Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels
One of the major challenges in person Re-Identification (ReID) is the inconsistent visual appearance of a person. Current works on visual feature and distance metric learning have achieved significant achievements, but still suffer from the limited robustness to pose variations, viewpoint changes, e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8822734/ |
| _version_ | 1818855360975339520 |
|---|---|
| author | Shun Zhang Yantao He Jiang Wei Shaohui Mei Shuai Wan Ke Chen |
| author_facet | Shun Zhang Yantao He Jiang Wei Shaohui Mei Shuai Wan Ke Chen |
| author_sort | Shun Zhang |
| collection | DOAJ |
| description | One of the major challenges in person Re-Identification (ReID) is the inconsistent visual appearance of a person. Current works on visual feature and distance metric learning have achieved significant achievements, but still suffer from the limited robustness to pose variations, viewpoint changes, etc. This makes person ReID among multiple cameras still challenging. This work is motivated to learn mid-level human attributes which are robust to visual appearance variations and could be used as efficient features for person matching. We propose a supervised multi-task learning framework which considers attribute label information with joint identification-verification network to simultaneously learn an attribute-semantic and identity-discriminative feature representation. Specifically, this framework adopts the part-based deep neural network and learn three different tasks simultaneously: person identification, person verifications and attribute identification, so as to discover and capture concurrently complementary discriminative information about a person image from global and local image features and mid-level attribute features in one deep neural network. With the multi-task learning architecture, we obtain a discriminative model that reaches a synergy in distinguishing different person images, as manifested with the competitive accuracy on three person ReID datasets: Market1501, DukeMTMC-reID and VIPeR. |
| first_indexed | 2024-12-19T08:07:23Z |
| format | Article |
| id | doaj.art-d706ad848cd8476e9774d71896b1ebdb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T08:07:23Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d706ad848cd8476e9774d71896b1ebdb2022-12-21T20:29:43ZengIEEEIEEE Access2169-35362019-01-01712611612612610.1109/ACCESS.2019.29390718822734Person Re-Identification With Joint Verification and Identification of Identity-Attribute LabelsShun Zhang0https://orcid.org/0000-0003-3380-8957Yantao He1Jiang Wei2Shaohui Mei3https://orcid.org/0000-0002-8018-596XShuai Wan4Ke Chen5School of Electronic and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronic and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronic and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronic and Information, Northwestern Polytechnical University, Xi’an, ChinaSchool of Electronic and Information, Northwestern Polytechnical University, Xi’an, ChinaDepartment of Computer Science, The University of Manchester, Manchester, U.K.One of the major challenges in person Re-Identification (ReID) is the inconsistent visual appearance of a person. Current works on visual feature and distance metric learning have achieved significant achievements, but still suffer from the limited robustness to pose variations, viewpoint changes, etc. This makes person ReID among multiple cameras still challenging. This work is motivated to learn mid-level human attributes which are robust to visual appearance variations and could be used as efficient features for person matching. We propose a supervised multi-task learning framework which considers attribute label information with joint identification-verification network to simultaneously learn an attribute-semantic and identity-discriminative feature representation. Specifically, this framework adopts the part-based deep neural network and learn three different tasks simultaneously: person identification, person verifications and attribute identification, so as to discover and capture concurrently complementary discriminative information about a person image from global and local image features and mid-level attribute features in one deep neural network. With the multi-task learning architecture, we obtain a discriminative model that reaches a synergy in distinguishing different person images, as manifested with the competitive accuracy on three person ReID datasets: Market1501, DukeMTMC-reID and VIPeR.https://ieeexplore.ieee.org/document/8822734/Person re-identificationattribute learningmulti-task learningconvolutional neural network |
| spellingShingle | Shun Zhang Yantao He Jiang Wei Shaohui Mei Shuai Wan Ke Chen Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels IEEE Access Person re-identification attribute learning multi-task learning convolutional neural network |
| title | Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels |
| title_full | Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels |
| title_fullStr | Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels |
| title_full_unstemmed | Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels |
| title_short | Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels |
| title_sort | person re identification with joint verification and identification of identity attribute labels |
| topic | Person re-identification attribute learning multi-task learning convolutional neural network |
| url | https://ieeexplore.ieee.org/document/8822734/ |
| work_keys_str_mv | AT shunzhang personreidentificationwithjointverificationandidentificationofidentityattributelabels AT yantaohe personreidentificationwithjointverificationandidentificationofidentityattributelabels AT jiangwei personreidentificationwithjointverificationandidentificationofidentityattributelabels AT shaohuimei personreidentificationwithjointverificationandidentificationofidentityattributelabels AT shuaiwan personreidentificationwithjointverificationandidentificationofidentityattributelabels AT kechen personreidentificationwithjointverificationandidentificationofidentityattributelabels |