Filters








50,891 Hits in 4.9 sec

Deep Representation Learning with Part Loss for Person Re-Identification [article]

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian
2017 arXiv   pre-print
Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID).  ...  The representation learning risk is evaluated by the proposed part loss, which automatically generates several parts for an image, and computes the person classification loss on each part separately.  ...  INTRODUCTION Person Re-Identification (ReID) targets to identify a probe person appeared under multiple cameras.  ... 
arXiv:1707.00798v2 fatcat:t4nei7ouxvehffdsdxjkoheifi

Deep Representation Learning with Part Loss for Person Re-Identification

Hantao Yao, Shiliang Zhang, Richang Hong, Yongdong Zhang, Changsheng Xu, Qi Tian
2019 IEEE Transactions on Image Processing  
Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID).  ...  Compared with traditional global classification loss, simultaneously considering part loss enforces the deep network to learn representations for different parts and gain the discriminative power on unseen  ...  Introduction Person Re-Identification (ReID) targets to identify a probe person appeared under multiple cameras.  ... 
doi:10.1109/tip.2019.2891888 fatcat:sixozjalnnh6lmcfturmo4jese

Deep-Person: Learning Discriminative Deep Features for Person Re-Identification [article]

Xiang Bai, Mingkun Yang, Tengteng Huang, Zhiyong Dou, Rui Yu, Yongchao Xu
2019 arXiv   pre-print
Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor.  ...  This results in a novel three-branch framework named Deep-Person, which learns highly discriminative features for person Re-ID.  ...  Xiang Bai by the National Program for Support of Topnotch Young Professionals and the Program for HUST Academic Frontier Youth Team. References  ... 
arXiv:1711.10658v4 fatcat:tnr7u5kd6ncxraiwlhtagbazem

Deep ranking model by large adaptive margin learning for person re-identification

Jiayun Wang, Sanping Zhou, Jinjun Wang, Qiqi Hou
2018 Pattern Recognition  
In this paper, we present a novel deep ranking model with feature learning and fusion by learning a large adaptive margin between the intra-class distance and inter-class distance to solve the person re-identification  ...  Treating these pairwise samples as inputs, we build a novel part-based deep convolutional neural network (CNN) to learn the layered feature representations by preserving a large adaptive margin.  ...  our part-based deep CNN to implement an end-to-end feature learning and fusion for person re-identification.  ... 
doi:10.1016/j.patcog.2017.09.024 fatcat:zwoaj2col5aa5oxnfef6vfmpnu

Learning Discriminative Features with Multiple Granularities for Person Re-Identification

Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, Xi Zhou
2018 2018 ACM Multimedia Conference on Multimedia Conference - MM '18  
The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks.  ...  Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios  ...  Related Works With the prosperity of deep learning, feature learning by deep networks has become a common practice in person Re-ID tasks.  ... 
doi:10.1145/3240508.3240552 dblp:conf/mm/WangYCLZ18 fatcat:2sijtwtxlnel5mxmd7pti4vkkq

An enhanced deep feature representation for person re-identification

Shangxuan Wu, Ying-Cong Chen, Xiang Li, An-Cong Wu, Jin-Jie You, Wei-Shi Zheng
2016 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Feature representation and metric learning are two critical components in person re-identification models.  ...  We propose a novel feature extraction model called Feature Fusion Net (FFN) for pedestrian image representation. In FFN, back propagation makes CNN features constrained by the handcrafted features.  ...  Existing deep re-identification networks for person reidentification adopt Deviance Loss [26] or Maximum Mean Discrepancy [1] as loss function.  ... 
doi:10.1109/wacv.2016.7477681 dblp:conf/wacv/WuCLWYZ16 fatcat:nncywoi2u5eapiyj7z5lruejmu

Multi-Scale Triplet CNN for Person Re-Identification

Jiawei Liu, Zheng-Jun Zha, QI Tian, Dong Liu, Ting Yao, Qiang Ling, Tao Mei
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
In particular, we design a unified multi-scale network architecture consisting of both deep and shallow neural networks, towards learning robust and effective features for person re-identification under  ...  We propose to optimize the network parameters by a comparative similarity loss on massive sample triplets, addressing the problem of small training set in person re-identification.  ...  ACKNOWLEDGMENTS This work was supported in part by the National Natural Science Foundation of China (NSFC) under Contract 61472392 and 61429201. This work was also supported in part to Dr.  ... 
doi:10.1145/2964284.2967209 dblp:conf/mm/LiuZTLYLM16 fatcat:dkozhjjbcjfc3iw4haelmya2wi

CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification [article]

Jiawei Liu and Zheng-Jun Zha and Hongtao Xie and Zhiwei Xiong and Yongdong Zhang
2018 arXiv   pre-print
Deep learning techniques have been applied for person re-identification recently, towards learning representation of pedestrian appearance.  ...  This paper presents a novel Contextual-Attentional Attribute-Appearance Network (CA3Net) for person re-identification.  ...  Recently, deep learning technique has been adopted for person re-identification, towards learning discriminative representation of pedestrian appearance. For example, Liu et al.  ... 
arXiv:1811.07544v1 fatcat:qsgoqomymjbuzmqe3wk3nljarm

Occluded Person Re-identification [article]

Jiaxuan Zhuo, Zeyu Chen, Jianhuang Lai, Guangcong Wang
2018 arXiv   pre-print
Person re-identification (re-id) suffers from a serious occlusion problem when applied to crowded public places.  ...  for full-body person images, and 2) multi-task losses that force the neural network not only to discriminate a person's identity but also to determine whether a sample is from the occluded data distribution  ...  datasets for the occluded person re-id to learn a suitable model, especially for deep learning.  ... 
arXiv:1804.02792v3 fatcat:4t2gs2xmsbcu7g25w47bmljfby

Deep learning-based person re-identification methods: A survey and outlook of recent works [article]

Zhangqiang Ming, Min Zhu, Xiangkun Wang, Jiamin Zhu, Junlong Cheng, Chengrui Gao, Yong Yang, Xiaoyong Wei
2022 arXiv   pre-print
With the widespread application of deep neural networks, many deep learning-based person Re-ID methods have emerged.  ...  In recent years, with the increasing demand for public safety and the rapid development of intelligent surveillance networks, person re-identification (Re-ID) has become one of the hot research topics  ...  JG2018190), and in part by the National Natural Science Foundation of China (No. 61872256).  ... 
arXiv:2110.04764v5 fatcat:x2on7dfe2rdfxhaev3c3j34ugu

Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings [article]

Zhongwei Xie, Lin Li, Xian Zhong, Luo Zhong
2018 arXiv   pre-print
Image-to-video person re-identification identifies a target person by a probe image from quantities of pedestrian videos captured by non-overlapping cameras.  ...  In this paper,we propose an end-to-end neural network framework for image-to-video person reidentification by leveraging cross-modal embeddings learned from extra information.Concretely speaking,cross-modal  ...  In general, there are two major types of deep learning structures for person re-identification, i.e. verification models and identification models.  ... 
arXiv:1810.03989v2 fatcat:q3vxzvnukfg25c2nill7y5it2m

Person Re-identification Using Visual Attention [article]

Alireza Rahimpour, Liu Liu, Ali Taalimi, Yang Song, Hairong Qi
2019 arXiv   pre-print
In this paper, we propose a novel approach based on using a gradient-based attention mechanism in deep convolution neural network for solving the person re-identification problem.  ...  Our model learns to focus selectively on parts of the input image for which the networks' output is most sensitive to and processes them with high resolution while perceiving the surrounding image in low  ...  RELATED WORKS Generally, existing approaches for person re-identification are mainly focused on two aspects: learning a distance metric [8] [9] [10] and developing a new feature representation [7, [  ... 
arXiv:1707.07336v7 fatcat:o5x2sk2mlredvek6fs6ox7qjeu

Omnidirectional Feature Learning for Person Re-identification

Di Wu, Hong-Wei Yang, De-Shuang Huang, Chang-An Yuan, Xiao Qin, Yang Zhao, Xin-Yong Zhao, JIAN-HONG SUN
2019 IEEE Access  
INDEX TERMS Person re-identification, deep learning, part feature, triplet model, identification model.  ...  Person re-identification (PReID) has received increasing attention due to it being an important role in intelligent surveillance. Many state-of-the-art PReID methods are part-based deep models.  ...  CONCLUSION In this study, we propose an omnidirectional feature learning deep model for person re-identification.  ... 
doi:10.1109/access.2019.2901764 fatcat:ztucd5y2mzcfloespk6dzvbtbq

HSME: Hypersphere Manifold Embedding for Visible Thermal Person Re-Identification

Yi Hao, Nannan Wang, Jie Li, Xinbo Gao
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Heterogeneous person re-identification between thermal(infrared) and visible images is essentially a cross-modality problem and important for night-time surveillance application.  ...  Person Re-identification(re-ID) has great potential to contribute to video surveillance that automatically searches and identifies people across different cameras.  ...  Acknowledgments This work was supported in part by the National Natural Science Foundation of China under Grant 61876142, 61432014, U1605252, 61671339, 61772402, 61501339, and  ... 
doi:10.1609/aaai.v33i01.33018385 fatcat:aplgooxs45abpeg332ddwqk43q

Omni-directional Feature Learning for Person Re-identification [article]

Di Wu, Hong-Wei Yang, De-Shuang Huang
2018 arXiv   pre-print
Person re-identification (PReID) has received increasing attention due to it is an important part in intelligent surveillance.  ...  Recently, many state-of-the-art methods on PReID are part-based deep models. Most of them focus on learning the part feature representation of person body in horizontal direction.  ...  The model can learn part representation with spatial information from vertical and horizontal orientations.  ... 
arXiv:1812.05319v1 fatcat:lkcfzdynezec7apyaqpmltfj2q
« Previous Showing results 1 — 15 out of 50,891 results