{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:43:27Z","timestamp":1778172207799,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation of China","award":["62176134"],"award-info":[{"award-number":["62176134"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611889","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"1809-1820","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Improving Scene Graph Generation with Superpixel-Based Interaction Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7832-8848","authenticated-orcid":false,"given":"Jingyi","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9530-5218","authenticated-orcid":false,"given":"Can","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Media Lab, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0081-4106","authenticated-orcid":false,"given":"Jinfa","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1646-9183","authenticated-orcid":false,"given":"Botao","family":"Ren","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9970-1023","authenticated-orcid":false,"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3015433"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01005"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475297"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01145"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01515"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548356"},{"key":"e_1_3_2_1_12_1","volume-title":"Scene Graph Reasoning for Visual Question Answering. CoRR","author":"Hildebrandt Marcel","year":"2020","unstructured":"Marcel Hildebrandt, Hang Li, Rajat Koner, Volker Tresp, and Stephan G\u00fcnnemann. 2020. Scene Graph Reasoning for Visual Question Answering. CoRR, Vol. abs\/2007.01072 (2020)."},{"key":"e_1_3_2_1_13_1","first-page":"30291","article-title":"Expectation-maximization contrastive learning for compact video-and-language representations","volume":"35","author":"Jin Peng","year":"2022","unstructured":"Peng Jin, Jinfa Huang, Fenglin Liu, Xian Wu, Shen Ge, Guoli Song, David Clifton, and Jie Chen. 2022. Expectation-maximization contrastive learning for compact video-and-language representations. Advances in Neural Information Processing Systems, Vol. 35 (2022), 30291--30306.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"e_1_3_2_1_15_1","volume-title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment. In International Conference on International Joint Conferences on Artificial Intelligence.","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Hao Li, Zesen Cheng, Jinfa Huang, Zhennan Wang, Li Yuan, Chang Liu, and Jie Chen. 2023 c. Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment. In International Conference on International Joint Conferences on Artificial Intelligence."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00610"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01790"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6783"},{"key":"e_1_3_2_1_19_1","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 A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision Vol. 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00609"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276570"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_20"},{"key":"e_1_3_2_1_24_1","first-page":"635","article-title":"Shadow knowledge distillation: Bridging offline and online knowledge transfer","volume":"35","author":"Li Lujun","year":"2022","unstructured":"Lujun Li and Zhe Jin. 2022. Shadow knowledge distillation: Bridging offline and online knowledge transfer. Advances in Neural Information Processing Systems, Vol. 35 (2022), 635--649.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548164"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099369"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1356--1363","author":"Li Zhengqin","year":"2015","unstructured":"Zhengqin Li and Jiansheng Chen. 2015. Superpixel segmentation using Linear Spectral Clustering. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1356--1363."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning.","author":"Liang James","year":"2023","unstructured":"James Liang, Tianfei Zhou, Dongfang Liu, and Wenguan Wang. 2023. CLUSTSEG: Clustering for Universal Segmentation. In Proceedings of the 40th International Conference on Machine Learning."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475712"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"e_1_3_2_1_34_1","volume-title":"Importance Weighted Structure Learning for Scene Graph Generation. arXiv preprint arXiv:2205.07017","author":"Liu Daqi","year":"2022","unstructured":"Daqi Liu, Miroslaw Bober, and Josef Kittler. 2022. Importance Weighted Structure Learning for Scene Graph Generation. arXiv preprint arXiv:2205.07017 (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"e_1_3_2_1_36_1","volume-title":"NORM: Knowledge Distillation via N-to-One Representation Matching. arXiv preprint arXiv:2305.13803","author":"Liu Xiaolong","year":"2023","unstructured":"Xiaolong Liu, Lujun Li, Chao Li, and Anbang Yao. 2023. NORM: Knowledge Distillation via N-to-One Representation Matching. arXiv preprint arXiv:2305.13803 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Ma Xu","year":"2023","unstructured":"Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, and Yun Fu. 2023. Image as Set of Points. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02184"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20108"},{"key":"e_1_3_2_1_40_1","unstructured":"Shaoqing Ren Kaiming He Ross B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In NIPS. 91--99."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238308"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475326"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475545"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Hongshuo Tian Ning Xu An-An Liu and Yongdong Zhang. 2020. Part-Aware Interactive Learning for Scene Graph Generation. In ACM Multimedia. ACM 3155--3163.","DOI":"10.1145\/3394171.3413501"},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems 30. Curran Associates","author":"Vaswani Ashish","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30. Curran Associates, Inc., 5998--6008."},{"key":"e_1_3_2_1_49_1","volume-title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs. In IEEE International Conference on Robotics and Automation (ICRA).","author":"Wang Jingyi","year":"2023","unstructured":"Jingyi Wang, Jinfa Huang, Can Zhang, and Zhidong Deng. 2023. Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs. In IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548324"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00699"},{"key":"e_1_3_2_1_52_1","volume-title":"Unified Perceptual Parsing for Scene Understanding. In European Conference on Computer Vision","volume":"11209","author":"Xiao Tete","year":"2018","unstructured":"Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, and Jian Sun. 2018. Unified Perceptual Parsing for Scene Understanding. In European Conference on Computer Vision, Vol. 11209. 432--448."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_54_1","volume-title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation. In ACM Multimedia. 265--273.","author":"Yan Shaotian","year":"2020","unstructured":"Shaotian Yan, Chen Shen, Zhongming Jin, Jianqiang Huang, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua. 2020. PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation. In ACM Multimedia. 265--273."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3119892"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01398"},{"key":"e_1_3_2_1_57_1","volume-title":"ECCV (1) (Lecture Notes in Computer Science","author":"Yang Jianwei","unstructured":"Jianwei Yang, Jiasen Lu, Stefan Lee, Dhruv Batra, and Devi Parikh. 2018. Graph R-CNN for Scene Graph Generation. In ECCV (1) (Lecture Notes in Computer Science, Vol. 11205). 690--706."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"e_1_3_2_1_59_1","volume-title":"Auto-Encoding Scene Graphs for Image Captioning. In 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10685--10694","author":"Yang Xu","year":"2019","unstructured":"Xu Yang, Kaihua Tang, Hanwang Zhang, and Jianfei Cai. 2019. Auto-Encoding Scene Graphs for Image Captioning. In 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10685--10694."},{"key":"e_1_3_2_1_60_1","volume-title":"ECCV (23) (Lecture Notes in Computer Science","author":"Zareian Alireza","unstructured":"Alireza Zareian, Svebor Karaman, and Shih-Fu Chang. 2020. Bridging Knowledge Graphs to Generate Scene Graphs. In ECCV (23) (Lecture Notes in Computer Science, Vol. 12368). 606--623."},{"key":"e_1_3_2_1_61_1","volume-title":"Neural Motifs: Scene Graph Parsing With Global Context. In 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5831--5840","author":"Zellers Rowan","year":"2018","unstructured":"Rowan Zellers, Mark Yatskar, Sam Thomson, and Yejin Choi. 2018. Neural Motifs: Scene Graph Parsing With Global Context. In 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5831--5840."},{"key":"e_1_3_2_1_62_1","volume-title":"Fine-Grained Scene Graph Generation with Data Transfer. In European Conference on Computer Vision. 409--424","author":"Zhang Ao","year":"2022","unstructured":"Ao Zhang, Yuan Yao, Qianyu Chen, Wei Ji, Zhiyuan Liu, Maosong Sun, and Tat-Seng Chua. 2022b. Fine-Grained Scene Graph Generation with Data Transfer. In European Conference on Computer Vision. 409--424."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350876"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00285"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02182"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611889","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:03:31Z","timestamp":1755821011000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":68,"alternative-id":["10.1145\/3581783.3611889","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611889","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}