Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification

By Mang Ye, Xiangyuan Lan, Zheng Wang, Pong Chi Yuen. IEEE Transactions on Information Forensics and Security, 2020

294 citations recorded by the source corpus.

Visible thermal person re-identification (VT-REID) is a task of matching person images captured by thermal and visible cameras, which is an extremely important issue in night-time surveillance applications. Existing cross-modality recognition works mainly focus on learning sharable feature representations to handle the cross-modality discrepancies. However, apart from the cross-modality discrepancy caused by different camera spectrums, VT-REID also suffers from large cross-modality and intra-modality variations caused by different camera environments and human poses, and so on. In this paper, we propose a dual-path network with a novel bi-directional dual-constrained top-ranking (BDTR) loss to learn discriminative feature representations. It is featured in two aspects: 1) end-to-end learning without extra metric learning step and 2) the dual-constraint simultaneously handles the cross-modality and intra-modality variations to ensure the feature discriminability. Meanwhile, a bi-directional center-constrained top-ranking (eBDTR) is proposed to incorporate the previous two constraints into a single formula, which preserves the properties to handle both cross-modality and intra-modality variations. The extensive experiments on two cross-modality re-ID datasets demonstrate the superiority of the proposed method compared to the state-of-the-arts.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/27069f8d6ba847bd53d6fe1446df7a1403ffc68a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “A two stream network is introduced in [146], [190] to model the modalitysharable and -specific information, addressing the intra- and cross-modality variations simultaneously.”
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, methodology): “Eventually, the coexistence of intra- and crossmodality discrepancies leads to a critical situation where the intra-class distance is larger than the inter-class distance in VI-ReID [38, 31].”
Channel Augmented Joint Learning for Visible-Infrared Recognition (2021, methodology): “Following the settings in [42, 49], rank-k matching accuracy and mean Average Precision (mAP) are used as evaluation metrics.”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “The comparison includes eBDTR [58], D(2)RL [49], MAC [56], MSR [9], AlignGAN [44] and Xmodal [19].”