{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:09:46Z","timestamp":1770354586225,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Peng Cheng Laboratory Research Project","award":["No. PCL2023A08"],"award-info":[{"award-number":["No. PCL2023A08"]}]},{"name":"Natural Science Foundation of China","award":["Nos. U21B2025."],"award-info":[{"award-number":["Nos. U21B2025."]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680818","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3037-3046","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Calibration for Long-tailed Scene Graph Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8151-4204","authenticated-orcid":false,"given":"Xuhan","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences & Pengcheng Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-9515","authenticated-orcid":false,"given":"Yifei","family":"Xing","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Pengcheng Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2595","authenticated-orcid":false,"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6110-4036","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8564-0346","authenticated-orcid":false,"given":"Xiangyuan","family":"Lan","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157567"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01005"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Chao Chen Yibing Zhan Baosheng Yu Liu Liu Yong Luo and Bo Du. 2022. Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation. In AAAI.","DOI":"10.1609\/aaai.v36i1.19896"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612031"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475297"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_2_1_7_1","first-page":"1","article-title":"The comparison and evaluation of forecasters","volume":"32","author":"DeGroot Morris H","year":"1983","unstructured":"Morris H DeGroot and Stephen E Fienberg. 1983. The comparison and evaluation of forecasters. Journal of the Royal Statistical Society: Series D (The Statistician), Vol. 32, 1--2 (1983), 12--22.","journal-title":"Journal of the Royal Statistical Society: Series D (The Statistician)"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00681"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00353"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384457"},{"key":"e_1_3_2_1_13_1","unstructured":"Moritz Fuchs Camila Gonzalez and Anirban Mukhopadhyay. 2021. Practical uncertainty quantification for brain tumor segmentation. In Medical Imaging with Deep Learning."},{"key":"e_1_3_2_1_14_1","volume-title":"A Comparative Study of Confidence Calibration in Deep Learning: From Computer Vision to Medical Imaging. arXiv preprint arXiv:2206.08833","author":"Gao Riqiang","year":"2022","unstructured":"Riqiang Gao, Thomas Li, Yucheng Tang, Zhoubing Xu, Michael Kammer, Sanja L Antic, Kim Sandler, Fabien Moldonado, Thomas A Lasko, and Bennett Landman. 2022. A Comparative Study of Confidence Calibration in Deep Learning: From Computer Vision to Medical Imaging. arXiv preprint arXiv:2206.08833 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 1321--1330","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. 2017. On calibration of modern neural networks. In International conference on machine learning. PMLR, 1321--1330."},{"key":"e_1_3_2_1_17_1","volume-title":"Piotr Dollar, and Ross Girshick","author":"Gupta Agrim","year":"2019","unstructured":"Agrim Gupta, Piotr Dollar, and Ross Girshick. 2019. Lvis: A dataset for large vocabulary instance segmentation. In CVPR. 5356--5364."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00015"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_21_1","volume-title":"Class-distribution-aware calibration for long-tailed visual recognition. arXiv preprint arXiv:2109.05263","author":"Islam Mobarakol","year":"2021","unstructured":"Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren, and Ben Glocker. 2021. Class-distribution-aware calibration for long-tailed visual recognition. arXiv preprint arXiv:2109.05263 (2021)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00697"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827223"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2991231"},{"key":"e_1_3_2_1_26_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 1 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_27_1","volume-title":"Markus K\u00e4ngsepp, Telmo Silva Filho, Hao Song, and Peter Flach.","author":"Kull Meelis","year":"2019","unstructured":"Meelis Kull, Miquel Perello Nieto, Markus K\u00e4ngsepp, Telmo Silva Filho, Hao Song, and Peter Flach. 2019. Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with dirichlet calibration. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00171"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02306"},{"key":"e_1_3_2_1_30_1","volume-title":"Compositional Feature Augmentation for Unbiased Scene Graph Generation. arXiv preprint arXiv:2308.06712","author":"Li Lin","year":"2023","unstructured":"Lin Li, Guikun Chen, Jun Xiao, Yi Yang, Chunping Wang, and Long Chen. 2023. Compositional Feature Augmentation for Unbiased Scene Graph Generation. arXiv preprint arXiv:2308.06712 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2207.13316"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"R. Li S. Zhang B. Wan and X. He. 2021. Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"e_1_3_2_1_34_1","volume-title":"PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation. In CVPR.","author":"Li Wei","year":"2022","unstructured":"Wei Li, Haiwei Zhang, Qijie Bai, Guoqing Zhao, Ning Jiang, and Xiaojie Yuan. 2022. PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation. In CVPR."},{"key":"e_1_3_2_1_35_1","unstructured":"Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He and Piotr Dollar. 2017. Focal Loss for Dense Object Detection."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01885"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings, Part I 14","author":"Lu Cewu","year":"2016","unstructured":"Cewu Lu, Ranjay Krishna, Michael Bernstein, and Li Fei-Fei. 2016. Visual relationship detection with language priors. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part I 14. Springer, 852--869."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01886"},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. PMLR, 7235--7245","author":"Ma Xingchen","year":"2021","unstructured":"Xingchen Ma and Matthew B Blaschko. 2021. Meta-cal: Well-controlled post-hoc calibration by ranking. In International Conference on Machine Learning. PMLR, 7235--7245."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3006437"},{"key":"e_1_3_2_1_41_1","volume-title":"Himanshu Jain, Andreas Veit, and Sanjiv Kumar.","author":"Menon Aditya Krishna","year":"2020","unstructured":"Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, and Sanjiv Kumar. 2020. Long-tail learning via logit adjustment. arXiv preprint arXiv:2007.07314 (2020)."},{"key":"e_1_3_2_1_42_1","volume-title":"Daniel Coelho de Castro","author":"Monteiro Miguel","year":"2020","unstructured":"Miguel Monteiro, Lo\"ic Le Folgoc, Daniel Coelho de Castro, Nick Pawlowski, Bernardo Marques, Konstantinos Kamnitsas, Mark van der Wilk, and Ben Glocker. 2020. Stochastic segmentation networks: Modelling spatially correlated aleatoric uncertainty. Advances in neural information processing systems, Vol. 33 (2020), 12756--12767."},{"key":"e_1_3_2_1_43_1","first-page":"15288","article-title":"Calibrating deep neural networks using focal loss","volume":"33","author":"Mukhoti Jishnu","year":"2020","unstructured":"Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip Torr, and Puneet Dokania. 2020. Calibrating deep neural networks using focal loss. Advances in Neural Information Processing Systems, Vol. 33 (2020), 15288--15299.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","first-page":"38706","article-title":"Towards improving calibration in object detection under domain shift","volume":"35","author":"Munir Muhammad Akhtar","year":"2022","unstructured":"Muhammad Akhtar Munir, Muhammad Haris Khan, M Sarfraz, and Mohsen Ali. 2022. Towards improving calibration in object detection under domain shift. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38706--38718.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102430"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01890"},{"key":"e_1_3_2_1_47_1","volume-title":"Single-Stage Bimodal Transformer for Scene Graph Generation in OR. arXiv preprint arXiv:2402.14461","author":"Pei Jialun","year":"2024","unstructured":"Jialun Pei, Diandian Guo, Jingyang Zhang, Manxi Lin, Yueming Jin, and Pheng-Ann Heng. 2024. S^ 2Former-OR: Single-Stage Bimodal Transformer for Scene Graph Generation in OR. arXiv preprint arXiv:2402.14461 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_49_1","volume-title":"Belief Scene Graphs: Expanding Partial Scenes with Objects through Computation of Expectation. arXiv preprint arXiv:2402.03840","author":"Saucedo Mario AV","year":"2024","unstructured":"Mario AV Saucedo, Akash Patel, Akshit Saradagi, Christoforos Kanellakis, and George Nikolakopoulos. 2024. Belief Scene Graphs: Expanding Partial Scenes with Objects through Computation of Expectation. arXiv preprint arXiv:2402.03840 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Kaihua Tang Yulei Niu Jianqiang Huang Jiaxin Shi and Hanwang Zhang. 2020. Unbiased Scene Graph Generation From Biased Training. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Kaihua Tang Hanwang Zhang Baoyuan Wu Wenhan Luo and Wei Liu. 2019. Learning to Compose Dynamic Tree Structures for Visual Contexts. In CVPR.","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01883"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00999"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02265"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00732"},{"key":"e_1_3_2_1_57_1","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yudong Chen, and Wenwu Zhu. 2021. A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4555--4576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00855"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Jianwei Yang Jiasen Lu Stefan Lee Dhruv Batra and Devi Parikh. 2018. Graph r-cnn for scene graph generation. In ECCV. 670--685.","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"e_1_3_2_1_60_1","volume-title":"Identifying and compensating for feature deviation in imbalanced deep learning. arXiv preprint arXiv:2001.01385","author":"Ye Han-Jia","year":"2020","unstructured":"Han-Jia Ye, Hong-You Chen, De-Chuan Zhan, and Wei-Lun Chao. 2020. Identifying and compensating for feature deviation in imbalanced deep learning. arXiv preprint arXiv:2001.01385 (2020)."},{"key":"e_1_3_2_1_61_1","unstructured":"Jing Yu Yuan Chai Yujing Wang Yue Hu and Qi Wu. 2021. CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation. In IJCAI."},{"key":"e_1_3_2_1_62_1","volume-title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World. arXiv preprint arXiv:2303.13233","author":"Yu Qifan","year":"2023","unstructured":"Qifan Yu, Juncheng Li, Yu Wu, Siliang Tang, Wei Ji, and Yueting Zhuang. 2023. Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World. arXiv preprint arXiv:2303.13233 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3074854"},{"key":"e_1_3_2_1_64_1","volume-title":"Neural Motifs: Scene Graph Parsing With Global Context. In CVPR.","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 CVPR."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Ao Zhang Yuan Yao Qianyu Chen Wei Ji Zhiyuan Liu Maosong Sun and Tat-Seng Chua. 2022. Fine-Grained Scene Graph Generation with Data Transfer. In ECCV.","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02182"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"e_1_3_2_1_68_1","volume-title":"Tin Lun Lam, and Yangsheng Xu","author":"Zhou Liguang","year":"2022","unstructured":"Liguang Zhou, Junjie Hu, Yuhongze Zhou, Tin Lun Lam, and Yangsheng Xu. 2022. Peer learning for unbiased scene graph generation. arXiv preprint arXiv:2301.00146 (2022)."},{"key":"e_1_3_2_1_69_1","volume-title":"Tin Lun Lam, and Yangsheng Xu","author":"Zhou Liguang","year":"2022","unstructured":"Liguang Zhou, Yuhongze Zhou, Tin Lun Lam, and Yangsheng Xu. 2022. Context-aware mixture-of-experts for unbiased scene graph generation. arXiv preprint arXiv:2208.07109 (2022)."},{"key":"e_1_3_2_1_70_1","volume-title":"Syed Afaq Ali Shah, et al","author":"Zhu Guangming","year":"2022","unstructured":"Guangming Zhu, Liang Zhang, Youliang Jiang, Yixuan Dang, Haoran Hou, Peiyi Shen, Mingtao Feng, Xia Zhao, Qiguang Miao, Syed Afaq Ali Shah, et al. 2022. Scene graph generation: A comprehensive survey. arXiv preprint arXiv:2201.00443 (2022)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.07.007"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107977"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680818","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":72,"alternative-id":["10.1145\/3664647.3680818","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680818","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}