• Home
  • Search
  • Semi-supervised Person Re-identification by Attribute Similarity Guidance
  • Cite Icon2
  • https://doi.org/10.1109/icpr48806.2021.9412561Copy DOI Icon

Semi-supervised Person Re-identification by Attribute Similarity Guidance

  • Jan 10, 2021
  • Peixian Hong +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Although supervised person re-identification (RE-ID) has achieved great progress with deep learning, it requires time-consuming annotation of a large number of pedestrian identities. To reduce labeling cost, we attempt to reduce cross-camera identity annotations and exploit pedestrian attribute annotations as auxiliary information instead. The pedestrian attributes, such as outfit styles, contain coarse semantic knowledge. Although pedestrian attributes are annotated without exhaustive searching in a camera network, which is much easier than cross-camera identity annotation, ambiguity exists in attributes when different persons have similar outfits. To solve this problem, we propose an Attribute Similarity Guidance loss (ASG) to guide appearance feature learning for RE-ID by selective attribute similarity preservation to avoid the impact of such ambiguity. Finally, we develop an attribute-guided self training framework to jointly utilize attribute annotations, unlabeled data and limited labeled data for semi-supervised learning. Extensive experiments on Market-1501 and DukeMTMC-ReID show the superiority of our method for semi-supervised RE-ID.

Similar Papers
  • Video Transcripts

Semi-supervised Person Re-identification by Attribute Similarity Guidance

  • Dec 29, 2020
  • Underline Science Inc.
  • Peixian Hong
  • Conference Article
  • Citations322

Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios

  • Nov 01, 2015
  • Dangwei Li +2
  • Research Article
  • Citations4

Attribute-Guided Global and Part-Level Identity Network for Person Re-Identification

  • May 12, 2022
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Shaoming Pan +2
  • Research Article
  • Citations1

Person Re-identification Based on Attribute Hierarchy Recognition

  • Sep 10, 2019
  • 电子与信息学报
  • Hongchang Chen +3
  • Book Chapter
  • Citations5

Research on Pedestrian Attribute Recognition Based on Semantic Segmentation in Natural Scene

  • Jan 01, 2019
  • Xin Feng +3
  • PDF
  • Research Article
  • Citations36

Attention Based CNN-ConvLSTM for Pedestrian Attribute Recognition.

  • Feb 03, 2020
  • Sensors (Basel, Switzerland)
  • Yang Li +3
  • Book Chapter

Cross Domain Person ReID Based on Symmetric Coding and Pedestrian Similarity

  • Jan 01, 2022
  • Xingyu Gao +3
  • Conference Article
  • Citations7

Unsupervised Domain-Adaptive Person Re-Identification Based on Attributes

  • Sep 01, 2019
  • Xiangping Zhu +2
  • Research Article
  • Citations10

A novel self-boosting dual-branch model for pedestrian attribute recognition

  • Apr 14, 2023
  • Signal Processing: Image Communication
  • Yilu Cao +5
  • Research Article
  • Citations2

Pedestrian attribute recognition based on dual self-attention mechanism

  • Jan 01, 2023
  • Computer Science and Information Systems
  • Zhongkui Fan +1
  • Conference Article
  • Citations23

Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations

  • Jan 01, 2018
  • Yiqiang Chen +4
  • Conference Article
  • Citations3

Triplet CNN and pedestrian attribute recognition for improved person re-identification

  • Aug 01, 2017
  • Yiqiang Chen +4
  • Conference Article
  • Citations61

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

  • Jan 01, 2017
  • Yang Zhou +5
  • Conference Article
  • Citations2

Pedestrian attribute recognition in elevator

  • Jun 24, 2022
  • Pengyuan Zhang +1
  • Conference Article
  • Citations173

Attribute Recognition by Joint Recurrent Learning of Context and Correlation

  • Oct 01, 2017
  • Jingya Wang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.