{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:16:10Z","timestamp":1783145770651,"version":"3.54.6"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2025YJS051"],"award-info":[{"award-number":["2025YJS051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473033,62576028"],"award-info":[{"award-number":["62473033,62576028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L231012"],"award-info":[{"award-number":["L231012"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2022JJ40632"],"award-info":[{"award-number":["2022JJ40632"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/CAA J. Autom. Sinica"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/jas.2026.125786","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:54:22Z","timestamp":1783108462000},"page":"1470-1491","source":"Crossref","is-referenced-by-count":0,"title":["Bimodal Predicate Refinement with Decoupled Entity-Predicate Representations for Scene Graph Generation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9495-5040","authenticated-orcid":false,"given":"Guoqing","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University,State Key Laboratory of Advanced Rail Autonomous Operation, Visual Intellgence +X International Cooperation Joint Laboratory of MOE,Beijing,China,100044"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-6196","authenticated-orcid":false,"given":"Shichao","family":"Kan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University,Hunan,China,410083"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2206-5051","authenticated-orcid":false,"given":"Wanru","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University,State Key Laboratory of Advanced Rail Autonomous Operation, Visual Intellgence +X International Cooperation Joint Laboratory of MOE,Beijing,China,100044"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8408-3816","authenticated-orcid":false,"given":"Yi","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University,State Key Laboratory of Advanced Rail Autonomous Operation, Visual Intellgence +X International Cooperation Joint Laboratory of MOE,Beijing,China,100044"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2965-6196","authenticated-orcid":false,"given":"Yidong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University,State Key Laboratory of Advanced Rail Autonomous Operation, Visual Intellgence +X International Cooperation Joint Laboratory of MOE,Beijing,China,100044"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-9422","authenticated-orcid":false,"given":"Yigang","family":"Cen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University,State Key Laboratory of Advanced Rail Autonomous Operation, Visual Intellgence +X International Cooperation Joint Laboratory of MOE,Beijing,China,100044"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00144"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3195106.3195114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111883"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01568"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111641"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/make5010018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413722"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129525"},{"issue":"86","key":"ref20","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 29th Int. Conf. Neural Information Processing Systems","author":"Ren"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1764"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611847"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02680"},{"key":"ref29","first-page":"75234","article-title":"Noise-guided predicate representation extraction and diffusion-enhanced discretization for scene graph generation","volume-title":"Proc. 42nd Int. Conf. Machine Learning","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3198965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3559995"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3086066"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6783"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0949"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3528464"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6776"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482487"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref40","first-page":"1","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. 5th Int. Conf. Learning Representations","author":"Higgins"},{"key":"ref41","first-page":"2654","article-title":"Disentangling by factorising","volume-title":"Proc. 35th Int. Conf. Machine Learning","author":"Kim"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref43","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Int. Conf. Neural Information Processing Systems","author":"Ho"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Machine Learning","author":"Radford","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193857"},{"key":"ref54","first-page":"1","article-title":"Adaptive self-training framework for fine-grained scene graph generation","volume-title":"Proc. 12th Int. Conf. Learning Representations","author":"Kim"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00610"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02667"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475297"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3190135"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181511"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_16"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01005"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3282349"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239229"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01234"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01515"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01607"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01884"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3224872"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19896"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243306"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282889"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297842"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref80","article-title":"Towards lifelong scene graph generation with knowledge-ware in-context prompt learning","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01886"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01558"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.133"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00124"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref91","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Machine Learning","author":"Li"}],"container-title":["IEEE\/CAA Journal of Automatica Sinica"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570654\/11595007\/11595118.pdf?arnumber=11595118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:21:30Z","timestamp":1783142490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11595118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":91,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jas.2026.125786","relation":{},"ISSN":["2329-9266","2329-9274"],"issn-type":[{"value":"2329-9266","type":"print"},{"value":"2329-9274","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}