{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:20:36Z","timestamp":1779384036251,"version":"3.53.1"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62231002"],"award-info":[{"award-number":["62231002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62522101"],"award-info":[{"award-number":["62522101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401027"],"award-info":[{"award-number":["62401027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113396","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T17:45:33Z","timestamp":1772473533000},"page":"113396","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A novel geometry-aware spatio-temporal network for multi-view video feature learning"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3287-2474","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4639-8136","authenticated-orcid":false,"given":"Lai","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4708-6572","authenticated-orcid":false,"given":"Xin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113396_bib0001","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"1739","article-title":"Self-supervised human pose based multi-camera video synchronization","author":"Yin","year":"2022"},{"key":"10.1016\/j.patcog.2026.113396_bib0002","first-page":"2204","article-title":"Cross-view referring multi-object tracking","volume":"39","author":"Chen","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113396_bib0003","article-title":"Track initialization and re-identification for 3D multi-view multi-object tracking","volume":"111","author":"Van Ma","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113396_bib0004","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9834","article-title":"Visio-temporal attention for multi-camera multi-target association","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113396_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113072","article-title":"DSVTformer: dual-stream spatial-view-temporal transformer for multi-view 3D human pose estimation","volume":"175","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"issue":"9","key":"10.1016\/j.patcog.2026.113396_bib0006","doi-asserted-by":"crossref","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","article-title":"Multiple object tracking using k-shortest paths optimization","volume":"33","author":"Berclaz","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.patcog.2026.113396_bib0007","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1109\/TPAMI.2007.1174","article-title":"Multicamera people tracking with a probabilistic occupancy map","volume":"30","author":"Fleuret","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113396_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7236","article-title":"OCMCTrack: online multi-target multi-camera tracking with corrective matching cascade","author":"Specker","year":"2024"},{"issue":"1","key":"10.1016\/j.patcog.2026.113396_bib0009","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1007\/s11263-023-01857-z","article-title":"Benchmarking the complementary-view multi-human association and tracking","volume":"132","author":"Han","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113396_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21508","article-title":"GeoMVSNet: learning multi-view stereo with geometry perception","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113396_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110362","article-title":"Multi-granularity cross transformer network for person re-identification","volume":"150","author":"Li","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113396_bib0012","article-title":"ESMformer: error-aware self-supervised transformer for multi-view 3D human pose estimation","volume":"158","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.patcog.2026.113396_bib0013","first-page":"1","article-title":"An end-to-end heterogeneous restraint network for RGB-D cross-modal person re-identification","volume":"18","author":"Wu","year":"2022","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl.(TOMM)"},{"key":"10.1016\/j.patcog.2026.113396_bib0014","article-title":"Texture-aware transformer with pose-patch mapping for occluded person re-identification","volume":"172","author":"Wang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113396_bib0015","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/TIP.2025.3648582","article-title":"P-CLIP: progressive discrepancy learning for one-shot text-to-image person re-identification","volume":"35","author":"Wang","year":"2026","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113396_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110053","article-title":"Joint discriminative representation learning for end-to-end person search","volume":"147","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113396_bib0017","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2197","article-title":"Person re-identification by local maximal occurrence representation and metric learning","author":"Liao","year":"2015"},{"key":"10.1016\/j.patcog.2026.113396_bib0018","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"46","article-title":"Video-based visible-infrared person re-identification via style disturbance defense and dual interaction","author":"Zhou","year":"2023"},{"key":"10.1016\/j.patcog.2026.113396_bib0019","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3691","article-title":"Batch dropblock network for person re-identification and beyond","author":"Dai","year":"2019"},{"key":"10.1016\/j.patcog.2026.113396_bib0020","first-page":"11173","article-title":"Semantics-aligned representation learning for person re-identification","volume":"34","author":"Jin","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113396_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3186","article-title":"Relation-aware global attention for person re-identification","author":"Zhang","year":"2020"},{"issue":"6","key":"10.1016\/j.patcog.2026.113396_bib0022","doi-asserted-by":"crossref","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","article-title":"Deep learning for person re-identification: a survey and outlook","volume":"44","author":"Ye","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"10.1016\/j.patcog.2026.113396_bib0023","doi-asserted-by":"crossref","first-page":"17307","DOI":"10.1109\/TNNLS.2023.3301856","article-title":"Aaformer: auto-aligned transformer for person re-identification","volume":"35","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113396_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7267","article-title":"Cascade transformers for end-to-end person search","author":"Yu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113396_bib0025","series-title":"European Conference on Computer Vision","first-page":"621","article-title":"OIMNet++: prototypical normalization and localization-aware learning for person search","author":"Lee","year":"2022"},{"key":"10.1016\/j.patcog.2026.113396_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111443","article-title":"Adaptive transformer with pyramid fusion for cloth-changing person re-identification","volume":"163","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113396_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111247","article-title":"Local-enhanced representation for text-based person search","volume":"161","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.patcog.2026.113396_bib0028","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/TPAMI.2006.80","article-title":"Principal axis-based correspondence between multiple cameras for people tracking","volume":"28","author":"Hu","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113396_bib0029","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4256","article-title":"Multi-view people tracking via hierarchical trajectory composition","author":"Xu","year":"2016"},{"key":"10.1016\/j.patcog.2026.113396_bib0030","first-page":"7292","article-title":"Scene-centric joint parsing of cross-view videos","volume":"32","author":"Qi","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113396_bib0031","doi-asserted-by":"crossref","first-page":"5191","DOI":"10.1109\/TIP.2020.2980070","article-title":"Multi-target multi-camera tracking by tracklet-to-target assignment","volume":"29","author":"He","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113396_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13784","article-title":"DyGLIP: a dynamic graph model with link prediction for accurate multi-camera multiple object tracking","author":"Quach","year":"2021"},{"key":"10.1016\/j.patcog.2026.113396_bib0033","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10051","article-title":"Rest: a reconfigurable spatial-temporal graph model for multi-camera multi-object tracking","author":"Cheng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113396_bib0034","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"16892","article-title":"All-day multi-camera multi-target tracking","author":"Fan","year":"2025"},{"key":"10.1016\/j.patcog.2026.113396_bib0035","series-title":"2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance","first-page":"1","article-title":"Pets2009: dataset and challenge","author":"Ferryman","year":"2009"},{"key":"10.1016\/j.patcog.2026.113396_bib0036","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5030","article-title":"WILDTRACK: a multi-camera HD dataset for dense unscripted pedestrian detection","author":"Chavdarova","year":"2018"},{"key":"10.1016\/j.patcog.2026.113396_bib0037","doi-asserted-by":"crossref","unstructured":"Y. Hou, L. Zheng, S. Gould, Multiview detection with feature perspective transformation, arXiv preprint arXiv: 2007.07247(2020).","DOI":"10.1007\/978-3-030-58571-6_1"},{"key":"10.1016\/j.patcog.2026.113396_bib0038","series-title":"Proc. IEEE International Conference on Computer Vision","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.patcog.2026.113396_bib0039","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113396_bib0040","series-title":"2017 IEEE International Conference on Image Processing (ICIP)","first-page":"3645","article-title":"Simple online and realtime tracking with a deep association metric","author":"Wojke","year":"2017"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003614?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003614?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:02:10Z","timestamp":1779382930000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326003614"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":40,"alternative-id":["S0031320326003614"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113396","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A novel geometry-aware spatio-temporal network for multi-view video feature learning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113396","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113396"}}