{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:45:16Z","timestamp":1777657516514,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DARPA Assured Neuro Symbolic Learning and Reasoning (ANSR) Program","award":["FA8750-23-2-1016"],"award-info":[{"award-number":["FA8750-23-2-1016"]}]},{"name":"DARPA Knowledge Management at Scale and Speed (KMASS) Program","award":["HR00112220047"],"award-info":[{"award-number":["HR00112220047"]}]},{"name":"DARPA Computational Cultural Understanding (CCU) Program","award":["HR001122C0029"],"award-info":[{"award-number":["HR001122C0029"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62306064"],"award-info":[{"award-number":["62306064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3330304","type":"journal-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T19:20:48Z","timestamp":1699644048000},"page":"6274-6288","source":"Crossref","is-referenced-by-count":17,"title":["Toward a Unified Transformer-Based Framework for Scene Graph Generation and Human-Object Interaction Detection"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8676-7429","authenticated-orcid":false,"given":"Tao","family":"He","sequence":"first","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4651-2821","authenticated-orcid":false,"given":"Yuan-Fang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Data Science and AI, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref3","first-page":"2171","article-title":"Pixels to graphs by associative embedding","volume-title":"Proc. NIPS","author":"Newell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/82"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01568"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref13","article-title":"RelTR: Relation transformer for scene graph generation","author":"Cong","year":"2022","journal-title":"arXiv:2201.11460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref19","article-title":"ICAN: Instance-centric attention network for human-object interaction detection","author":"Gao","year":"2018","journal-title":"arXiv:1808.10437"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"ref26","article-title":"SGTR: End-to-end scene graph generation with transformer","author":"Li","year":"2021","journal-title":"arXiv:2112.12970"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00977"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_15"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_15"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1595"},{"key":"ref39","article-title":"Improving multi-task deep neural networks via knowledge distillation for natural language understanding","author":"Liu","year":"2019","journal-title":"arXiv:1904.09482"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref52","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01563"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref55","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"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10315051.pdf?arnumber=10315051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T17:27:30Z","timestamp":1709400450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10315051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3330304","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}