1,041 Hits in 6.6 sec

Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification

Xiujun Shu, Ge Li, Xiao Wang, Weijian Ruan, Qi Tian
2021 IEEE Signal Processing Letters  
The key to this task is to exploit cloth-irrelevant cues. This paper proposes a semantic-guided pixel sampling approach for the cloth-changing person re-ID task.  ...  Cloth-changing person re-identification (re-ID) is a new rising research topic that aims at retrieving pedestrians whose clothes are changed.  ...  CONCLUSION In this paper, we propose a semantic-guided pixel sampling approach for cloth-changing person re-identification.  ... 
doi:10.1109/lsp.2021.3091924 fatcat:gv3x3gy63ffohmttqbwwjlccne

Person image generation with semantic attention network for person re-identification [article]

Meichen Liu, Kejun Wang, Juihang Ji, Shuzhi Sam Ge
2020 arXiv   pre-print
Pose variation is one of the key factors which prevents the network from learning a robust person re-identification (Re-ID) model.  ...  Furthermore, we conduct extensive evaluations by using person re-identification (Re-ID) systems trained with the pose-transferred person based augmented data.  ...  Acknowledgments The work is supported by National Natural Science Foundation of China (61573114) and Fundamental Research Funds for the Central Universities (HEU-CF160415).  ... 
arXiv:2008.07884v1 fatcat:3onnpv5xfvhulaq3hyb3ajzax4

A Semantic-aware Attention and Visual Shielding Network for Cloth-changing Person Re-identification [article]

Zan Gao, Hongwei Wei, Weili Guan, Jie Nie, Meng Wang, Shenyong Chen
2022 arXiv   pre-print
To solve these issues, in this work, a novel semantic-aware attention and visual shielding network for cloth-changing person ReID (abbreviated as SAVS) is proposed where the key idea is to shield clues  ...  Cloth-changing person reidentification (ReID) is a newly emerging research topic that aims to retrieve pedestrians whose clothes are changed.  ...  Index Terms-Cloth-changing Person Re-identification; Visual Clothes Shielding; Human Semantic Attention; Semantic-aware; I.  ... 
arXiv:2207.08387v1 fatcat:z2vbvna4bfdrbmfjh6vzkap2a4

Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification [article]

Fufu Yu, Xinyang Jiang, Yifei Gong, Shizhen Zhao, Xiaowei Guo, Wei-Shi Zheng, Feng Zheng, Xing Sun
2020 arXiv   pre-print
Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-pointand similar clothing still bring great challenges.  ...  high feature similarity or same semantic labels.  ...  body and latent parts for person re-identification.  ... 
arXiv:2009.05250v2 fatcat:7nj52wpupzcb5bt5vwst27l3ai

Semantic-Guided Shared Feature Alignment for Occluded Person Re-IDentification

Xuena Ren, Dongming Zhang, Xiuguo Bao
2020 Asian Conference on Machine Learning  
regions for Re-ID.  ...  Occluded Person Re-ID is a challenging task under resolved.  ...  Introduction Person Re-IDentification (Re-ID) aims at retrieving the same person across different cameras with various backgrounds, poses, and positions.  ... 
dblp:conf/acml/RenZB20 fatcat:kmsen5e5a5eb3b66bqsw6bkgwi

Visual Appearance Based Person Retrieval in Unconstrained Environment Videos

Hiren Galiyawala, Mehul S. Raval, Shivansh Dave
2019 Image and Vision Computing  
The algorithm uses fine-tuned Mask R-CNN and DenseNet-169 for person detection and attribute classification respectively.  ...  This paper proposes person retrieval from surveillance video using height, torso cloth type, torso cloth color and gender.  ...  The authors acknowledge the support of NVIDIA Corporation for a donation of the Quadro K5200 GPU used for this research.  ... 
doi:10.1016/j.imavis.2019.10.002 fatcat:7btrdc4cfvf3nkjinm3fq3dqfa

Unsupervised Person Image Generation with Semantic Parsing Transformation [article]

Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei
2019 arXiv   pre-print
Our method is generalizable to other semantic-aware person image generation tasks, eg, clothing texture transfer and controlled image manipulation.  ...  In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation.  ...  This topic is of great importance in fashion and art domains for a wide range of applications from image / video editing, person re-identification to movie production.  ... 
arXiv:1904.03379v2 fatcat:gvw4h2psvrbsthvimimninsqeq

Parts Semantic Segmentation Aware Representation Learning for Person Re-Identification

Hua Gao, Shengyong Chen, Zhaosheng Zhang
2019 Applied Sciences  
Since three body parts are well aligned, the approach significantly improves person re-identification.  ...  Person re-identification is a typical computer vision problem which aims at matching pedestrians across disjoint camera views.  ...  It proposes a human parts semantic segmentation aware representation learning method for person re-identification.  ... 
doi:10.3390/app9061239 fatcat:vvcpps6m4rfnpgvgqwc34tma24

The Re-identification Challenge [chapter]

Shaogang Gong, Marco Cristani, Chen Change Loy, Timothy M. Hospedales
2014 Person Re-Identification  
For making sense of the vast quantity of visual data generated by the rapid expansion of large scale distributed multi-camera systems, automated person re-identification is essential.  ...  Whilst solving the person re-identification problem is inherently challenging, it also promises enormous potential for a wide range of practical applications, ranging from security and surveillance to  ...  Chapter 5 embeds middle-level cloth attributes via a latent SVM framework for more robust person re-identification.  ... 
doi:10.1007/978-1-4471-6296-4_1 dblp:series/acvpr/GongCLH14 fatcat:l7jbhs4g2jgcxdjceywbszb374

Deep Learning-based Occluded Person Re-identification: A Survey [article]

Yunjie Peng, Saihui Hou, Chunshui Cao, Xu Liu, Yongzhen Huang, Zhiqiang He
2022 arXiv   pre-print
Occluded person re-identification (Re-ID) aims at addressing the occlusion problem when retrieving the person of interest across multiple cameras.  ...  With the promotion of deep learning technology and the increasing demand for intelligent video surveillance, the frequent occlusion in real-world applications has made occluded person Re-ID draw considerable  ...  ., the saliency and the semantic parsing, to guide the CNN backbone to learn complementary representations for re-identification.  ... 
arXiv:2207.14452v1 fatcat:egnltk4epndh5ovxaz3zocicim

Pose-Guided Multi-Scale Structural Relationship Learning for Video-Based Pedestrian Re-Identification

Dan Wei, Xiaoqiang Hu, Ziyang Wang, Jianglin Shen, Hongjuan Ren
2021 IEEE Access  
How to extract discriminative features from redundant video information is a key issue for video pedestrian re-identification.  ...  In this paper, a posture-guided multi-scale structural relationship learning pedestrian re-identification method is proposed.  ...  of occlusion, posture change and redundant information on re-identification.  ... 
doi:10.1109/access.2021.3062967 fatcat:rec42qjynbg7dhpbfvvwy7t3ja

User recognition for guiding and following people with a mobile robot in a clinical environment

Markus Eisenbach, Alexander Vorndran, Sven Sorge, Horst-Michael Gross
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Therefore, we implemented a person re-identification module that continuously reidentifies the patient, using only few amount of the robot's processing resources.  ...  To hold contact to the patient, even after temporally full occlusions, robust user re-identification is essential.  ...  Fig. 2 . 2 Processing chain for fast person re-identification on a mobile robot. Fig. 3 . 3 Systematization of visual features for person re-identification.  ... 
doi:10.1109/iros.2015.7353880 dblp:conf/iros/EisenbachVSG15 fatcat:qpzeau4jibhchfllumzbloifum

Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation

Jilin Tang, Yi Yuan, Tianjia Shao, Yong Liu, Mengmeng Wang, Kun Zhou
In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance.  ...  Specifically, instead of learning the complex overall pose changes of human body, we decompose the human body into different semantic parts (e.g., head, torso, and legs) and apply different networks to  ...  in Figure 1 ), has aroused extensive attention due to its wide range of practical applications for image editing, image animation, person re-identification (ReID), and so on.  ... 
doi:10.1609/aaai.v35i3.16369 fatcat:52xug5alyfgylmvim4d5ffv4mi

Human Pose Transfer by Adaptive Hierarchical Deformation [article]

Jinsong Zhang, Xingzi Liu, Kun Li
2020 arXiv   pre-print
The first level generates human semantic parsing aligned with the target pose, and the second level generates the final textured person image in the target pose with the semantic guidance.  ...  Furthermore, our method can be applied to clothing texture transfer.  ...  ] , person re-identification [QFX * 18, ZYY * 19] and image-based animation [LYL * 17] .  ... 
arXiv:2012.06940v1 fatcat:v5tiht5l3jhm5hofpake7e25wm

Person Re-identification by Effective Features and Self-optimized Pseudo-label

Ming-Xiang He, Jin-Fang Gao, Guan Li, You-Zhi Xin
2021 IEEE Access  
With the development of deep learning, person re-identification (ReID) has been widely concerned and studied.  ...  INDEX TERMS Person re-identification, deep learning, saliency feature, head-shoulder feature, pseudo-label.  ...  INTRODUCTION The task of person re-identification (ReID) is to identify the target person from a large set collected by multiple non-overlapping cameras [1] .  ... 
doi:10.1109/access.2021.3062281 fatcat:vefmpocgjfes5lmqnk6velh3zq
« Previous Showing results 1 — 15 out of 1,041 results