{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:43Z","timestamp":1783737823638,"version":"3.55.0"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004733","name":"University of Macau","doi-asserted-by":"publisher","award":["CG2025-FST"],"award-info":[{"award-number":["CG2025-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01090","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11720-11730","source":"Crossref","is-referenced-by-count":2,"title":["Beyond Walking: A Large-Scale Image-Text Benchmark for Text-Based Person Anomaly Search"],"prefix":"10.1109","author":[{"given":"Shuyu","family":"Yang","sequence":"first","affiliation":[{"name":"Xi©an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi©an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhedong","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Macau"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70825"},{"key":"ref3","author":"Almazan","year":"2018","journal-title":"Re-id done right: towards good practices for person reidentification"},{"key":"ref4","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372466"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref8","author":"Chen","year":"2023","journal-title":"Shikra: Unleashing multi-modal llm\u2019s referential dialogue magic"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref11","author":"Ding","year":"2021","journal-title":"Semantically self-aligned network for text-to-image part-aware person re-identification"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583365"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475693"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00947"},{"key":"ref16","author":"Gao","year":"2021","journal-title":"Contextual non-local alignment over full-scale representation for text-based person search"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645701"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240550"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.10"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657823"},{"key":"ref24","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746846"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.111"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref34","first-page":"0","article-title":"Aggregating deep pyramidal representations for person reidentification","volume-title":"CVPR workshops","author":"Martinel","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_27"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2699623"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093457"},{"key":"ref41","author":"Reiss","year":"2022","journal-title":"Attribute-based representations for accurate and interpretable video anomaly detection"},{"key":"ref42","article-title":"SG_161222","volume-title":"Realvisxl_v4.0","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714788"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110363"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755422"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729902"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374070"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3327924"},{"key":"ref57","article-title":"When urban region profiling meets large language models","author":"Yan","year":"2024","journal-title":"W W W"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2026.113511"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583232"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3565392"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02082"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"ref64","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"Zeng","year":"2022","journal-title":"ICML"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110280"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref67","article-title":"2","author":"Zheng","year":"2024","journal-title":"object re-identification: Problems, algorithms and responsible research practice. The Boundaries of Data, page 21"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00224"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444668.pdf?arnumber=11444668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:03Z","timestamp":1777612203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01090","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}