Filters








25,058 Hits in 6.4 sec

Parameter-Efficient Person Re-identification in the 3D Space [article]

Zhedong Zheng, Nenggan Zheng, Yi Yang
2021 arXiv   pre-print
To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space.  ...  However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people.  ...  In this work, we conduct the person re-identification in the 3D space, and learn a new type of robust re-id feature.  ... 
arXiv:2006.04569v3 fatcat:4bjdlqpuvzendmg5xehnidpw4m

Guest Editorial Introduction to the Special Section on Intelligent Visual Content Analysis and Understanding

Hongliang Li, Lu Fang, Tianzhu Zhang
2020 IEEE transactions on circuits and systems for video technology (Print)  
Person Re-Identification refers to matching persons captured by multiply cameras.  ...  In addition to network design, "Top-push constrained modality-adaptive dictionary learning for cross-modality person re-identification," by Zhang et al., discusses the crossmodality person re-identification  ... 
doi:10.1109/tcsvt.2020.3031416 fatcat:gpwbmydqbza5lddatxcfcidwcq

Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild [chapter]

Mang Ye, Xiangyuan Lan, Pong C. Yuen
2018 Lecture Notes in Computer Science  
This paper addresses the scalability and robustness issues of estimating labels from imbalanced unlabeled data for unsupervised video-based person re-identification (re-ID).  ...  After that, a robust and efficient top-k counts label prediction strategy is proposed to predict the labels of unlabeled image sequences.  ...  Acknowledgments This work is partially supported by Hong Kong RGC General Research Fund HKBU (12254316), and National Natural Science Foundation of China (61562048).  ... 
doi:10.1007/978-3-030-01234-2_11 fatcat:dycgvmar55efdmx2dxzdib7yq4

Context-Aware Hypergraph Modeling for Re-identification and Summarization

Santhoshkumar Sunderrajan, B. S. Manjunath
2016 IEEE transactions on multimedia  
We consider the problem of person re-identification and tracking, and propose a novel clothing context-aware color extraction method that is robust to such changes.  ...  A hypergraph representation is used to link related objects for search and re-identification. A diverse hypergraph ranking technique is proposed for person-focused network summarization.  ...  This paper extends these by modeling color drift in such networks and including such contextual information within a graph ranking procedure for person re-identification tasks. B.  ... 
doi:10.1109/tmm.2015.2496139 fatcat:vpnool2wfzdgvdhppf53jagx2y

Dynamic Label Graph Matching for Unsupervised Video Re-identification

Mang Ye, Andy J. Ma, Liang Zheng, Jiawei Li, Pong C. Yuen
2017 2017 IEEE International Conference on Computer Vision (ICCV)  
Label estimation is an important component in an unsupervised person re-identification (re-ID) system.  ...  Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association.  ...  [35] , and then a graph matching procedure is conducted to do re-identification. (2) Establishing a graph for each camera view, Hamid et al  ... 
doi:10.1109/iccv.2017.550 dblp:conf/iccv/YeMZLY17 fatcat:rqkdhr3hsbcdxdw6gq5edqddxa

Person re-identification via rich color-gradient feature

Lingxiang Wu, Jinqiao Wang, Guibo Zhu, Min Xu, Hanqing Lu
2016 2016 IEEE International Conference on Multimedia and Expo (ICME)  
Person re-identification refers to match the same pedestrian across disjoint views in non-overlapping camera networks.  ...  Experimental results on three public datasets, VIPeR, CAVIAR and CUHK01, show the promise of the proposed approach. Index Terms-Person re-identification, encoding color space, second order histogram  ...  [10] formulated person re-id as a graph matching problem and represented person as a graph, which aimed not only at rejecting erroneous matches but also selecting additional useful ones.  ... 
doi:10.1109/icme.2016.7552869 dblp:conf/icmcs/WuWZXL16 fatcat:eaq5gyqylbh5bhsjkm7ldn4age

Person re-identification via efficient inference in fully connected CRF [article]

Jiuqing Wan, Menglin Xing
2015 arXiv   pre-print
In this paper, we address the problem of person re-identification problem, i.e., retrieving instances from gallery which are generated by the same person as the given probe image.  ...  A label variable is associated with each node to indicate whether the corresponding image is from target person.  ...  One of them is focusing on designing suitable feature representation for person re-identification.  ... 
arXiv:1506.06905v1 fatcat:jlbmfnrvlje4tlwfzpiv7uz5t4

2021 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 43

2022 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This index covers all technical items-papers, correspondence, reviews, etc.-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TPAMI March 2021 1085-1091 A Graph-Based Approach for Making Consensus-Based Decisions in Image Search and Person Re-Identification.  ... 
doi:10.1109/tpami.2021.3126216 fatcat:h6bdbf2tdngefjgj76cudpoyia

Learning Multi-Attention Context Graph for Group-Based Re-Identification

Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
A multi-level attention mechanism is developed to formulate both intra- and inter-group context, with an additional self-attention module for robust graph-level representations.  ...  ., group re-id and group-aware person re-id. Specifically, we construct a context graph to exploit dependencies among different people.  ...  PREF [49] learns a feature dictionary for single person re-id and then transfers it for group appearance encoding.  ... 
doi:10.1109/tpami.2020.3032542 pmid:33079658 fatcat:53pzxlxw7fg6bg4chkqvwikts4

Dual Regularized KISS Metric Learning for Person Reidentification

R. Muthumari, S. Manjula
2018 International Journal of Trend in Scientific Research and Development  
To overcome this problem, it introduces regularization techniques to improve the keep it simple and straightforward ( learning for person re-identification.  ...  Person re-identification denotes to the task of matching images of walkers across different camera views at different locations, and the system is particularly popular for video investigation.  ...  Besides distance metric learning based matching schemes, contextual cues are very useful for improving the accuracy and robustness of person re-identification.  ... 
doi:10.31142/ijtsrd13015 fatcat:fif5irzu4be7togcmlsrxkamry

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
This index covers all technical items-papers, correspondence, reviews, etc.-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 92-107 Robust and Efficient Graph Correspondence Transfer for Person Re-Identification.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

The Re-identification Challenge [chapter]

Shaogang Gong, Marco Cristani, Chen Change Loy, Timothy M. Hospedales
2014 Person Re-Identification  
This chapter introduces the re-identification problem, highlights the difficulties in building person re-identification systems, and presents an overview of recent progress and the state-of-the-art approaches  ...  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

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.  ...  INDEX TERMS Pedestrian re-identification, relationship model, graph convolutional network, multi-scale structure relationship.  ...  Extracting robust feature representations is the key to pedestrian re-identification.  ... 
doi:10.1109/access.2021.3062967 fatcat:rec42qjynbg7dhpbfvvwy7t3ja

Unsupervised Person Re-identification via Multi-order Cross-view Graph Adversarial Network

Xiang Fu, Xinyu Lai
2021 IEEE Access  
Unsupervised person re-identification (re-id) is an effective analysis for video surveillance in practice, which can train a pedestrian matching model without any annotations, and it is easy to deploy  ...  INDEX TERMS Unsupervised person re-identification, cross-view graph, graph adversarial network, multi-order correlations.  ...  [9] designed a domain-transferred graph neural network for group re-identification, and the method can obtain robust representation for group images with style-transfer and graph-convolution.  ... 
doi:10.1109/access.2020.3048834 fatcat:v3bhppj4qnccjmsmmrzfgbwie4

PRISM: Person Re-Identification via Structured Matching [article]

Ziming Zhang, Venkatesh Saligrama
2015 arXiv   pre-print
Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network.  ...  We implement PRISM on single shot and multi-shot scenarios. PRISM uniformly outperforms state-of-the-art in terms of matching rate while being computationally efficient.  ...  Robust Person Re-identification In this experiment, we would like to demonstrate the robustness of our method by including the missing match scenarios for re-id.  ... 
arXiv:1406.4444v4 fatcat:qu2e4fskkfgtzgwwxbs7cei7va
« Previous Showing results 1 — 15 out of 25,058 results