{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T13:55:54Z","timestamp":1769262954404,"version":"3.49.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62476021"],"award-info":[{"award-number":["62476021"]}],"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":["72225011"],"award-info":[{"award-number":["72225011"]}],"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":["72434005"],"award-info":[{"award-number":["72434005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Projects Program of State Key Laboratory of Multimodal Artificial Intelligence Systems","award":["MAIS2024106"],"award-info":[{"award-number":["MAIS2024106"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2025JBZX062"],"award-info":[{"award-number":["2025JBZX062"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2026.3652953","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:05:43Z","timestamp":1768255543000},"page":"551-555","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Spatial Guided Reasoning for Human-Object Interaction Detection"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-1392","authenticated-orcid":false,"given":"Ping","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1161-8995","authenticated-orcid":false,"given":"Chunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0405-5458","authenticated-orcid":false,"given":"Xiaolong","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artifical Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3503359"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3339593"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3575626"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3549698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.100939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3612592"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214431"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3329457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref16","first-page":"23551","article-title":"Visual relation diffusion for human-object interaction detection","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Cao","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11208960"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3606840"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1775"},{"key":"ref21","first-page":"45895","article-title":"CLIP4HOI: Towards adapting CLIP for practical zero-shot HOI detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mao","year":"2023"},{"key":"ref22","first-page":"739","article-title":"Detecting any human-object interaction relationship: Universal HOI detector with spatial prompt learning on foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01858"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01466"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32411"},{"key":"ref26","first-page":"5011","article-title":"Hoi analysis: Integrating and decomposing human-object interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01880"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref32","article-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref35","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015"},{"key":"ref36","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02642"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2025.104607"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867733"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3559891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3457036"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319330"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11345983.pdf?arnumber=11345983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:02:20Z","timestamp":1769202140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/lsp.2026.3652953","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}