Deep Learning for Human Parsing: A Survey
Xiaomei Zhang, Xiangyu Zhu, Ming Tang, Zhen Lei · ACM Computing Surveys · 2025
Human parsing has recently attracted increasing attention due to its wide applications in many areas, such as surveillance analysis, human-robot interaction, and person search. Many methods now focus on developing human parsing algorithms based on deep learning. To stimulate future research, we present the comprehensive review of recent advances in this field. This survey analyzes state-of-the-art methods, covering a broad spectrum of pioneering works for human parsing. This work introduces five insightful categories: (1) structure-driven architectures that exploit the relationship of different parts and the inherent hierarchical structure of a human body, (2) graph-based networks model part-relation reasoning to achieve an effective human body analysis, (3) context-aware networks utilize multiple types of contextual information to classify pixels accurately, (4) LSTM-based methods combine short-distance and long-distance spatial dependencies to leverage local and global contexts, and (5) combined auxiliary information approaches use related tasks to improve the performance. We also discuss the advantages and disadvantages of each category and the relationships between different methods. Additionally, we present quantitative performance comparisons of the reviewed methods on benchmark datasets. Finally, we introduce some common applications and suggest new directions for future study.