GaitTAKE: Gait Recognition by Temporal Attention and Keypoint-guided Embedding
원문 초록
Gait recognition, which refers to the recognition or identification of a person based on their body shape and walking styles, derived from video data captured from a distance, is widely used in crime prevention, forensic identification, and social security. However, to the best of our knowledge, most of the existing methods use appearance, posture and temporal feautures without considering a learned temporal attention mechanism for global and local information fusion. In this paper, we propose a novel gait recognition framework, called Temporal Attention and Keypoint-guided Embedding (GaitTAKE), which effectively fuses temporal-attention-based global and local appearance feature and temporal aggregated human pose feature. Experimental results show that our proposed method achieves a new SOTA in gait recognition with rank-1 accuracy of 98.0% (normal), 97.5% (bag) and 92.2% (coat) on the CASIA-B gait dataset; 90.4% accuracy on the OU-MVLP gait dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
On Denoising Walking Videos for Gait Recognition
H-MoRe: Learning Human-centric Motion Representation for Action Analysis
Open-Set Gait Recognition from Sparse mmWave Radar Point Clouds
UNB StepUP: A footStep database for gait analysis and recognition using Underfoot Pressure
MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation
GLGait: A Global-Local Temporal Receptive Field Network for Gait Recognition in the Wild
토론
이 논문과 연결된 포럼 글이 아직 없습니다.