A Survey on 3D Skeleton Based Person Re-Identification: Approaches, Designs, Challenges, and Future Directions
CoRR(2024)
摘要
Person re-identification via 3D skeletons is an important emerging research
area that triggers great interest in the pattern recognition community. With
distinctive advantages for many application scenarios, a great diversity of 3D
skeleton based person re-identification (SRID) methods have been proposed in
recent years, effectively addressing prominent problems in skeleton modeling
and feature learning. Despite recent advances, to the best of our knowledge,
little effort has been made to comprehensively summarize these studies and
their challenges. In this paper, we attempt to fill this gap by providing a
systematic survey on current SRID approaches, model designs, challenges, and
future directions. Specifically, we first formulate the SRID problem, and
propose a taxonomy of SRID research with a summary of benchmark datasets,
commonly-used model architectures, and an analytical review of different
methods' characteristics. Then, we elaborate on the design principles of SRID
models from multiple aspects to offer key insights for model improvement.
Finally, we identify critical challenges confronting current studies and
discuss several promising directions for future research of SRID.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要