{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:31Z","timestamp":1777865371873,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62476021,72225011,72434005,62372339,92470203"],"award-info":[{"award-number":["62476021,72225011,72434005,62372339,92470203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02186","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23551-23560","source":"Crossref","is-referenced-by-count":0,"title":["Visual Relation Diffusion for Human-Object Interaction Detection"],"prefix":"10.1109","author":[{"given":"Ping","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology BJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yepeng","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology BJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology BJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Zheng","sequence":"additional","affiliation":[{"name":"CASIA,State Key Laboratory of Multimodal Artifical Intelligence Systems"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Liang","sequence":"additional","affiliation":[{"name":"NERCMS, School of Computer Science, Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology BJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, School of Computer Science and Technology BJTU"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","article-title":"Label-efficient semantic segmentation with diffusion models","author":"Baranchuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0034"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02147"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref9","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1775"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_1"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0746"},{"key":"ref24","first-page":"5011","article-title":"Hoi analysis: Integrating and decomposing human-object interaction","volume":"33","author":"Li","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02663"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02665"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1989"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01976"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02642"},{"key":"ref37","article-title":"Diffusion feedback helps clip see better","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Cyclehoi: Improving human-object interaction detection with cycle consistency of detection and generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01466"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00461"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01604"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref46","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage hoi detection","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214431"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120319"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3339593"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.100939"},{"key":"ref51","first-page":"13319","article-title":"Spatially conditioned graphs for detecting human-object interactions","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Frederic","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref53","first-page":"10411","article-title":"Exploring predicate visual context in detecting of human-object interactions","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Frederic","year":"2023"},{"key":"ref54","article-title":"Fast sampling of diffusion models with exponential integrator","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444909.pdf?arnumber=11444909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:44Z","timestamp":1777530044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02186","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}