{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T05:53:52Z","timestamp":1777787632365,"version":"3.51.4"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401447"],"award-info":[{"award-number":["62401447"]}],"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":["62133013"],"award-info":[{"award-number":["62133013"]}],"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":["U24B20161"],"award-info":[{"award-number":["U24B20161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016692","name":"Key Research and Development Program of Shaanxi","doi-asserted-by":"publisher","award":["2024GX-YBXM-051"],"award-info":[{"award-number":["2024GX-YBXM-051"]}],"id":[{"id":"10.13039\/100016692","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcyb.2026.3659335","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:20:50Z","timestamp":1771449650000},"page":"2638-2649","source":"Crossref","is-referenced-by-count":0,"title":["VL-HTR: Learning Human\u2013Target Representation From Vision\u2013Language Model"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-4685","authenticated-orcid":false,"given":"Binglu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6307-5969","authenticated-orcid":false,"given":"Chenxi","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyi","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Xi&#x2019;an University of Architecture and Technology, Xi&#x2019;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haisheng","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5205-6319","authenticated-orcid":false,"given":"Guangyu","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3909-488X","authenticated-orcid":false,"given":"Zhijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321337"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318839"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02689"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0149-7634(00)00025-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2023.3296489"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IECON51785.2023.10312057"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-02180-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01914"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3606947"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01898"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD54268.2022.9776291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HDIS56859.2022.9991423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3312392"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3244269"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0500"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00349"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28883"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3639891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32444"},{"key":"ref26","article-title":"GazeCLIP: Enhancing gaze estimation through text-guided multimodal learning","author":"Wang","year":"2023","journal-title":"arXiv:2401.00260"},{"key":"ref27","first-page":"199","article-title":"Where are they looking","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"28","author":"Recasens"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00544"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3066465"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3165063"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00064-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00196"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00101-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01998"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref38","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref39","first-page":"34899","article-title":"Fully convolutional one-stage 3D object detection on LiDAR range images","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Tian"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref41","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref43","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"issue":"140","key":"ref44","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"ref45","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref46","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref47","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yao"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02386"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28496"},{"key":"ref57","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_3"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01123"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3071621"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3190314"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01373"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/11481828\/11398822.pdf?arnumber=11398822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:51:26Z","timestamp":1777492286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11398822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":64,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2026.3659335","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}