{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:09Z","timestamp":1777865349946,"version":"3.51.4"},"reference-count":45,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFC3305600"],"award-info":[{"award-number":["2023YFC3305600"]}],"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":["62132016"],"award-info":[{"award-number":["62132016"]}],"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\/iccv51701.2025.01556","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16755-16764","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language Interactive Relation Mining for Open-Vocabulary Scene Graph Generation"],"prefix":"10.1109","author":[{"given":"Yukuan","family":"Min","sequence":"first","affiliation":[{"name":"Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muli","family":"Yang","sequence":"additional","affiliation":[{"name":"A*STAR,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aming","family":"Wu","sequence":"additional","affiliation":[{"name":"Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.739"},{"key":"ref3","author":"Bi","year":"2025","journal-title":"Prism: Self-pruning intrinsic selection method for training-free multimodal data selection"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_7"},{"issue":"70","key":"ref6","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref11","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional trans-formers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin"},{"key":"ref13","article-title":"Adaptive self-training framework for fine-grained scene graph generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kim"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref17","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"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01888"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3402143"},{"key":"ref24","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Long-tail learning via logit adjustment","author":"Krishna Menon","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref33","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.273"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485484"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3557578"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref39","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01971"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00285"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref45","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representations","author":"Zhu"}],"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\/11444622.pdf?arnumber=11444622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:09Z","timestamp":1777529949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01556","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}