TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Harmonious Attention Network for Person Re-Identification

Harmonious Attention Network for Person Re-Identification

Wei Li, Xiatian Zhu, Shaogang Gong

2018-02-22CVPR 2018 6Person Re-Identification
PaperPDFCode

Abstract

Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HA-CNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.

Results

TaskDatasetMetricValueModel
Person Re-IdentificationCUHK03 detectedMAP38.6HA-CNN (CVPR'18)
Person Re-IdentificationCUHK03 detectedRank-141.7HA-CNN (CVPR'18)
Person Re-IdentificationCUHK03 labeledMAP41HA-CNN (CVPR'18)
Person Re-IdentificationCUHK03 labeledRank-144.4HA-CNN (CVPR'18)
Person Re-IdentificationCUHK03MAP38.6HA-CNN
Person Re-IdentificationCUHK03Rank-141.7HA-CNN

Related Papers

Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning2025-07-17WhoFi: Deep Person Re-Identification via Wi-Fi Channel Signal Encoding2025-07-17Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID2025-07-15Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction2025-07-15KeyRe-ID: Keypoint-Guided Person Re-Identification using Part-Aware Representation in Videos2025-07-10CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion2025-07-04Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence2025-07-02DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding2025-06-16