{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:22:18Z","timestamp":1779380538407,"version":"3.53.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62206075"],"award-info":[{"award-number":["62206075"]}],"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":["61733011"],"award-info":[{"award-number":["61733011"]}],"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":["62261160652"],"award-info":[{"award-number":["62261160652"]}],"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":["U23A20343"],"award-info":[{"award-number":["U23A20343"]}],"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":["61821005"],"award-info":[{"award-number":["61821005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515110438"],"award-info":[{"award-number":["2021A1515110438"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["RCBS20221008093220004"],"award-info":[{"award-number":["RCBS20221008093220004"]}]},{"name":"Shenzhen Science and Technology Program","award":["GXWD20231129125006001"],"award-info":[{"award-number":["GXWD20231129125006001"]}]},{"name":"Chinese Academy of Sciences (CAS) Project for Young Scientists in Basic Research","award":["YSBR-041"],"award-info":[{"award-number":["YSBR-041"]}]},{"name":"Youth Innovation Promotion Association of CAS","award":["Y202051"],"award-info":[{"award-number":["Y202051"]}]},{"DOI":"10.13039\/501100011259","name":"State Key Laboratory of Robotics","doi-asserted-by":"publisher","award":["2023-O06"],"award-info":[{"award-number":["2023-O06"]}],"id":[{"id":"10.13039\/501100011259","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3402247","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T18:09:17Z","timestamp":1715969357000},"page":"9760-9773","source":"Crossref","is-referenced-by-count":28,"title":["Learning Self- and Cross-Triplet Context Clues for Human-Object Interaction Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3839-0078","authenticated-orcid":false,"given":"Weihong","family":"Ren","sequence":"first","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinguo","family":"Luo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weibo","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8235-7852","authenticated-orcid":false,"given":"Liangqiong","family":"Qu","sequence":"additional","affiliation":[{"name":"Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8039-6679","authenticated-orcid":false,"given":"Zhi","family":"Han","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5027-1381","authenticated-orcid":false,"given":"Jiandong","family":"Tian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2880-4698","authenticated-orcid":false,"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3190314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057469"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/384"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231528"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216663"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3119892"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref22","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref25","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref28","first-page":"1","article-title":"Visual recognition with deep nearest centroids","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref29","first-page":"12826","article-title":"Learning equivariant segmentation with instance-unique querying","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Wang"},{"key":"ref30","article-title":"ICAN: Instance-centric attention network for human-object interaction detection","author":"Gao","year":"2018","journal-title":"arXiv:1808.10437"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00977"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01458-8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_15"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054048"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3049156"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref49","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01976"},{"key":"ref54","first-page":"20787","article-title":"CLUSTSEG: Clustering for universal segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref56","first-page":"37416","article-title":"RLIP: Relational language-image pre-training for human-object interaction detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref58","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"},{"key":"ref59","first-page":"21158","article-title":"Neural-logic human-object interaction detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611735"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref62","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"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20041"},{"key":"ref68","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"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01893"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_8"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20229"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01858"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01466"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02147"},{"key":"ref75","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739869\/10533224.pdf?arnumber=10533224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:19:44Z","timestamp":1732666784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10533224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":78,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3402247","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}