判别式
计算机科学
人工智能
生成模型
步态
模式识别(心理学)
代表(政治)
生成语法
生物识别
机器学习
特征学习
隐马尔可夫模型
计算机视觉
期限(时间)
特征提取
特征(语言学)
作者
Xiong, Haijun,Feng Bin,Wang Bang,Wang Xing-gang,Liu, Wenyu
标识
DOI:10.48550/arxiv.2511.06245
摘要
Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models remains largely underexplored. In this paper, we introduce \textbf{CoD$^2$}, a novel framework that combines the data distribution modeling capabilities of diffusion models with the semantic representation learning strengths of discriminative models to extract robust gait features. We propose a Multi-level Conditional Control strategy that incorporates both high-level identity-aware semantic conditions and low-level visual details. Specifically, the high-level condition, extracted by the discriminative extractor, guides the generation of identity-consistent gait sequences, whereas low-level visual details, such as appearance and motion, are preserved to enhance consistency. Furthermore, the generated sequences facilitate the discriminative extractor's learning, enabling it to capture more comprehensive high-level semantic features. Extensive experiments on four datasets (SUSTech1K, CCPG, GREW, and Gait3D) demonstrate that CoD$^2$ achieves state-of-the-art performance and can be seamlessly integrated with existing discriminative methods, yielding consistent improvements.
科研通智能强力驱动
Strongly Powered by AbleSci AI