{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:57:13Z","timestamp":1781539033167,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810741","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"635-644","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["KG-CPEN: Knowledge-Guided Compositional Prototype Evolution for Unbiased Scene Graph Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5449-1087","authenticated-orcid":false,"given":"Yujun","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8604-8495","authenticated-orcid":false,"given":"Changbo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Data Science and Engineering, East China Normal University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8365-0970","authenticated-orcid":false,"given":"Gaoqi","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859970"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Yuren Cong Michael\u00a0Ying Yang and Bodo Rosenhahn. 2023. Reltr: Relation transformer for scene graph generation. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 9 (2023) 11169\u201311183.","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Nicolas Courty R\u00e9mi Flamary Devis Tuia and Alain Rakotomamonjy. 2016. Optimal transport for domain adaptation. IEEE transactions on pattern analysis and machine intelligence 39 9 (2016) 1853\u20131865.","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_3_2_7_2","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01515"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Xianjing Han Xingning Dong Xuemeng Song Tian Gan Yibing Zhan Yan Yan and Liqiang Nie. 2022. Divide-and-conquer predictor for unbiased scene graph generation. IEEE Transactions on Circuits and Systems for Video Technology 32 12 (2022) 8611\u20138622.","DOI":"10.1109\/TCSVT.2022.3193857"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Xianjing Han Xuemeng Song Xingning Dong Yinwei Wei Meng Liu and Liqiang Nie. 2022. DBiased-P: Dual-biased predicate predictor for unbiased scene graph generation. IEEE Transactions on Multimedia 25 (2022) 5319\u20135329.","DOI":"10.1109\/TMM.2022.3190135"},{"key":"e_1_3_3_2_15_2","unstructured":"Xiaotian Han Jianwei Yang Houdong Hu Lei Zhang Jianfeng Gao and Pengchuan Zhang. 2021. Image scene graph generation (sgg) benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.12604 (2021)."},{"key":"e_1_3_3_2_16_2","unstructured":"Tao He Lianli Gao Jingkuan Song Jianfei Cai and Yuan-Fang Li. 2021. Semantic compositional learning for low-shot scene graph generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.08600 (2021)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Zih-Siou Hung Arun Mallya and Svetlana Lazebnik. 2020. Contextual translation embedding for visual relationship detection and scene graph generation. IEEE transactions on pattern analysis and machine intelligence 43 11 (2020) 3820\u20133832.","DOI":"10.1109\/TPAMI.2020.2992222"},{"key":"e_1_3_3_2_19_2","first-page":"18664","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jung Deunsol","year":"2023","unstructured":"Deunsol Jung, Sanghyun Kim, Won\u00a0Hwa Kim, and Minsu Cho. 2023. Devil\u2019s on the edges: Selective quad attention for scene graph generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18664\u201318674."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01558"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01553"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David\u00a0A Shamma et\u00a0al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 1 (2017) 32\u201373.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00609"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Alexander Kolesnikov et\u00a0al. 2020. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. International journal of computer vision 128 7 (2020) 1956\u20131981.","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01887"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01885"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Daqi Liu Miroslaw Bober and Josef Kittler. 2023. Neural belief propagation for scene graph generation. IEEE transactions on pattern analysis and machine intelligence 45 8 (2023) 10161\u201310172.","DOI":"10.1109\/TPAMI.2023.3243306"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26071"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Jianhao Lv Rong Zhang Xinyu Li Shimin Liu Tianyuan Liu Qi Zhang and Jinsong Bao. 2023. A multimodality scene graph generation approach for robust human\u2013robot collaborative assembly visual relationship representation. IEEE Transactions on Industrial Informatics 20 3 (2023) 3242\u20133251.","DOI":"10.1109\/TII.2023.3303964"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01886"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Xinyu Lyu Lianli Gao Junlin Xie Pengpeng Zeng Yulu Tian Jie Shao and Heng\u00a0Tao Shen. 2025. Multi-Concept Learning for Scene Graph Generation. IEEE Transactions on Image Processing (2025).","DOI":"10.1109\/TIP.2025.3540296"},{"key":"e_1_3_3_2_36_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Leitian Tao Li Mi Nannan Li Xianhang Cheng Yaosi Hu and Zhenzhong Chen. 2022. Predicate correlation learning for scene graph generation. IEEE Transactions on Image Processing 31 (2022) 4173\u20134185.","DOI":"10.1109\/TIP.2022.3181511"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"e_1_3_3_2_43_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00212"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00952"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413722"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"e_1_3_3_2_50_2","unstructured":"Jing Yu Yuan Chai Yujing Wang Yue Hu and Qi Wu. 2020. Cogtree: Cognition tree loss for unbiased scene graph generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.07526 (2020)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"e_1_3_3_2_54_2","volume-title":"Forty-second International Conference on Machine Learning","author":"Zhang Guoqing","unstructured":"Guoqing Zhang, Shichao Kan, Fanghui Zhang, Wanru Xu, Yue Zhang, and Yigang Cen. [n. d.]. Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859940"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00184"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01697"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:36:57Z","timestamp":1781537817000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":58,"alternative-id":["10.1145\/3805622.3810741","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810741","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}