temporal features via linear embedding layers in a multi-set manner. Our method achieves competitive performance through embedding key point shifts with trivial computational cost, achieving the state-of-the-art performance of 82.05% on Mini-Kinetics and competitive performance on UCF101, Something-Something-v1, and HMDB51 datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
Action Recognition in Real-World Ambient Assisted Living Environment
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
토론
이 논문과 연결된 포럼 글이 아직 없습니다.