Visual Appearance and Soft Biometrics Fusion for Person Re-Identification Using Deep Learning
dc.contributor.author | Khan, Samee Ullah | |
dc.contributor.author | Khan, Noman | |
dc.contributor.author | Hussain, Tanveer | |
dc.contributor.author | Muhammad, Khan | |
dc.contributor.author | Hijji, Mohammad | |
dc.contributor.author | Del Ser, Javier | |
dc.contributor.author | Baik, Sung Wook | |
dc.contributor.institution | IA | |
dc.date.accessioned | 2024-09-06T10:40:01Z | |
dc.date.available | 2024-09-06T10:40:01Z | |
dc.date.issued | 2023-05-01 | |
dc.description | Publisher Copyright: © 2023 IEEE. | |
dc.description.abstract | Learning descriptions of individual pedestrian is a common goal of both person re-identification (P-ReID) and attribute recognition methods, which are typically differentiated only in terms of their granularity. However, existing P-ReID methods only consider identification labels for individual pedestrian. In this article, we present a multi-scale pyramid attention (MSPA) model for P-ReID that jointly manipulates the complementarity between semantic attributes and visual appearance to address this limitation. The proposed MSPA method mainly comprises three steps. Initially, a backbone model followed by appearance and attribute networks is individually trained to perform P-ReID and pedestrian attribute classification tasks. The attribute network primarily focuses on suppressed image areas associated with soft biometric data while retaining the semantic context among attributes using a convolutional long short-term memory architecture. Additionally, the identification network extracts rich contextual features from an image at varying scales using a residual pyramid module. In the second step, the dual network features are fused, and MSPA is re-trained for the P-ReID task to further improve its complementary capabilities. Finally, we experimentally evaluated the proposed model on the two benchmark datasets Market-1501 and DukeMTMC-reID, and the results show that our approach achieved state-of-the-art performance. | en |
dc.description.sponsorship | This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea Government, MSIT, under Grant 2023R1A2C1005788. | |
dc.description.status | Peer reviewed | |
dc.format.extent | 12 | |
dc.identifier.citation | Khan , S U , Khan , N , Hussain , T , Muhammad , K , Hijji , M , Del Ser , J & Baik , S W 2023 , ' Visual Appearance and Soft Biometrics Fusion for Person Re-Identification Using Deep Learning ' , IEEE Journal on Selected Topics in Signal Processing , vol. 17 , no. 3 , pp. 575-586 . https://doi.org/10.1109/JSTSP.2023.3260627 | |
dc.identifier.doi | 10.1109/JSTSP.2023.3260627 | |
dc.identifier.issn | 1932-4553 | |
dc.identifier.uri | https://hdl.handle.net/11556/4916 | |
dc.identifier.url | http://www.scopus.com/inward/record.url?scp=85151496540&partnerID=8YFLogxK | |
dc.language.iso | eng | |
dc.relation.ispartof | IEEE Journal on Selected Topics in Signal Processing | |
dc.relation.projectID | Ministry of Science, ICT and Future Planning, MSIP, 2023R1A2C1005788 | |
dc.relation.projectID | National Research Foundation of Korea, NRF | |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.subject.keywords | Deep learning | |
dc.subject.keywords | multi-view surveillance data | |
dc.subject.keywords | person re-identification | |
dc.subject.keywords | soft biometric | |
dc.subject.keywords | Signal Processing | |
dc.subject.keywords | Electrical and Electronic Engineering | |
dc.title | Visual Appearance and Soft Biometrics Fusion for Person Re-Identification Using Deep Learning | en |
dc.type | journal article |