{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:33Z","timestamp":1777888833215,"version":"3.51.4"},"reference-count":86,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02108","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22707-22717","source":"Crossref","is-referenced-by-count":0,"title":["No More Sibling Rivalry: Debiasing Human-Object Interaction Detection"],"prefix":"10.1109","author":[{"given":"Bin","family":"Yang","sequence":"first","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"Zhang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sibei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0034"},{"key":"ref5","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref6","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445463"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/mva57639.2023.10215534"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02369"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01893"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16217"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00139"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref19","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Nofrills human-object interaction detection: Factorization, layout encodings, and training techniques","author":"Gupta","year":"2019","journal-title":"ICCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018417"},{"key":"ref22","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657505"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1138"},{"key":"ref26","article-title":"Mvtokenflow: High-quality 4d content generation using multiview token flow","author":"Huang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref29","article-title":"Detecting human-object interactions with action cooccurrence priors","author":"Kim","year":"2020","journal-title":"In ECCV"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref33","first-page":"19730","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"ref36","article-title":"Hoi analysis: Integrating and decomposing humanobject interaction","author":"Li","year":"2020","journal-title":"In NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02663"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_15"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02665"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3331738"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref47","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref49","volume-title":"Human-computer interaction","author":"Preece","year":"1994"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref52","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01438"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"ref57","article-title":"The devil is in the object boundary: Towards annotation-free instance segmentation using foundation models","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_13"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02642"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_15"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref70","article-title":"Cyclehoi: Improving human-object interaction detection with cycle consistency of detection and generation","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00212"},{"key":"ref73","article-title":"Boosting human-object interaction detection with text-to-image diffusion model","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01604"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref76","article-title":"Rlip: Relational language-image pre-training for human-object interaction detection","author":"Yuan","year":"2022","journal-title":"In NeurIPS"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref80","first-page":"10411","article-title":"Exploring predicate visual context in detecting of human-object interactions","volume-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Frederic"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0228"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3049156"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00433"}],"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\/11443644.pdf?arnumber=11443644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:35Z","timestamp":1777611575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02108","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}