{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T05:17:14Z","timestamp":1784956634843,"version":"3.55.0"},"reference-count":63,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>Scene graph generation (SGG) aims to perceive objects and their relations in images, which can bridge the gap between upstream detection tasks and downstream high-level visual understanding tasks. For SGG models, over-fitting head predicates can lead to bias in the generated scene graph, which has become a consensus. A series of debiasing methods have been proposed to solve the problem. However, some existing debiasing SGG methods have a tendency to over-fit tail predicates, which is another type of bias. In order to eliminate the one-way over-fitting of head or tail predicates, this article proposes a balanced relation prediction (BRP) module which is model-agnostic and compatible with existing re-balancing methods. Moreover, because the relation prediction is based on object feature representation, this article proposes a scene adaptive context fusion (SACF) module to refine the object feature representation. Specifically, SACF models the context based on a chain structure, where the order of objects in the chain structure is adaptively arranged according to the scene content, achieving visual information fusion that adapts to the scene where the objects are located. Experiments on VG and GQA datasets show that the proposed method achieves competitive results on the comprehensive metric\u00a0of R@K and mR@K.<\/jats:p>","DOI":"10.1145\/3708350","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T12:45:31Z","timestamp":1734525931000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Scene Adaptive Context Modeling and Balanced Relation Prediction for Scene Graph Generation"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4334-2444","authenticated-orcid":false,"given":"Kai","family":"Xu","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4174-0027","authenticated-orcid":false,"given":"Lichun","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-8303","authenticated-orcid":false,"given":"Shuang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0439-4644","authenticated-orcid":false,"given":"Tong","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-6647","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Benedikt Alkin Maximilian Beck Korbinian P\u00f6ppel Sepp Hochreiter and Johannes Brandstetter. 2024. Vision-LSTM: xLSTM as generic vision backbone. arXiv:2406.04303. Retrieved from https:\/\/arxiv.org\/abs\/2406.04303"},{"key":"e_1_3_2_3_2","first-page":"41","volume-title":"Proc. ICML","author":"Bengio Yoshua","year":"2009","unstructured":"Yoshua Bengio, J\u00e9r\u00f4me Louradour, Ronan Collobert, and Jason Weston. 2009. Curriculum learning. In Proc. ICML, 41\u201348."},{"key":"e_1_3_2_4_2","first-page":"10429","volume-title":"Proc. CVPR","author":"Biswas Bashirul Azam","year":"2023","unstructured":"Bashirul Azam Biswas and Qiang Ji. 2023. Probabilistic debiasing of scene graphs. In Proc. CVPR, 10429\u201310438."},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1609\/aaai.v36i1.19896","article-title":"Resistance training using prior bias: Toward unbiased scene graph generation","volume":"36","author":"Chen Chao","year":"2022","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 Proc. AAAI 36 (2022), 212\u2013220.","journal-title":"Proc. AAAI"},{"key":"e_1_3_2_6_2","first-page":"19830","volume-title":"Proc. ICCV","author":"Chen Shoufa","year":"2023","unstructured":"Shoufa Chen, Peize Sun, Yibing Song, and Ping Luo. 2023. Diffusiondet: Diffusion model for object detection. In Proc. ICCV, 19830\u201319843."},{"key":"e_1_3_2_7_2","first-page":"6163","volume-title":"Proc. CVPR","author":"Chen Tianshui","year":"2019","unstructured":"Tianshui Chen, Weihao Yu, Riquan Chen, and Liang Lin. 2019. Knowledge-embedded routing network for scene graph generation. In Proc. CVPR, 6163\u20136171."},{"key":"e_1_3_2_8_2","first-page":"4838","volume-title":"Proc. ACM \u2019MM","author":"Chen Zhiqing","year":"2023","unstructured":"Zhiqing Chen, Yawei Luo, Jian Shao, Yi Yang, Chunping Wang, Lei Chen, and Jun Xiao. 2023. Dark knowledge balance learning for unbiased scene graph generation. In Proc. ACM \u2019MM, 4838\u20134847."},{"key":"e_1_3_2_9_2","first-page":"1581","volume-title":"Proc. ACM\u2019MM","author":"Chiou Meng-Jiun","year":"2021","unstructured":"Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, and Jiashi Feng. 2021. Recovering the unbiased scene graphs from the biased ones. In Proc. ACM\u2019MM, 1581\u20131590."},{"key":"e_1_3_2_10_2","first-page":"9268","volume-title":"Proc. CVPR","author":"Cui Yin","year":"2019","unstructured":"Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. 2019. Class-balanced loss based on effective number of samples. In Proc. CVPR, 9268\u20139277."},{"key":"e_1_3_2_11_2","first-page":"15404","volume-title":"Proc. CVPR","author":"Desai Alakh","year":"2021","unstructured":"Alakh Desai, Tz-Ying Wu, Subarna Tripathi, and Nuno Vasconcelos. 2021. Learning of visual relations: The devil is in the tails. In Proc. CVPR, 15404\u201315413."},{"key":"e_1_3_2_12_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. Retrieved from https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_13_2","first-page":"2150","volume-title":"Proc. CVPR","author":"Dhingra Naina","year":"2021","unstructured":"Naina Dhingra, Florian Ritter, and Andreas Kunz. 2021. BGT-Net: Bidirectional GRU transformer network for scene graph generation. In Proc. CVPR, 2150\u20132159."},{"key":"e_1_3_2_14_2","first-page":"19427","volume-title":"Proc. CVPR","author":"Dong Xingning","year":"2022","unstructured":"Xingning Dong, Tian Gan, Xuemeng Song, Jianlong Wu, Yuan Cheng, and Liqiang Nie. 2022. Stacked hybrid-attention and group collaborative learning for unbiased scene graph generation. In Proc. CVPR, 19427\u201319436."},{"key":"e_1_3_2_15_2","first-page":"1","volume-title":"Proc. CACS","author":"Er Meng Joo","year":"2017","unstructured":"Meng Joo Er, Rajasekar Venkatesan, Ning Wang, and Chiang-Ju Chien. 2017. Progressive learning strategies for multi-class classification. In Proc. CACS. IEEE, 1\u20136."},{"issue":"3","key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1111\/coin.12202","article-title":"A hierarchical recurrent approach to predict scene graphs from a visual-attention-oriented perspective","volume":"35","author":"Gao Wenjing","year":"2019","unstructured":"Wenjing Gao, Yonghua Zhu, Wenjun Zhang, Ke Zhang, and Honghao Gao. 2019. A hierarchical recurrent approach to predict scene graphs from a visual-attention-oriented perspective. Comput. Intell. 35, 3 (2019), 496\u2013516.","journal-title":"Comput. Intell"},{"key":"e_1_3_2_17_2","first-page":"1735","volume-title":"Neural Computat.","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fargen Schmidhuber. 1997. Long short-term memory. Neural Computat. 9, 8 (1997), 1735\u20131780."},{"key":"e_1_3_2_18_2","first-page":"16383","volume-title":"Proc. ICCV","author":"Guo Yuyu","year":"2021","unstructured":"Yuyu Guo, Lianli Gao, Xuanhan Wang, Yuxuan Hu, Xing Xu, Xu Lu, Heng Tao Shen, and Jingkuan Song. 2021. From general to specific: Informative scene graph generation via balance adjustment. In Proc. ICCV, 16383\u201316392."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3190135"},{"key":"e_1_3_2_20_2","first-page":"6700","volume-title":"Proc. CVPR","author":"Hudson Drew A.","year":"2019","unstructured":"Drew A. Hudson and Christopher D. Manning. 2019. GQA: A new dataset for real-world visual reasoning and compositional question answering. In Proc. CVPR, 6700\u20136709."},{"key":"e_1_3_2_21_2","first-page":"18664","volume-title":"Proc. CVPR","author":"Jung Deunsol","year":"2023","unstructured":"Deunsol Jung, Sanghyun Kim, Won Hwa Kim, and Minsu Cho. 2023. Devil\u2019s on the edges: Selective quad attention for scene graph generation. In Proc. CVPR, 18664\u201318674."},{"key":"e_1_3_2_22_2","volume-title":"Proc. ICLR","author":"Kim Kibum","year":"2024","unstructured":"Kibum Kim, Kanghoon Yoon, Yeonjun In, Jinyoung Moon, Donghyun Kim, and Chanyoung Park. 2024. Adaptive self-training framework for fine-grained scene graph generation. In Proc. ICLR."},{"issue":"1","key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna Ranjay","year":"2017","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. Int. J. Computer Vis. 123, 1 (2017), 32\u201373.","journal-title":"Int. J. Computer Vis"},{"issue":"1","key":"e_1_3_2_24_2","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"Kuhn Harold W.","year":"1955","unstructured":"Harold W. Kuhn. 1955. The Hungarian method for the assignment problem. Nav. Res. Logist. 2, 1\u20132 (1955), 83\u201397.","journal-title":"Nav. Res. Logist"},{"key":"e_1_3_2_25_2","first-page":"1189","volume-title":"Proc. NIPS","volume":"1","author":"Kumar M.","year":"2010","unstructured":"M. Kumar, Benjamin Packer, and Daphne Koller. 2010. Self-paced learning for latent variable models. In Proc. NIPS, Vol. 1, 1189\u20131197."},{"issue":"1","key":"e_1_3_2_26_2","first-page":"1","article-title":"Zero-shot scene graph generation via triplet calibration and reduction","volume":"20","author":"Li Jiankai","year":"2023","unstructured":"Jiankai Li, Yunhong Wang, and Weixin Li. 2023. Zero-shot scene graph generation via triplet calibration and reduction. ACM Trans. Multimedia Comput. Commun. Appl. 20, 1 (Aug 2023), Article 5, pages 1\u201321.","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl"},{"key":"e_1_3_2_27_2","first-page":"21685","volume-title":"Proc. ICCV","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. In Proc. ICCV, 21685\u201321695."},{"key":"e_1_3_2_28_2","first-page":"18869","volume-title":"Proc. CVPR","author":"Li Lin","year":"2022","unstructured":"Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, and Jun Xiao. 2022. The devil is in the labels: Noisy label correction for robust scene graph generation. In Proc. CVPR, 18869\u201318878."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3282349"},{"key":"e_1_3_2_30_2","first-page":"11109","volume-title":"Proc. CVPR","author":"Li Rongjie","year":"2021","unstructured":"Rongjie Li, Songyang Zhang, Bo Wan, and Xuming He. 2021. Bipartite graph network with adaptive message passing for unbiased scene graph generation. In Proc. CVPR, 11109\u201311119."},{"key":"e_1_3_2_31_2","first-page":"19447","volume-title":"Proc. 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 Proc. CVPR, 19447\u201319456."},{"issue":"8","key":"e_1_3_2_32_2","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1109\/TMM.2019.2896516","article-title":"Know more say less: Image captioning based on scene graphs","volume":"21","author":"Li Xiangyang","year":"2019","unstructured":"Xiangyang Li and Shuqiang Jiang. 2019. Know more say less: Image captioning based on scene graphs. IEEE Trans. Multimedia 21, 8 (2019), 2117\u20132130.","journal-title":"IEEE Trans. Multimedia"},{"key":"e_1_3_2_33_2","first-page":"2117","volume-title":"Proc. CVPR","author":"Lin Tsung-Yi","year":"2017","unstructured":"Tsung-Yi Lin, Piotr Doll\u00e1r, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2017. Feature pyramid networks for object detection. In Proc. CVPR, 2117\u20132125."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"e_1_3_2_35_2","first-page":"852","volume-title":"Proc. ECCV","author":"Lu Cewu","year":"2016","unstructured":"Cewu Lu, Ranjay Krishna, Michael Bernstein, and Li Fei-Fei. 2016. Visual relationship detection with language priors. In Proc. ECCV, 852\u2013869."},{"key":"e_1_3_2_36_2","first-page":"19467","volume-title":"Proc. CVPR","author":"Lyu Xinyu","year":"2022","unstructured":"Xinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao, Hao Huang, Heng Tao Shen, and Jingkuan Song. 2022. Fine-grained predicates learning for scene graph generation. In Proc. CVPR, 19467\u201319475."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298356"},{"key":"e_1_3_2_38_2","first-page":"13296","volume-title":"Proc. ICCV","author":"Min Yukuan","year":"2023","unstructured":"Yukuan Min, Aming Wu, and Cheng Deng. 2023. Environment-invariant curriculum relation learning for fine-grained scene graph generation. In Proc. ICCV, 13296\u201313307."},{"key":"e_1_3_2_39_2","first-page":"1532","volume-title":"Proc. EMNLP","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Proc. EMNLP, 1532\u20131543."},{"key":"e_1_3_2_40_2","first-page":"91","volume-title":"Proc. NIPS","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. In Proc. NIPS, 91\u201399."},{"key":"e_1_3_2_41_2","first-page":"761","volume-title":"Proc. CVPR","author":"Shrivastava Abhinav","year":"2016","unstructured":"Abhinav Shrivastava, Abhinav Gupta, and Ross Girshick. 2016. Training region-based object detectors with online hard example mining. In Proc. CVPR, 761\u2013769."},{"key":"e_1_3_2_42_2","first-page":"3716","volume-title":"Proc. CVPR","author":"Tang Kaihua","year":"2020","unstructured":"Kaihua Tang, Yulei Niu, Jianqiang Huang, Jiaxin Shi, and Hanwang Zhang. 2020. Unbiased scene graph generation from biased training. In Proc. CVPR, 3716\u20133725."},{"key":"e_1_3_2_43_2","first-page":"6619","volume-title":"Proc. CVPR","author":"Tang Kaihua","year":"2019","unstructured":"Kaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, and Wei Liu. 2019. Learning to compose dynamic tree structures for visual contexts. In Proc. CVPR, 6619\u20136628."},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","first-page":"4926","DOI":"10.1109\/TPAMI.2024.3365104","article-title":"Smart: Syntax-calibrated multi-aspect relation transformer for change captioning","volume":"46","author":"Tu Yunbin","year":"2024","unstructured":"Yunbin Tu, Liang Li, Li Su, Zheng-Jun Zha, and Qingming Huang. 2024. Smart: Syntax-calibrated multi-aspect relation transformer for change captioning. IEEE Trans. Pattern Anal. Mach. Intell. 46 (2024), 4926\u20134943.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3226328"},{"key":"e_1_3_2_46_2","unstructured":"Tzu-Jui Julius Wang Selen Pehlivan and Jorma Laaksonen. 2020. Tackling the unannotated: Scene graph generation with bias-reduced models. arXiv:2008.07832. Retrieved from https:\/\/arxiv.org\/abs\/2008.07832"},{"key":"e_1_3_2_47_2","first-page":"15900","volume-title":"Proc. CVPR","author":"Wang Wenbin","year":"2021","unstructured":"Wenbin Wang, Ruiping Wang, and Xilin Chen. 2021. Topic scene graph generation by attention distillation from caption. In Proc. CVPR, 15900\u201315910."},{"key":"e_1_3_2_48_2","first-page":"8188","volume-title":"Proc. CVPR","author":"Wang Wenbin","year":"2019","unstructured":"Wenbin Wang, Ruiping Wang, Shiguang Shan, and Xilin Chen. 2019. Exploring context and visual pattern of relationship for scene graph generation. In Proc. CVPR, 8188\u20138197."},{"key":"e_1_3_2_49_2","first-page":"222","volume-title":"Proc. ECCV","author":"Wang Wenbin","year":"2020","unstructured":"Wenbin Wang, Ruiping Wang, Shiguang Shan, and Xilin Chen. 2020. Sketching image gist: Human-mimetic hierarchical scene graph generation. In Proc. ECCV, 222\u2013239."},{"issue":"2","key":"e_1_3_2_50_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439734","article-title":"Integrating scene semantic knowledge into image captioning","volume":"17","author":"Wei Haiyang","year":"2021","unstructured":"Haiyang Wei, Zhixin Li, Feicheng Huang, Canlong Zhang, Huifang Ma, and Zhongzhi Shi. 2021. Integrating scene semantic knowledge into image captioning. ACM Trans. Multimedia Comput. Commun. Appl. 17, 2 (May 2021), Article 52, pages 1\u201322.","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl"},{"issue":"6","key":"e_1_3_2_51_2","doi-asserted-by":"crossref","first-page":"2872","DOI":"10.1109\/TIP.2019.2891895","article-title":"Progressive learning for person re-identification with one example","volume":"28","author":"Wu Yu","year":"2019","unstructured":"Yu Wu, Yutian Lin, Xuanyi Dong, Yan Yan, Wei Bian, and Yi Yang. 2019. Progressive learning for person re-identification with one example. IEEE Trans. Image Process. 28, 6 (2019), 2872\u20132881.","journal-title":"IEEE Trans. Image Process"},{"key":"e_1_3_2_52_2","first-page":"5410","volume-title":"Proc. CVPR","author":"Xu Dafni","year":"2017","unstructured":"Dafni Xu, Yuke Zhu, Christopher B. Choy, and Li Fei-Fei. 2017. Scene graph generation by iterative message passing. In Proc. CVPR, 5410\u20135419."},{"key":"e_1_3_2_53_2","first-page":"216","volume-title":"Proc. ICANN","author":"Xu Kai","year":"2023","unstructured":"Kai Xu, Lichun Wang, Shuang Li, Huiyong Zhang, and Baocai Yin. 2023. A balanced relation prediction framework for scene graph generation. In Proc. ICANN, 216\u2013228."},{"key":"e_1_3_2_54_2","first-page":"670","volume-title":"Proc. ECCV","author":"Yang Jianwei","year":"2018","unstructured":"Jianwei Yang, Jiasen Lu, Stefan Lee, Dhruv Batra, and Devi Parikh. 2018. Graph R-CNN for scene graph generation. In Proc. ECCV, 670\u2013685."},{"key":"e_1_3_2_55_2","first-page":"1274","volume-title":"Proc. IJCAI","author":"Yu Jing","year":"2021","unstructured":"Jing Yu, Yuan Chai, Yujing Wang, Yue Hu, and Qi Wu. 2021. CogTree: Cognition tree loss for unbiased scene graph generation. In Proc. IJCAI, 1274\u20131280. DOI: 10.24963\/ijcai.2021\/176"},{"key":"e_1_3_2_56_2","first-page":"606","volume-title":"Proc. ECCV","author":"Zareian Alireza","year":"2020","unstructured":"Alireza Zareian, Svebor Karaman, and Shih-Fu Chang. 2020. Bridging knowledge graphs to generate scene graphs. In Proc. ECCV, 606\u2013623."},{"key":"e_1_3_2_57_2","first-page":"5831","volume-title":"Proc. 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 Proc. CVPR, 5831\u20135840."},{"key":"e_1_3_2_58_2","first-page":"409","volume-title":"Proc. ECCV","author":"Zhang Ao","year":"2022","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 Proc. ECCV, 409\u2013424."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432099"},{"issue":"8","key":"e_1_3_2_60_2","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","article-title":"Stackgan++: Realistic image synthesis with stacked generative adversarial networks","volume":"41","author":"Zhang Han","year":"2019","unstructured":"Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris N. Metaxas. 2019. Stackgan++: Realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41, 8 (2019), 1947\u20131962.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"issue":"1","key":"e_1_3_2_61_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3514041","article-title":"Boosting scene graph generation with visual relation saliency","volume":"19","author":"Zhang Yong","year":"2023","unstructured":"Yong Zhang, Yingwei Pan, Ting Yao, Rui Huang, Tao Mei, and Chang-Wen Chen. 2023. Boosting scene graph generation with visual relation saliency. ACM Trans. Multimedia Comput. Commun. Appl. 19, 1 (2023), 1\u201317.","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297842"},{"key":"e_1_3_2_63_2","first-page":"1","volume-title":"Proc. ICME","author":"Zheng Chaofan","year":"2022","unstructured":"Chaofan Zheng, Xinyu Lyu, Yuyu Guo, Pengpeng Zeng, Jingkuan Song, and Lianli Gao. 2022. Learning to generate scene graph from head to tail. In Proc. ICME. IEEE, 1\u20136."},{"key":"e_1_3_2_64_2","first-page":"9719","volume-title":"Proc. CVPR","author":"Zhou Boyan","year":"2020","unstructured":"Boyan Zhou, Quan Cui, Xiu-Shen Wei, and Zhao-Min Chen. 2020. Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In Proc. CVPR, 9719\u20139728."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708350","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:45Z","timestamp":1750295385000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":63,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3708350"],"URL":"https:\/\/doi.org\/10.1145\/3708350","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,20]]},"assertion":[{"value":"2024-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}