{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:25:03Z","timestamp":1778372703955,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62394330"],"award-info":[{"award-number":["62394330"]}],"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":["62102105"],"award-info":[{"award-number":["62102105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024A1515012064"],"award-info":[{"award-number":["2024A1515012064"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2025A1515010157"],"award-info":[{"award-number":["2025A1515010157"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Program of Guangzhou","award":["2024A03J0394"],"award-info":[{"award-number":["2024A03J0394"]}]},{"name":"Key Laboratory of Philosophy and Social Sciences in Guangdong Province of Maritime Silk Road of Guangzhou University","award":["GD22TWCXGC15"],"award-info":[{"award-number":["GD22TWCXGC15"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tce.2025.3571778","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T13:15:04Z","timestamp":1747746904000},"page":"3617-3630","source":"Crossref","is-referenced-by-count":1,"title":["LactFormer: Language-Aware Context Learning With Multi-Cue Transformers for HOI Detection"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5820-889X","authenticated-orcid":false,"given":"Weilong","family":"Peng","sequence":"first","affiliation":[{"name":"Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keke","family":"Tang","sequence":"additional","affiliation":[{"name":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Health Science Center, Jinan University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4605-9270","authenticated-orcid":false,"given":"Yangtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhao","family":"Xie","sequence":"additional","affiliation":[{"name":"Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4292-8889","authenticated-orcid":false,"given":"Meie","family":"Fang","sequence":"additional","affiliation":[{"name":"Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3373824"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3303309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3210433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2009.5174427"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3349678"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2014.7027342"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref8","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.169"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00977"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3330164"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102043"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01893"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref29","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_22"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00695"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611712"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref37","article-title":"The overlooked classifier in human-object interaction recognition","author":"Jin","year":"2022","journal-title":"arXiv:2203.05676"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095949"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref42","first-page":"1","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Gao"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01948"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331738"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334100"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3330304"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358952"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01604"},{"key":"ref51","first-page":"23655","article-title":"Human-object interaction detection collaborated with large relation-driven diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Li"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01568"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8511-7_34"},{"key":"ref57","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref60","first-page":"5011","article-title":"HOI analysis: Integrating and decomposing human-object interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11128999\/11007583.pdf?arnumber=11007583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T04:44:03Z","timestamp":1755578643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3571778","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}