Multi‐branch network with hierarchical bilinear pooling for person reidentification
Abstract Because of issues such as viewpoint changes, posture variations, and background cluttering, the task of person reidentification (Re‐ID) remains challenging. The model of combining global features and part features has been widely used in person Re‐ID technology in recent years, but these ef...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | IET Biometrics |
| Online Access: | https://doi.org/10.1049/bme2.12040 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546699724193792 |
|---|---|
| author | Wenyu Wei Wenzhong Yang Enguang Zuo Qiuru Ren Qiuchang Chen |
| author_facet | Wenyu Wei Wenzhong Yang Enguang Zuo Qiuru Ren Qiuchang Chen |
| author_sort | Wenyu Wei |
| collection | DOAJ |
| description | Abstract Because of issues such as viewpoint changes, posture variations, and background cluttering, the task of person reidentification (Re‐ID) remains challenging. The model of combining global features and part features has been widely used in person Re‐ID technology in recent years, but these efforts ignored feature interaction between the convolutional layers and thus lost detailed information conducive to identifying pedestrians under different cameras. To achieve interaction between hierarchical features, a multibranch network with hierarchical bilinear pooling (MBN‐HBP) is proposed. The network consists of a global branch, a part‐level branch, and a hierarchical bilinear pooling (HBP) branch. The person features extracted by the network include not only global and part‐level features but also detailed HBP features. The final feature representation will be more robust to deal with the complex surveillance environment. By conducting comprehensive experiments, competitive performance on the Market‐1501, DukeMTMC‐Re‐ID, and CUHK03 datasets is obtained. |
| format | Article |
| id | doaj-art-d5816dc6de974246bbc5650b0234a7a0 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-d5816dc6de974246bbc5650b0234a7a02025-02-03T06:47:35ZengWileyIET Biometrics2047-49382047-49462022-01-01111233410.1049/bme2.12040Multi‐branch network with hierarchical bilinear pooling for person reidentificationWenyu Wei0Wenzhong Yang1Enguang Zuo2Qiuru Ren3Qiuchang Chen4College of Information Science and Engineering Xinjiang University Urumqi Xinjiang ChinaCollege of Information Science and Engineering Xinjiang University Urumqi Xinjiang ChinaCollege of Information Science and Engineering Xinjiang University Urumqi Xinjiang ChinaCollege of Information Science and Engineering Xinjiang University Urumqi Xinjiang ChinaCollege of Information Science and Engineering Xinjiang University Urumqi Xinjiang ChinaAbstract Because of issues such as viewpoint changes, posture variations, and background cluttering, the task of person reidentification (Re‐ID) remains challenging. The model of combining global features and part features has been widely used in person Re‐ID technology in recent years, but these efforts ignored feature interaction between the convolutional layers and thus lost detailed information conducive to identifying pedestrians under different cameras. To achieve interaction between hierarchical features, a multibranch network with hierarchical bilinear pooling (MBN‐HBP) is proposed. The network consists of a global branch, a part‐level branch, and a hierarchical bilinear pooling (HBP) branch. The person features extracted by the network include not only global and part‐level features but also detailed HBP features. The final feature representation will be more robust to deal with the complex surveillance environment. By conducting comprehensive experiments, competitive performance on the Market‐1501, DukeMTMC‐Re‐ID, and CUHK03 datasets is obtained.https://doi.org/10.1049/bme2.12040 |
| spellingShingle | Wenyu Wei Wenzhong Yang Enguang Zuo Qiuru Ren Qiuchang Chen Multi‐branch network with hierarchical bilinear pooling for person reidentification IET Biometrics |
| title | Multi‐branch network with hierarchical bilinear pooling for person reidentification |
| title_full | Multi‐branch network with hierarchical bilinear pooling for person reidentification |
| title_fullStr | Multi‐branch network with hierarchical bilinear pooling for person reidentification |
| title_full_unstemmed | Multi‐branch network with hierarchical bilinear pooling for person reidentification |
| title_short | Multi‐branch network with hierarchical bilinear pooling for person reidentification |
| title_sort | multi branch network with hierarchical bilinear pooling for person reidentification |
| url | https://doi.org/10.1049/bme2.12040 |
| work_keys_str_mv | AT wenyuwei multibranchnetworkwithhierarchicalbilinearpoolingforpersonreidentification AT wenzhongyang multibranchnetworkwithhierarchicalbilinearpoolingforpersonreidentification AT enguangzuo multibranchnetworkwithhierarchicalbilinearpoolingforpersonreidentification AT qiururen multibranchnetworkwithhierarchicalbilinearpoolingforpersonreidentification AT qiuchangchen multibranchnetworkwithhierarchicalbilinearpoolingforpersonreidentification |