{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:11:40Z","timestamp":1759331500342,"version":"build-2065373602"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4703200"],"award-info":[{"award-number":["2022YFB4703200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206075","61733011","62261160652","U23A20343"],"award-info":[{"award-number":["62206075","61733011","62261160652","U23A20343"]}],"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":["2024A1515012028"],"award-info":[{"award-number":["2024A1515012028"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["RCBS20221008093220004","GXWD20231129125006001"],"award-info":[{"award-number":["RCBS20221008093220004","GXWD20231129125006001"]}]},{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund (FDCT), Macau, SAR","doi-asserted-by":"publisher","award":["0095\/2022\/AFJ"],"award-info":[{"award-number":["0095\/2022\/AFJ"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018617","name":"Liaoning Revitalization Talents Program","doi-asserted-by":"publisher","award":["XLYC2403128"],"award-info":[{"award-number":["XLYC2403128"]}],"id":[{"id":"10.13039\/501100018617","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3607614","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:36:12Z","timestamp":1758044172000},"page":"5710-5724","source":"Crossref","is-referenced-by-count":0,"title":["Synergistic Prompting Learning for Human-Object Interaction Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4069-1984","authenticated-orcid":false,"given":"Jinguo","family":"Luo","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering, State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3839-0078","authenticated-orcid":false,"given":"Weihong","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5546-6666","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4756-3962","authenticated-orcid":false,"given":"Xi\u2019ai","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation and the Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8548-861X","authenticated-orcid":false,"given":"Huijie","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation and the Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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 and the Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2880-4698","authenticated-orcid":false,"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113114"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6855"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093784"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3096333"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231528"},{"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\/CVPR.2019.00043"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01172"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01576"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01604"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref26","article-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022","journal-title":"arXiv:2203.17274"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125258"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00332"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02663"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334100"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01687"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054048"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01948"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref44","article-title":"ICAN: Instance-centric attention network for human-object interaction detection","author":"Gao","year":"2018","journal-title":"arXiv:1808.10437"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350978"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01466"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02642"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02665"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402247"},{"key":"ref56","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":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref58","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref59","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref61","first-page":"6690","article-title":"When visual prompt tuning meets source-free domain adaptive semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00229"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02147"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01976"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref68","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref72","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":"ref73","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":"ref74","first-page":"1","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11164877.pdf?arnumber=11164877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:29:33Z","timestamp":1759235373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3607614","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}