{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:22:44Z","timestamp":1784258564457,"version":"3.55.0"},"reference-count":69,"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":["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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01444","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15562-15572","source":"Crossref","is-referenced-by-count":1,"title":["SPADE: Spatial-Aware Denoising Network for Open-Vocabulary Panoptic Scene Graph Generation with Long- and Local-Range Context Reasoning"],"prefix":"10.1109","author":[{"given":"Xin","family":"Hu","sequence":"first","affiliation":[{"name":"The Laboratory of Intelligent Collaborative Computing of UESTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Qin","sequence":"additional","affiliation":[{"name":"The Laboratory of Intelligent Collaborative Computing of UESTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiduo","family":"Duan","sequence":"additional","affiliation":[{"name":"The Laboratory of Intelligent Collaborative Computing of UESTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan-Fang","family":"Li","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"He","sequence":"additional","affiliation":[{"name":"The Laboratory of Intelligent Collaborative Computing of UESTC"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","volume":"abs\/2211.01324","author":"Balaji","year":"2022","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_10"},{"key":"ref11","first-page":"41","article-title":"ican: Instancecentric attention network for human-object interaction detection","volume-title":"British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, September 3\u20136, 2018","author":"Gao","year":"2018"},{"key":"ref12","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2022","journal-title":"ICLR 2022, Virtual Event, April 25\u201329, 2022. OpenReview.net"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/82"},{"key":"ref15","article-title":"Semantic compositional learning for low-shot scene graph generation","author":"He","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01568"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3330304"},{"key":"ref19","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR 2022, Virtual Event, April 25\u201329, 2022. OpenReview.net"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_29"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01317"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.106"},{"key":"ref26","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28098"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","article-title":"Attending to graph transformers","volume":"2024","author":"M\u00fcller","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref41","first-page":"464","article-title":"Selfattention with relative position representations","volume-title":"NAACLHLT","volume":"2","author":"Shaw","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3646122"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1195"},{"key":"ref44","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora","author":"Smith","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref45","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. OpenReview.net"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103721"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01883"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1466"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3442301"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3108974"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01604"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01971"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859944"},{"key":"ref61","article-title":"Graph transformer networks","volume":"32","author":"Yun","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref64","article-title":"gddim: Generalized denoising diffusion implicit models","author":"Zhang","year":"2023","journal-title":"ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023. OpenReview.net"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00285"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01978"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_12"}],"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\/11446223.pdf?arnumber=11446223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:40Z","timestamp":1777613620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01444","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}