• Home
  • Search
  • Local Heterogeneous Features for Person Re-Identification in Harsh Environments
  • Cite Icon7
  • https://doi.org/10.1109/access.2020.2991838Copy DOI Icon

Local Heterogeneous Features for Person Re-Identification in Harsh Environments

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Local features could learn semantic information for pedestrian images and they are very important for person re-identification (Re-ID) in harsh environments. However, most approaches only optimize one kind of local feature, which results in incomplete local features. In this paper, we propose Local Heterogeneous Features (LHF) to extract discriminative local features from three aspects. To this end, we utilize three kinds of losses to learn three kinds of local features, i.e., local discriminative features, local relative features, local compact features. As for local discriminative features, we split the attention maps into three horizontal sub-regions and perform the classification operation. Then, we divide the attention maps into two horizontal sub-regions, and we synchronously apply the triplet loss and center loss to learn local relative features and local compact features. Finally, we utilize local discriminative features to represent pedestrian. We evaluate LHF on public person Re-ID datasets and prove LHF is meaningful for local feature learning.

Loading PDF

Similar Papers
  • Conference Article
  • Citations5

Pedestrian Detection with Local Feature Assistant

  • May 01, 2007
  • Y.W Xu +2
  • Conference Article
  • Citations59

Hierarchical Ensemble of Global and Local Classifiers for Face Recognition

  • Jan 01, 2007
  • Yu Su +3
  • Research Article
  • Citations26

Learning Semantic-Aware Local Features for Long Term Visual Localization

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Bin Fan +7
  • Research Article

Revamping Image-Recipe Cross-Modal Retrieval with Dual Cross Attention Encoders

  • Oct 11, 2024
  • Mathematics
  • Wenhao Liu +5
  • Conference Article
  • Citations2

Learning Multiple Granularity Features for Unsupervised Person Re-Identification

  • Jul 18, 2022
  • Shuai Wang +2
  • Conference Article
  • Citations3

Logo Spotting on Document Images using Local Features

  • Dec 03, 2015
  • Viet Phuong Le +2
  • Conference Article
  • Citations1

On visual vocabulary size in SVM classification

  • Mar 01, 2016
  • Weixue Liu +3
  • Research Article
  • Citations8

Intelligent Fault Diagnosis Method for Shearer Rocker Gear Based on Swin Transformer and Multiscale Convolution Parallel Integration

  • Jan 01, 2025
  • IEEE Transactions on Instrumentation and Measurement
  • Xiaochun Sun +5
  • PDF
  • Research Article
  • Citations22

Concave-convex local binary features for automatic target recognition in infrared imagery

  • Apr 21, 2014
  • EURASIP Journal on Image and Video Processing
  • Junding Sun +3
  • Preprint Article

SEFormer:A new method for Medical Image Segmentation

  • Jun 09, 2025
  • Research Square
  • Chen Ge +4
  • Research Article
  • Citations36

Person re-identification with part prediction alignment

  • Feb 03, 2021
  • Computer Vision and Image Understanding
  • Zhiyong Li +3
  • Research Article
  • Citations2

SADGFeat: Learning local features with layer spatial attention and domain generalization

  • Apr 21, 2024
  • Image and Vision Computing
  • Wenjing Bai +5
  • Conference Article
  • Citations4

Scheming an efficient facial recognition system using global and random local feature extraction methods

  • Oct 01, 2017
  • Omid Sharifi +2
  • PDF
  • Research Article
  • Citations1

Fine-Grained Image Retrieval via Object Localization

  • May 11, 2023
  • Electronics
  • Rong Wang +2
  • Research Article
  • Citations3

Local information interaction enhancement network for person re-identification

  • Jun 09, 2022
  • Journal of Electronic Imaging
  • Haishun Du +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.