Abstract In this paper, we propose an end-to-end deep correspondence structure learning (DCSL) approach to address the cross-camera person-matching problem in the person re-identification task. The proposed DCSL approach captures the intrinsic structural information on persons by learning a semanticsaware image representation based on convolutional neural networks, which adaptively learns discriminative features for person identification. Furthermore, the proposed DCSL approach seeks to adaptively learn a hierarchical data-driven feature matching function which outputs the matching correspondence results between the learned semantics-aware image representations for a person pair. Finally, we set up a unified end-toend deep learning scheme to jointly optimize the processes of semantics-aware image representation learning and cross-person correspondence structure learning, leading to more reliable and robust person re-identification results in complicated scenarios. Experimental results on several benchmark datasets demonstrate the effectiveness of our approach against the state-of-the-art approaches.