{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T03:01:39Z","timestamp":1780542099752,"version":"3.54.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["788506"],"award-info":[{"award-number":["788506"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Current methods that generate a scene graph of a given image create an overdense graph regarding the number of objects and relationships found in the image, making the graph less effective in describing what is relevant in the image and, consequently, in downstream tasks such as cross-modal retrieval and mining. In this work, we propose a novel method that generates a scene graph that reflects what humans find important when describing an image. During training, our scene generation method is guided by human-drafted captions describing the images, which we assume will focus on essential scene elements. This guidance is realized by properly designed loss functions. During inference, scene graphs are generated solely from images. We evaluate the resulting scene graphs by comparing them with the ground-truth scene graphs of Visual Genome that are created by humans. Evaluation is done with recall- and precision-oriented metrics and graph edit distances. In the first set of experiments, we benchmark existing scene graph generation models, then we add the newly proposed loss functions leading to improved performance, especially in terms of the graph edit distance. Extra experiments show that the correct recognition of unimportant background objects and their relationships is crucial when generating human-like scene graphs.\n                    <jats:italic>The codebase is released on github:<\/jats:italic>\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/VSJMilewski\/relevance_graphs\" ext-link-type=\"uri\">https:\/\/github.com\/VSJMilewski\/relevance_graphs<\/jats:ext-link>\n                  <\/jats:p>","DOI":"10.1007\/s11042-026-21166-0","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:13:52Z","timestamp":1780539232000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Human-like scene graph generation and evaluation"],"prefix":"10.1007","volume":"85","author":[{"given":"Victor","family":"Milewski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Francine","family":"Moens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9204-0389","authenticated-orcid":false,"given":"Maria Mihaela","family":"Trusca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"21166_CR1","doi-asserted-by":"crossref","unstructured":"Abu-Aisheh Z, Raveaux R, Ramel JY, and Martineau P (2015) An Exact Graph Edit Distance Algorithm for Solving Pattern Recognition Problems. In 4th International Conference on Pattern Recognition Applications and Methods 2015 pages 1\u20139 Lisbon Portugal","DOI":"10.5220\/0005209202710278"},{"key":"21166_CR2","doi-asserted-by":"crossref","unstructured":"Benetatos A, Diomataris M, Pitsikalis V, and Maragos P (2023) Generating salient scene graphs with weak language supervision. In 2023 31st European Signal Processing Conference (EUSIPCO) pages 526\u2013530","DOI":"10.23919\/EUSIPCO58844.2023.10289877"},{"issue":"1","key":"21166_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2021.3137605","volume":"45","author":"X Chang","year":"2023","unstructured":"Chang X, Ren P, Xu P, Li Z, Chen X, Hauptmann A (2023) A comprehensive survey of scene graphs: Generation and application. IEEE Trans Pattern Anal Mach Intell 45(1):1\u201326","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21166_CR4","doi-asserted-by":"crossref","unstructured":"Chattopadhyay A, Sarkar A, Howlader P, and Balasubramanian V.\u00a0N (2018) Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In 2018 IEEE Winter Conference on Applications of Computer Vision pages 839\u2013847. IEEE Computer Society","DOI":"10.1109\/WACV.2018.00097"},{"key":"21166_CR5","doi-asserted-by":"crossref","unstructured":"Cong Y, Yi J, Rosenhahn B, and Yang M.\u00a0Y (2023) SSGVS: semantic scene graph-to-video synthesis. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2023 - Workshops Vancouver BC Canada June 17-24 2023 pages 2555\u20132565. IEEE","DOI":"10.1109\/CVPRW59228.2023.00254"},{"key":"21166_CR6","doi-asserted-by":"crossref","unstructured":"Farshad A, Yeganeh Y, Chi Y, Shen C, Ommer B, and Navab N (2023) Scenegenie: Scene graph guided diffusion models for image synthesis. In IEEE\/CVF International Conference on Computer Vision ICCV 2023 - Workshops Paris France October 2-6 2023 pages 88\u201398. IEEE","DOI":"10.1109\/ICCVW60793.2023.00016"},{"key":"21166_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130496","volume":"648","author":"J Feng","year":"2025","unstructured":"Feng J, Wang L, Xu H, Xu K, Yin B (2025) Ensemble predicate decoding for unbiased scene graph generation. Neurocomputing 648:130496","journal-title":"Neurocomputing"},{"issue":"12","key":"21166_CR8","doi-asserted-by":"publisher","first-page":"8611","DOI":"10.1109\/TCSVT.2022.3193857","volume":"32","author":"X Han","year":"2022","unstructured":"Han X, Dong X, Song X, Gan T, Zhan Y, Yan Y, Nie L (2022) Divide-and-conquer predictor for unbiased scene graph generation. IEEE Trans Circuits Syst Video Technol 32(12):8611\u20138622","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"21166_CR9","doi-asserted-by":"publisher","first-page":"5319","DOI":"10.1109\/TMM.2022.3190135","volume":"25","author":"X Han","year":"2023","unstructured":"Han X, Song X, Dong X, Wei Y, Liu M, Nie L (2023) Dbiased-p: Dual-biased predicate predictor for unbiased scene graph generation. IEEE Trans Multimedia 25:5319\u20135329","journal-title":"IEEE Trans Multimedia"},{"key":"21166_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, and Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"21166_CR11","doi-asserted-by":"crossref","unstructured":"Jiang B, Zhuang Z, Shivakumar SS, Taylor CJ (2025) Enhancing scene graph generation with hierarchical relationships and commonsense knowledge. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV), IEEE, pp 8865\u20138876","DOI":"10.1109\/WACV61041.2025.00861"},{"key":"21166_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107707","volume":"112","author":"J Jiang","year":"2021","unstructured":"Jiang J, He Z, Zhang S, Zhao X, Tan J (2021) Learning to transfer focus of graph neural network for scene graph parsing. Pattern Recogn 112:107707","journal-title":"Pattern Recogn"},{"key":"21166_CR13","unstructured":"Jin Y, Liu B, and Wang J (2023) Video captioning with aggregated features based on dual graphs and gated fusion. arXiv preprint arXiv:2308.06685"},{"key":"21166_CR14","doi-asserted-by":"crossref","unstructured":"Johnson J, Krishna R, Stark M, Li LJ, Shamma D, Bernstein M, and Fei-Fei L (2015) Image retrieval using scene graphs. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3668\u20133678","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"21166_CR15","doi-asserted-by":"crossref","unstructured":"Kim K, Yoon K, Jeon J, In Y, Moon J, Kim D, and Park C (2024) LLM4SGG: Large language models for weakly supervised scene graph generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, pp 28306\u201328316","DOI":"10.1109\/CVPR52733.2024.02674"},{"key":"21166_CR16","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2016","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li LJ, Shamma DA, Bernstein MS, Fei-Fei L (2016) Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int J Comput Vision 123:32\u201373","journal-title":"Int J Comput Vision"},{"key":"21166_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127052","volume":"566","author":"H Li","year":"2024","unstructured":"Li H, Zhu G, Zhang L, Jiang Y, Dang Y, Hou H, Shen P, Zhao X, Shah SAA, Bennamoun M (2024) Scene graph generation: A comprehensive survey. Neurocomputing 566:127052","journal-title":"Neurocomputing"},{"key":"21166_CR18","doi-asserted-by":"crossref","unstructured":"Li J, Wang Y, Guo X, Yang R, and Li W (2024) Leveraging predicate and triplet learning for scene graph generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), pp 28369\u201328379. IEEE","DOI":"10.1109\/CVPR52733.2024.02680"},{"issue":"1","key":"21166_CR19","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1109\/TCSVT.2023.3282349","volume":"34","author":"L Li","year":"2024","unstructured":"Li L, Xiao J, Shi H, Wang W, Shao J, Liu A, Yang Y, Chen L (2024) Label semantic knowledge distillation for unbiased scene graph generation. IEEE Trans Circuits Syst Video Technol 34(1):195\u2013206","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"21166_CR20","unstructured":"Li X, Chen L, Shao J, Xiao S, Zhang S, and Xiao J (2022) Rethinking the evaluation of unbiased scene graph generation. In 33rd British Machine Vision Conference 2022 BMVC 2022 London UK November 21-24 2022, pp 1\u201314. BMVA Press"},{"key":"21166_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108300","volume":"122","author":"B Lin","year":"2022","unstructured":"Lin B, Zhu Y, Liang X (2022) Atom correlation based graph propagation for scene graph generation. Pattern Recogn 122:108300","journal-title":"Pattern Recogn"},{"key":"21166_CR22","doi-asserted-by":"crossref","unstructured":"Lin TY, Dollar P, Girshick R, He K, Hariharan B, and Belongie S (2017) Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"21166_CR23","doi-asserted-by":"crossref","unstructured":"Lin X, Ding C, Zeng J, and Tao D (2020) Gps-net: Graph property sensing network for scene graph generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 3746\u20133753","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"21166_CR24","doi-asserted-by":"crossref","unstructured":"Lu C, Krishna R, Bernstein M, Fei-Fei L (2016) Visual relationship detection with language priors. In: Leibe B Matas J Sebe N Welling M (eds) Computer Vision - ECCV 2016. Cham. Springer International Publishing, pp 852\u2013869","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"21166_CR25","doi-asserted-by":"crossref","unstructured":"Lu F, Wu W, Zheng K, Ma S, Gong B, Liu J, Zhai W, Cao Y, Shen Y, and Zha ZJ (2025) Benchmarking large vision-language models via directed scene graph for comprehensive image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), pp 19618\u201319627. Computer Vision Foundation \/ IEEE","DOI":"10.1109\/CVPR52734.2025.01827"},{"issue":"2","key":"21166_CR26","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1007\/s00530-022-01012-7","volume":"29","author":"X Lu","year":"2023","unstructured":"Lu X, Gao Y (2023) Guide and interact: scene-graph based generation and control of video captions. Multimedia Syst 29(2):797\u2013809","journal-title":"Multimedia Syst"},{"key":"21166_CR27","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H (2008) Introduction to Information Retrieval. Cambridge University Press"},{"key":"21166_CR28","doi-asserted-by":"crossref","unstructured":"Milewski VSJ, Moens MF, Calixto I (2020) Are scene graphs good enough to improve image captioning? In Proceedings of the 1st conference of the asia-pacific chapter of the association for computational linguistics and the 10th international joint conference on natural language processing, pp 504\u2013515","DOI":"10.18653\/v1\/2020.aacl-main.50"},{"key":"21166_CR29","unstructured":"Newell A, Deng J (2017) Pixels to graphs by associative embedding. Adv Neural Inf Process Syst 30"},{"key":"21166_CR30","doi-asserted-by":"crossref","unstructured":"Peyrard M (2019) A simple theoretical model of importance for summarization. In Proceedings of the 57th annual meeting of the association for computational linguistics, Florence Italy. Association for Computational Linguistics, pp 1059\u20131073","DOI":"10.18653\/v1\/P19-1101"},{"key":"21166_CR31","doi-asserted-by":"publisher","first-page":"128245","DOI":"10.1109\/ACCESS.2023.3332098","volume":"11","author":"I Phueaksri","year":"2023","unstructured":"Phueaksri I, Kastner MA, Kawanishi Y, Komamizu T, Ide I (2023) An approach to generate a caption for an image collection using scene graph generation. IEEE Access 11:128245\u2013128260","journal-title":"IEEE Access"},{"key":"21166_CR32","doi-asserted-by":"crossref","unstructured":"Phueaksri I, Kastner MA, Kawanishi Y, Komamizu T, Ide I (2023) Towards captioning an image collection from a combined scene graph representation approach. In: Dang-Nguyen D-T Gurrin C Larson M Smeaton AF Rudinac S Dao M-S Trattner C Chen P (eds) MultiMedia Modeling. Cham. Springer International Publishing, pp 178\u2013190","DOI":"10.1007\/978-3-031-27077-2_14"},{"key":"21166_CR33","doi-asserted-by":"crossref","unstructured":"Phueaksri I, Kastner M.\u00a0A, Kawanishi Y, Komamizu T, and Ide I (2024) Image-collection summarization using scene-graph generation with external knowledge. IEEE Access","DOI":"10.1109\/ACCESS.2024.3360113"},{"key":"21166_CR34","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 3982\u20133992 Hong Kong China. Association for Computational Linguistics","DOI":"10.18653\/v1\/D19-1410"},{"key":"21166_CR35","unstructured":"Ren S, He K, Girshick R, and Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28"},{"key":"21166_CR36","doi-asserted-by":"crossref","unstructured":"Schuster S, Krishna R, Chang A, Fei-Fei L, and Manning C.\u00a0D (2015) Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In Belz A, Coheur L, Ferrari V, Moens MF, Pastra K, and Vuli\u0107 I (eds) proceedings of the fourth workshop on vision and language, Lisbon Portugal. Association for Computational Linguistics, pp 70\u201380","DOI":"10.18653\/v1\/W15-2812"},{"key":"21166_CR37","unstructured":"Shukor M, Couairon G, and Cord M (2022) Efficient vision-language pretraining with visual concepts and hierarchical alignment. In 33rd British machine vision conference 2022, BMVA Press, p 353"},{"key":"21166_CR38","unstructured":"Tang K (2020) A scene graph generation codebase in pytorch. https:\/\/github.com\/KaihuaTang\/Scene-Graph-Benchmark.pytorch"},{"key":"21166_CR39","doi-asserted-by":"crossref","unstructured":"Tang K, Niu Y, Huang J, Shi J, and Zhang H (2020) Unbiased scene graph generation from biased training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3716\u20133725","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"21166_CR40","doi-asserted-by":"crossref","unstructured":"Tang K, Zhang H, Wu B, Luo W, and Liu W (2019) Learning to compose dynamic tree structures for visual contexts. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6619\u20136628","DOI":"10.1109\/CVPR.2019.00678"},{"key":"21166_CR41","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A.\u00a0N, Kaiser \u0141, and Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems 30"},{"key":"21166_CR42","doi-asserted-by":"crossref","unstructured":"Wang S, Zhou F, Yang M, Shi L, Tan C (2025) SGG-MVAR: Cross-modal retrieval with scene graph generation and multiview attribute relationship guidance. IEEE Trans Comput Social Syst IEEE","DOI":"10.1109\/TCSS.2024.3524297"},{"key":"21166_CR43","doi-asserted-by":"crossref","unstructured":"Wang W, Wang R, and Chen X (2021) Topic scene graph generation by attention distillation from caption. In Proceedings of the IEEE\/CVF international conference on computer vision, pp 15900\u201315910","DOI":"10.1109\/ICCV48922.2021.01560"},{"key":"21166_CR44","unstructured":"Wang Y, Li Z, Zhang W, Zhang Z, Xie B, Liu X, Zeng W, and Jin X (2024) Scene graph disentanglement and composition for generalizable complex image generation. In advances in neural information processing systems 38 (NeurIPS 2024) Vancouver BC Canada December,pp 10\u201315"},{"key":"21166_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109634","volume":"141","author":"Z Wang","year":"2023","unstructured":"Wang Z, Xu X, Luo Y, Wang G, Yang Y (2023) Hypercomplex context guided interaction modeling for scene graph generation. Pattern Recogn 141:109634","journal-title":"Pattern Recogn"},{"key":"21166_CR46","doi-asserted-by":"crossref","unstructured":"Wu Z, Li H, Chen G, Yu Z, Gu X, and Wang Y (2024) 3D question answering with scene graph reasoning. In Proceedings of the 32nd ACM International Conference on Multimedia (MM 2024), pp 1370\u20131378. ACM","DOI":"10.1145\/3664647.3681517"},{"key":"21166_CR47","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Dollar P, Tu Z, and He K (2017) Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"key":"21166_CR48","doi-asserted-by":"crossref","unstructured":"Xu D, Zhu Y, Choy C.\u00a0B, and Fei-Fei L (2017) Scene graph generation by iterative message passing. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5410\u20135419","DOI":"10.1109\/CVPR.2017.330"},{"key":"21166_CR49","doi-asserted-by":"crossref","unstructured":"Yang J, Lu J, Lee S, Batra D, and Parikh D (2018) Graph r-cnn for scene graph generation. In Proceedings of the European Conference on Computer Vision (ECCV), pp 670\u2013685","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"21166_CR50","doi-asserted-by":"crossref","unstructured":"Yang X, Liu Y, and Wang X (2022) Reformer: The relational transformer for image captioning. In Proceedings of the 30th ACM International Conference on Multimedia MM \u201922 page 5398\u20135406 New York NY USA. Association for Computing Machinery","DOI":"10.1145\/3503161.3548409"},{"key":"21166_CR51","doi-asserted-by":"crossref","unstructured":"Yang X, Peng J, Wang Z, Xu H, Ye Q, Li C, Huang S, Huang F, Li Z, and Zhang Y (2023) Transforming visual scene graphs to image captions. In Rogers A, Boyd-Graber J, and Okazaki N, editors Proceedings of the 61st annual meeting of the association for computational linguistics (Volume 1: Long Papers), Toronto Canada. Association for Computational Linguistics, pp 12427\u201312440","DOI":"10.18653\/v1\/2023.acl-long.694"},{"key":"21166_CR52","doi-asserted-by":"crossref","unstructured":"Yoon K, Kim K, Moon J, and Park C (2023) Unbiased heterogeneous scene graph generation with relation-aware message passing neural network. In Thirty-Seventh AAAI Conference on Artificial Intelligence AAAI 2023 35th conference on innovative applications of artificial intelligence IAAI 2023 13th symposium on educational advances in artificial intelligence EAAI 2023 Washington DC USA February 7-14 2023, AAAI Press, pp 3285\u20133294","DOI":"10.1609\/aaai.v37i3.25435"},{"key":"21166_CR53","doi-asserted-by":"crossref","unstructured":"Yu J, Chai Y, Wang Y, Hu Y, and Wu Q (2021) Cogtree: Cognition tree loss for unbiased scene graph generation. In Zhou ZH, editor Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence IJCAI-21, International Joint Conferences on Artificial Intelligence Organization. Main Track, pp 1274\u20131280","DOI":"10.24963\/ijcai.2021\/176"},{"key":"21166_CR54","doi-asserted-by":"crossref","unstructured":"Zellers R, Yatskar M, Thomson S, and Choi Y (2018) Neural motifs: Scene graph parsing with global context. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5831\u20135840","DOI":"10.1109\/CVPR.2018.00611"},{"key":"21166_CR55","doi-asserted-by":"crossref","unstructured":"Zhang A, Yao Y, Chen Q, Ji W, Liu Z, Sun M, and Chua TS (2022) Fine-grained scene graph generation with data transfer. In ECCV page 409\u2013424","DOI":"10.1007\/978-3-031-19812-0_24"},{"key":"21166_CR56","doi-asserted-by":"crossref","unstructured":"Zhang C, Huang C, Li Y, Zhang X, Ye Y, and Zhang C (2022) Look twice as much as you say: Scene graph contrastive learning for self-supervised image caption generation. In Proceedings of the 31st ACM international conference on information & knowledge management CIKM \u201922 page 2519\u20132528 New York NY USA. Association for Computing Machinery","DOI":"10.1145\/3511808.3557382"},{"key":"21166_CR57","doi-asserted-by":"crossref","unstructured":"Zhang J, Elhoseiny M, Cohen S, Chang W, and Elgammal A (2017) Relationship proposal networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 5678\u20135686","DOI":"10.1109\/CVPR.2017.555"},{"key":"21166_CR58","doi-asserted-by":"crossref","unstructured":"Zhang Y, Pan Y, Yao T, Huang R, Mei T, and Chen CW (2023) Learning to generate language-supervised and open-vocabulary scene graph using pre-trained visual-semantic space. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 2915\u20132924","DOI":"10.1109\/CVPR52729.2023.00285"},{"key":"21166_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110221","volume":"149","author":"M Zhao","year":"2024","unstructured":"Zhao M, Kong Y, Zhang L, Yin B (2024) Class correlation correction for unbiased scene graph generation. Pattern Recogn 149:110221","journal-title":"Pattern Recogn"},{"key":"21166_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108367","volume":"123","author":"H Zhou","year":"2022","unstructured":"Zhou H, Yang Y, Luo T, Zhang J, Li S (2022) A unified deep sparse graph attention network for scene graph generation. Pattern Recogn 123:108367","journal-title":"Pattern Recogn"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21166-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21166-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21166-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:14:38Z","timestamp":1780539278000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21166-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":60,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["21166"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21166-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"assertion":[{"value":"18 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"552"}}