Graph-based Person Signature for Person Re-Identifications

  title={Graph-based Person Signature for Person Re-Identifications},
  author={Binh X. Nguyen and Binh Nguyen and Tuong KL. Do and Erman Tjiputra and Quang D. Tran and Anh Gia-Tuan Nguyen},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Binh X. Nguyen, Binh Nguyen, A. Nguyen
  • Published 14 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
The task of person re-identification (ReID) is to match images of the same person over multiple non-overlapping camera views. Due to the variations in visual factors, previous works have investigated how the person identity, body parts, and attributes benefit the person ReID problem. However, the correlations between attributes, body parts, and within each attribute are not fully utilized. In this paper, we propose a new method to effectively aggregate detailed person descriptions (attributes… 

Figures and Tables from this paper

Relation Preserving Triplet Mining for Stabilizing the Triplet Loss in Vehicle Re-identification
Relation Preserving Triplet Mining (RPTM) is introduced, a feature matching guided triplet mining scheme, that ensures triplets will respect the natural sub-groupings within an object ID.
Global-Local Attention for Emotion Recognition
A new deep network to effectively recognize human emotions using a novel global-local attention mechanism, designed to extract features from both facial and context regions independently, then learn them together using the attention module.
Coarse-to-Fine Reasoning for Visual Question Answering
This paper presents a new reasoning framework to fill the gap between visual features and semantic clues in the VQA task, and first extracts the features and predicates from the image and question and proposes a new Reasoning framework to effectively jointly learn these features andpredicates in a coarse-tofine manner.
Attention Gate in Traffic Forecasting
This paper applies the attention mechanism on U-Net based model, especially an attention gate on the skip-connection between contraction path and expansion path to reduce the effect of non-traffic region features and focus more on crucial region features.
Fine-Grained Visual Classification using Self Assessment Classifier
Extracting discriminative features plays a crucial role in the fine-grained visual classification task. Most of the existing methods focus on developing attention or augmentation mechanisms to achieve


Relation Network for Person Re-identification
This work proposes a new relation network for person reID that considers relations between individual body parts and the rest of them, and makes a single part-level feature incorporate partial information of other body parts as well, supporting it to be more discriminative.
Part-Based Attribute-Aware Network for Person Re-Identification
A multi-branch model, namely part-based attribute-aware network (PAAN) is proposed, to leverage both person reID and attribute performance, which not only utilizes ID label visible to the whole image but also utilizes attribute information.
Person Re-identification by Deep Learning Attribute-Complementary Information
This work trains an attribute classifier on separate data and includes its responses into the training process of the person re-id model which is based on convolutional neural networks (CNNs), allowing it to learn a person representation which contains information complementary to that contained within the attributes.
Horizontal Pyramid Matching for Person Re-identification
A simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be still identified even even some key parts are missing.
Attributes-aided Part Detection and Refinement for Person Re-identification
Person Re-identification with Deep Similarity-Guided Graph Neural Network
This paper proposes a novel deep learning framework, named Similarity-Guided Graph Neural Network (SGGNN), which learns the edge weights with rich labels of gallery instance pairs directly, which provides relation fusion more precise information.
Improving Person Re-identification by Attribute and Identity Learning
Semantics-Aligned Representation Learning for Person Re-identification
A framework that drives the reID network to learn semantics-aligned feature representation through delicate supervision designs is proposed and achieves the state-of-the-art performances on the benchmark datasets CUHK03, Market1501, MSMT17, and the partial person reID dataset Partial REID.
Improving person re-identification by multi-task learning
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
A novel coarse-to-fine pyramid model is proposed to relax the need of bounding boxes and learn discriminative identity representation, which not only incorporates local and global information, but also integrates the gradual cues between them.