Devil's In The Details: Aligning Visual Clues For Conditional Embedding In Person Re-identification

Abstract

Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-pointand similar clothing still bring great challenges. Besides overall visual features, matching and comparing detailed information is also essential for tackling these challenges. This paper proposes two key recognition patterns to better utilize the detail information of pedestrian images, that most of the existing methods are unable to satisfy. Firstly, Visual Clue Alignment requires the model to select and align decisive regions pairs from two images for pair-wise comparison, while existing methods only align regions with predefined rules like high feature similarity or same semantic labels. Secondly, the Conditional Feature Embedding requires the overall feature of a query image to be dynamically adjusted based on the gallery image it matches, while most of the existing methods ignore the reference images. By introducing novel techniques including correspondence attentio

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2020devil

Related papers

• Bridging The Gap: Multi-level Cross-modality Joint Alignment For Visible-infrared Person Re-identification (2023)11.29
• Deep Co-attention Based Comparators For Relative Representation Learning In Person Re-identification (2018)13.34
• Pose Invariant Embedding For Deep Person Re-identification (2017)19.34
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Learning Context-aware Embedding For Person Search (2021)0.00
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71
• Implicit Discriminative Knowledge Learning For Visible-infrared Person Re-identification (2024)16.19
• Dynamic Dual-attentive Aggregation Learning For Visible-infrared Person Re-identification (2020)19.67