{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:19:31Z","timestamp":1783613971923,"version":"3.55.0"},"reference-count":110,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2017YFB1002101"],"award-info":[{"award-number":["2017YFB1002101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Joint Advanced Research Foundation of China Electronics Technology Group Corporation","award":["6141B08010102"],"award-info":[{"award-number":["6141B08010102"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17594-x","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T06:01:46Z","timestamp":1700114506000},"page":"55471-55508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Graph neural networks for visual question answering: a systematic review"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3137-2398","authenticated-orcid":false,"given":"Abdulganiyu Abdu","family":"Yusuf","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1691-1584","authenticated-orcid":false,"given":"Chong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianling","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9195-4920","authenticated-orcid":false,"given":"Ramadhani","family":"Ally Duma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5360-9326","authenticated-orcid":false,"given":"Mohammed Salah","family":"Abood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2279-3606","authenticated-orcid":false,"given":"Abdulrahman Hamman Adama","family":"Chukkol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"17594_CR1","unstructured":"Xu K, Ba JL, Kiros R, et al (2015) Show, attend and tell: Neural image caption generation with visual attention. 32nd International Conference on Machine Learning, ICML 2015 3:2048\u20132057"},{"key":"17594_CR2","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.patrec.2017.09.008","volume":"98","author":"D Mandal","year":"2017","unstructured":"Mandal D, Biswas S (2017) Query specific re-ranking for improved cross-modal retrieval. Pattern Recognit Lett 98:110\u2013116. https:\/\/doi.org\/10.1016\/j.patrec.2017.09.008","journal-title":"Pattern Recognit Lett"},{"key":"17594_CR3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-016-0966-6","volume":"123","author":"A Agrawal","year":"2017","unstructured":"Agrawal A, Lu J, Antol S et al (2017) VQA: Visual question answering. Int J Comput Vision 123:4\u201331. https:\/\/doi.org\/10.1007\/s11263-016-0966-6","journal-title":"Int J Comput Vision"},{"key":"17594_CR4","doi-asserted-by":"crossref","unstructured":"Yu Z, Yu J, Cui Y et al (2019) Deep Modular Co-attention networks for visual question answering. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 6274\u20136283","DOI":"10.1109\/CVPR.2019.00644"},{"key":"17594_CR5","doi-asserted-by":"crossref","unstructured":"Malinowski M, Rohrbach M, Fritz M (2015) Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images. In: 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, pp 1\u20139","DOI":"10.1109\/ICCV.2015.9"},{"key":"17594_CR6","unstructured":"Kim JH, Lee SW, Kwak D, Heo MO, Kim J, Ha JW, Zhang BT (2016) Multimodal residual learning for visual QA. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp 361\u2013369"},{"key":"17594_CR7","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C et al (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"17594_CR8","doi-asserted-by":"publisher","unstructured":"Cho K, van Merri\u00ebnboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: Encoder\u2013decoder approaches. Proceedings of SSST 2014 - 8th Workshop on Syntax, Semantics and Structure in Statistical Translation 103\u2013111. https:\/\/doi.org\/10.3115\/v1\/w14-4012","DOI":"10.3115\/v1\/w14-4012"},{"key":"17594_CR9","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell 39:1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17594_CR10","doi-asserted-by":"crossref","unstructured":"Shih KJ, Singh S, Hoiem D (2016) Where to look: Focus regions for visual question answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 4613\u20134621","DOI":"10.1109\/CVPR.2016.499"},{"key":"17594_CR11","doi-asserted-by":"crossref","unstructured":"Wu C, Liu J, Wang X, Dong X (2018) Object-difference attention. In: Proceedings of the 26th ACM international conference on Multimedia. ACM, New York, NY, USA, pp 519\u2013527","DOI":"10.1145\/3240508.3240513"},{"key":"17594_CR12","doi-asserted-by":"crossref","unstructured":"Yang Z, He X, Gao J et al (2016) Stacked attention networks for image question answering. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 21\u201329","DOI":"10.1109\/CVPR.2016.10"},{"key":"17594_CR13","doi-asserted-by":"crossref","unstructured":"Teney D, Liu L, Van Den Hengel A (2017) Graph-structured representations for visual question answering. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 3233\u20133241","DOI":"10.1109\/CVPR.2017.344"},{"key":"17594_CR14","unstructured":"Norcliffe-Brown W, Vafeias E, Parisot S (2018) Learning conditioned graph structures for interpretable visual question answering. Adv Neural Inf Process Syst 2018-Decem 8334\u20138343"},{"key":"17594_CR15","doi-asserted-by":"publisher","first-page":"7370","DOI":"10.1609\/aaai.v33i01.33017370","volume":"33","author":"L Yao","year":"2019","unstructured":"Yao L, Mao C, Luo Y (2019) Graph convolutional networks for text classification. Proc AAAI Conf Artif Intell 33:7370\u20137377. https:\/\/doi.org\/10.1609\/aaai.v33i01.33017370","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"17594_CR16","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1162\/tacl_a_00049","volume":"5","author":"N Peng","year":"2017","unstructured":"Peng N, Poon H, Quirk C et al (2017) Cross-sentence N -ary relation extraction with graph LSTMs. Trans Assoc Comput Linguist 5:101\u2013115. https:\/\/doi.org\/10.1162\/tacl_a_00049","journal-title":"Trans Assoc Comput Linguist"},{"key":"17594_CR17","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.3390\/rs13071404","volume":"13","author":"H Liu","year":"2021","unstructured":"Liu H, Xu D, Zhu T et al (2021) Graph convolutional networks by architecture search for PolSAR image classification. Remote Sens 13:1404. https:\/\/doi.org\/10.3390\/rs13071404","journal-title":"Remote Sens"},{"key":"17594_CR18","doi-asserted-by":"crossref","unstructured":"Shi W, Rajkumar R (2020) Point-GNN: Graph neural network for 3D object detection in a point cloud. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1708\u20131716","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"17594_CR19","doi-asserted-by":"crossref","unstructured":"Gori M, Monfardini G, Scarselli F (2005) A new model for learning in graph domains. In: 2005 IEEE International Joint Conference on Neural Networks. IEEE, pp 729\u2013734","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"17594_CR20","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli F, Gori M, Tsoi AC et al (2009) The Graph Neural Network Model. IEEE Trans Neural Networks 20:61\u201380. https:\/\/doi.org\/10.1109\/TNN.2008.2005605","journal-title":"IEEE Trans Neural Networks"},{"key":"17594_CR21","doi-asserted-by":"publisher","unstructured":"Zhang S, Tong H, Xu J, Maciejewski R (2019) Graph convolutional networks: a comprehensive review. Comput Soc Netw 6. https:\/\/doi.org\/10.1186\/s40649-019-0069-y","DOI":"10.1186\/s40649-019-0069-y"},{"key":"17594_CR22","doi-asserted-by":"publisher","first-page":"35929","DOI":"10.1109\/ACCESS.2020.2975067","volume":"8","author":"W Cao","year":"2020","unstructured":"Cao W, Yan Z, He Z, He Z (2020) A comprehensive survey on geometric deep learning. IEEE Access 8:35929\u201335949. https:\/\/doi.org\/10.1109\/ACCESS.2020.2975067","journal-title":"IEEE Access"},{"key":"17594_CR23","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","volume":"1","author":"J Zhou","year":"2020","unstructured":"Zhou J, Cui G, Hu S et al (2020) Graph neural networks: A review of methods and applications. AI Open 1:57\u201381. https:\/\/doi.org\/10.1016\/j.aiopen.2021.01.001","journal-title":"AI Open"},{"key":"17594_CR24","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu Z, Pan S, Chen F et al (2021) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32:4\u201324. https:\/\/doi.org\/10.1109\/TNNLS.2020.2978386","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"17594_CR25","doi-asserted-by":"publisher","first-page":"60588","DOI":"10.1109\/ACCESS.2021.3071274","volume":"9","author":"NA Asif","year":"2021","unstructured":"Asif NA, Sarker Y, Chakrabortty RK et al (2021) Graph neural network: A comprehensive review on non-euclidean space. IEEE Access 9:60588\u201360606. https:\/\/doi.org\/10.1109\/ACCESS.2021.3071274","journal-title":"IEEE Access"},{"key":"17594_CR26","doi-asserted-by":"publisher","unstructured":"Zhou Y, Zheng H, Huang X et al (2022) Graph neural networks: taxonomy, advances, and trends. ACM Trans Intell Syst Technol 13. https:\/\/doi.org\/10.1145\/3495161","DOI":"10.1145\/3495161"},{"key":"17594_CR27","doi-asserted-by":"publisher","first-page":"13387","DOI":"10.1007\/s00521-022-07368-1","volume":"34","author":"P Cao","year":"2022","unstructured":"Cao P, Zhu Z, Wang Z et al (2022) Applications of graph convolutional networks in computer vision. Neural Comput Appl 34:13387\u201313405. https:\/\/doi.org\/10.1007\/s00521-022-07368-1","journal-title":"Neural Comput Appl"},{"key":"17594_CR28","doi-asserted-by":"publisher","first-page":"109250","DOI":"10.1016\/j.knosys.2022.109250","volume":"251","author":"H Ren","year":"2022","unstructured":"Ren H, Lu W, Xiao Y et al (2022) Knowledge-based systems graph convolutional networks in language and vision\u202f: A survey. Knowl-Based Syst 251:109250. https:\/\/doi.org\/10.1016\/j.knosys.2022.109250","journal-title":"Knowl-Based Syst"},{"key":"17594_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10151-2","author":"AA Yusuf","year":"2022","unstructured":"Yusuf AA, Chong F, Xianling M (2022) An analysis of graph convolutional networks and recent datasets for visual question answering. Artif Intell Rev L. https:\/\/doi.org\/10.1007\/s10462-022-10151-2","journal-title":"Artif Intell Rev L"},{"key":"17594_CR30","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1016\/j.infsof.2010.03.006","volume":"52","author":"B Kitchenham","year":"2010","unstructured":"Kitchenham B, Pretorius R, Budgen D et al (2010) Systematic literature reviews in software engineering \u2013 A tertiary study. Inf Softw Technol 52:792\u2013805. https:\/\/doi.org\/10.1016\/j.infsof.2010.03.006","journal-title":"Inf Softw Technol"},{"key":"17594_CR31","unstructured":"Narasimhan M, Lazebnik S, Schwing AG (2018) Out of the box: Reasoning with graph convolution nets for factual visual question answering. Adv Neural Inf Process Syst 2018-Decem:2654\u20132665"},{"key":"17594_CR32","doi-asserted-by":"crossref","unstructured":"Yang Z, Qin Z, Yu J, Hu Y (2019) Scene graph reasoning with prior visual relationship for visual question answering. arXiv preprint arXiv:1812.09681","DOI":"10.1109\/ICIP40778.2020.9190771"},{"key":"17594_CR33","doi-asserted-by":"publisher","unstructured":"Lee S, Kim JW, Oh Y, Jeon JH (2019) Visual question answering over scene graph. Proceedings - 2019 1st International Conference on Graph Computing, GC 2019 45\u201350. https:\/\/doi.org\/10.1109\/GC46384.2019.00015","DOI":"10.1109\/GC46384.2019.00015"},{"key":"17594_CR34","first-page":"10294","volume":"2019","author":"R Hu","year":"2019","unstructured":"Hu R, Rohrbach A, Darrell T, Saenko K (2019) Language-conditioned graph networks for relational reasoning. IEEE\/CVF Int Conf Comput Vision (ICCV) 2019:10294\u201310303","journal-title":"IEEE\/CVF Int Conf Comput Vision (ICCV)"},{"key":"17594_CR35","unstructured":"Saqur R, Narasimhan K (2020) Multimodal graph networks for compositional generalization in visual question answering. Adv Neural Inf Process Syst 2020-Decem:1\u201312"},{"key":"17594_CR36","doi-asserted-by":"publisher","unstructured":"Gao D, Li K, Wang R et al (2020) Multi-modal graph neural network for joint reasoning on vision and scene text. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 12743\u201312753. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01276","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"17594_CR37","doi-asserted-by":"publisher","unstructured":"Zhu Z, Yu J, Wang Y et al (2020) Mucko: Multi-layer cross-modal knowledge reasoning for fact-based visual question answering. IJCAI Int Joint Conf Artif Intell 2021-Janua:1097\u20131103. https:\/\/doi.org\/10.24963\/ijcai.2020\/153","DOI":"10.24963\/ijcai.2020\/153"},{"key":"17594_CR38","doi-asserted-by":"publisher","unstructured":"Kim ES, Kang WY, On KW, et al (2020) Hypergraph attention networks for multimodal learning. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 14569\u201314578. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01459","DOI":"10.1109\/CVPR42600.2020.01459"},{"key":"17594_CR39","first-page":"1","volume":"2019","author":"C Zhang","year":"2020","unstructured":"Zhang C, Chao WL, Xuan D (2020) An empirical study on leveraging scene graphs for visual question answering. 30th British Machine Vision Conference 2019. BMVC 2019:1\u201321","journal-title":"BMVC"},{"key":"17594_CR40","doi-asserted-by":"publisher","unstructured":"Le TM, Le V, Venkatesh S, Tran T (2020) Dynamic language binding in relational visual reasoning. IJCAI Int Joint Conf Artif Intell 2021-Janua:818\u2013824. https:\/\/doi.org\/10.24963\/ijcai.2020\/114","DOI":"10.24963\/ijcai.2020\/114"},{"key":"17594_CR41","doi-asserted-by":"publisher","first-page":"106150","DOI":"10.1016\/j.knosys.2020.106150","volume":"203","author":"J Yu","year":"2020","unstructured":"Yu J, Zhang W, Yang Z et al (2020) Cross-modal learning with prior visual relation knowledge. Knowl-Based Syst 203:106150. https:\/\/doi.org\/10.1016\/j.knosys.2020.106150","journal-title":"Knowl-Based Syst"},{"key":"17594_CR42","doi-asserted-by":"publisher","unstructured":"Yu J, Zhu Z, Wang Y et al (2020) Cross-modal knowledge reasoning for knowledge-based visual question answering. Pattern Recognit 108. https:\/\/doi.org\/10.1016\/j.patcog.2020.107563","DOI":"10.1016\/j.patcog.2020.107563"},{"key":"17594_CR43","doi-asserted-by":"publisher","unstructured":"Huang Q, Wei J, Cai Y, Zheng C, Chen J, Leung HF, Li Q (2020) Aligned dual channel graph convolutional network for visual question answering. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 7166\u20137176. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.642","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"17594_CR44","doi-asserted-by":"publisher","unstructured":"Khademi M (2020) Multimodal neural graph memory networks for visual question answering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 7177\u20137188. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.643","DOI":"10.18653\/v1\/2020.acl-main.643"},{"key":"17594_CR45","doi-asserted-by":"crossref","unstructured":"Li L, Gan Z, Cheng Y, Liu J (2019) Relation-aware graph attention network for visual question answering. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, pp 10312\u201310321","DOI":"10.1109\/ICCV.2019.01041"},{"key":"17594_CR46","doi-asserted-by":"publisher","unstructured":"Hu Z, Wei J, Huang Q et al (2020) Graph convolutional network for visual question answering based on fine-grained question representation. Proceedings - 2020 IEEE 5th International Conference on Data Science in Cyberspace, DSC 2020 218\u2013224. https:\/\/doi.org\/10.1109\/DSC50466.2020.00040","DOI":"10.1109\/DSC50466.2020.00040"},{"key":"17594_CR47","doi-asserted-by":"publisher","unstructured":"Liang W, Jiang Y, Liu Z (2021) GraphVQA: language-guided graph neural networks for scene graph question answering. NAACL-HLT 2021 79. https:\/\/doi.org\/10.18653\/v1\/2021.maiworkshop-1.12","DOI":"10.18653\/v1\/2021.maiworkshop-1.12"},{"key":"17594_CR48","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.inffus.2021.02.006","volume":"72","author":"W Zhang","year":"2021","unstructured":"Zhang W, Yu J, Zhao W, Ran C (2021) DMRFNet: Deep multimodal reasoning and fusion for visual question answering and explanation generation. Information Fusion 72:70\u201379. https:\/\/doi.org\/10.1016\/j.inffus.2021.02.006","journal-title":"Information Fusion"},{"key":"17594_CR49","doi-asserted-by":"publisher","unstructured":"Xie J, Cai Y, Huang Q, Wang T (2021) Multiple objects-aware visual question generation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 4546\u20134554. https:\/\/doi.org\/10.1145\/3474085.3476969","DOI":"10.1145\/3474085.3476969"},{"key":"17594_CR50","doi-asserted-by":"publisher","unstructured":"Nuthalapati SV, Chandradevan R, Giunchiglia E, et al (2021) Lightweight visual question answering using scene graphs. 30th ACM Int Conf Inf Knowl Manage. https:\/\/doi.org\/10.1145\/3459637.3482218","DOI":"10.1145\/3459637.3482218"},{"key":"17594_CR51","doi-asserted-by":"publisher","first-page":"104165","DOI":"10.1016\/j.imavis.2021.104165","volume":"110","author":"H Sharma","year":"2021","unstructured":"Sharma H, Jalal AS (2021) Visual question answering model based on graph neural network and contextual attention. Image Vis Comput 110:104165. https:\/\/doi.org\/10.1016\/j.imavis.2021.104165","journal-title":"Image Vis Comput"},{"key":"17594_CR52","doi-asserted-by":"publisher","first-page":"16247","DOI":"10.1007\/s11042-020-08790-0","volume":"80","author":"X Zhu","year":"2021","unstructured":"Zhu X, Mao Z, Chen Z et al (2021) Object-difference drived graph convolutional networks for visual question answering. Multimed Tools Appl 80:16247\u201316265. https:\/\/doi.org\/10.1007\/s11042-020-08790-0","journal-title":"Multimed Tools Appl"},{"key":"17594_CR53","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1109\/TNNLS.2021.3104937","volume":"34","author":"D Guo","year":"2023","unstructured":"Guo D, Xu C, Tao D (2023) Bilinear graph networks for visual question answering. IEEE Trans Neural Netw Learn Syst 34:1023\u20131034. https:\/\/doi.org\/10.1109\/TNNLS.2021.3104937","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"17594_CR54","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-030-88361-4","volume":"1","author":"B Rk","year":"2021","unstructured":"Rk B, Li H, Hildebrandt M, Das D (2021) Graphhopper\u202f: Multi-hop scene graph. Int Semant Web Conf 1:111\u2013127. https:\/\/doi.org\/10.1007\/978-3-030-88361-4","journal-title":"Int Semant Web Conf"},{"key":"17594_CR55","doi-asserted-by":"publisher","first-page":"9603","DOI":"10.1109\/TPAMI.2021.3132034","volume":"44","author":"C Gao","year":"2021","unstructured":"Gao C, Zhu Q, Wang P et al (2021) Structured Multimodal Attentions for TextVQA. IEEE Trans Pattern Anal Mach Intell 44:9603\u20139614. https:\/\/doi.org\/10.1109\/TPAMI.2021.3132034","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17594_CR56","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.1109\/TNNLS.2020.2986029","volume":"32","author":"X Xu","year":"2021","unstructured":"Xu X, Wang T, Yang Y, Hanjalic A (2021) Radial graph convolutional network for visual question generation. IEEE Trans Neural Netw Learn Syst 32:1654\u20131667","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"17594_CR57","unstructured":"Damodaran V, Chakravarthy S, Kumar A, Umapathy A, Mitamura T, Nakashima Y, Garcia N, Chu C (2021) Understanding the role of scene graphs in visual question answering. arXiv preprint arXiv:2101.05479"},{"key":"17594_CR58","doi-asserted-by":"publisher","first-page":"e0277693","DOI":"10.1371\/journal.pone.0277693","volume":"17","author":"X Shen","year":"2022","unstructured":"Shen X, Han D, Chen C et al (2022) An effective spatial relational reasoning networks for visual question answering. PLoS ONE 17:e0277693. https:\/\/doi.org\/10.1371\/journal.pone.0277693","journal-title":"PLoS ONE"},{"key":"17594_CR59","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1007\/s11063-021-10689-2","volume":"54","author":"Y Miao","year":"2022","unstructured":"Miao Y, Cheng W, He S, Jiang H (2022) Research on Visual Question Answering Based on GAT Relational Reasoning. Neural Process Lett 54:1435\u20131448. https:\/\/doi.org\/10.1007\/s11063-021-10689-2","journal-title":"Neural Process Lett"},{"key":"17594_CR60","doi-asserted-by":"publisher","first-page":"107650","DOI":"10.1016\/j.knosys.2021.107650","volume":"237","author":"L Liu","year":"2022","unstructured":"Liu L, Wang M, He X et al (2022) Fact-based visual question answering via dual-process system. Knowl-Based Syst 237:107650. https:\/\/doi.org\/10.1016\/j.knosys.2021.107650","journal-title":"Knowl-Based Syst"},{"key":"17594_CR61","doi-asserted-by":"publisher","unstructured":"Qian Y, Hu Y, Wang R, Feng F, Wang X (2022) Question-driven graph fusion network for visual question answering. In: 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859591","DOI":"10.1109\/ICME52920.2022.9859591"},{"key":"17594_CR62","doi-asserted-by":"publisher","unstructured":"Li X, Wu B, Song J, et al (2022) Text-instance graph: Exploring the relational semantics for text-based visual question answering. Pattern Recognit 124. https:\/\/doi.org\/10.1016\/j.patcog.2021.108455","DOI":"10.1016\/j.patcog.2021.108455"},{"key":"17594_CR63","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s00530-020-00745-7","volume":"28","author":"R Liu","year":"2022","unstructured":"Liu R, Zhuang L, Yu Z et al (2022) Question-relationship guided graph attention network for visual question answer. Multimed Syst 28:445\u2013456. https:\/\/doi.org\/10.1007\/s00530-020-00745-7","journal-title":"Multimed Syst"},{"key":"17594_CR64","doi-asserted-by":"publisher","unstructured":"Jing C, Jia Y, Wu Y et al (2022) Maintaining reasoning consistency in compositional visual question answering. 5089\u20135098. https:\/\/doi.org\/10.1109\/cvpr52688.2022.00504","DOI":"10.1109\/cvpr52688.2022.00504"},{"key":"17594_CR65","doi-asserted-by":"publisher","unstructured":"Chae J, Kim J (2022) Uncertainty-based visual question answering: estimating semantic inconsistency between image and knowledge base. Proc Int Joint Conf Neural Netw 2022-July: https:\/\/doi.org\/10.1109\/IJCNN55064.2022.9892787","DOI":"10.1109\/IJCNN55064.2022.9892787"},{"key":"17594_CR66","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.neucom.2022.03.071","volume":"492","author":"H Pan","year":"2022","unstructured":"Pan H, Huang J (2022) Multimodal high-order relational network for vision-and-language tasks. Neurocomputing 492:62\u201375. https:\/\/doi.org\/10.1016\/j.neucom.2022.03.071","journal-title":"Neurocomputing"},{"key":"17594_CR67","doi-asserted-by":"crossref","unstructured":"Wang Y, Yasunaga M, Ren H, Wada S, Leskovec J (2022) VQA-GNN: Reasoning with multimodal semantic graph for visual question answering. arXiv preprint arXiv:2205.11501","DOI":"10.1109\/ICCV51070.2023.01973"},{"key":"17594_CR68","doi-asserted-by":"publisher","unstructured":"Cao J, Qin X, Zhao S, Shen J (2022) Bilateral cross-modality graph matching attention for feature fusion in visual question answering. IEEE Trans Neural Netw Learn Syst 1\u201312. https:\/\/doi.org\/10.1109\/TNNLS.2021.3135655","DOI":"10.1109\/TNNLS.2021.3135655"},{"key":"17594_CR69","doi-asserted-by":"publisher","first-page":"102329","DOI":"10.1016\/j.displa.2022.102329","volume":"75","author":"J Feng","year":"2022","unstructured":"Feng J, Liu R (2022) LRB-Net: Improving VQA via division of labor strategy and multimodal classifiers. Displays 75:102329. https:\/\/doi.org\/10.1016\/j.displa.2022.102329","journal-title":"Displays"},{"key":"17594_CR70","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s11063-021-10655-y","volume":"54","author":"H Sharma","year":"2022","unstructured":"Sharma H, Jalal AS (2022) An improved attention and hybrid optimization technique for visual question answering. Neural Process Lett 54:709\u2013730. https:\/\/doi.org\/10.1007\/s11063-021-10655-y","journal-title":"Neural Process Lett"},{"key":"17594_CR71","doi-asserted-by":"publisher","first-page":"40361","DOI":"10.1007\/s11042-022-13065-x","volume":"81","author":"AA Yusuf","year":"2022","unstructured":"Yusuf AA, Chong F, Xianling M (2022) Evaluation of graph convolutional networks performance for visual question answering on reasoning datasets. Multimed Tools Appl 81:40361\u201340370. https:\/\/doi.org\/10.1007\/s11042-022-13065-x","journal-title":"Multimed Tools Appl"},{"key":"17594_CR72","doi-asserted-by":"publisher","first-page":"108883","DOI":"10.1016\/j.patcog.2022.108883","volume":"131","author":"G Kv","year":"2022","unstructured":"Kv G, Mittal A (2022) On the role of question encoder sequence model in robust visual question answering. Pattern Recognit 131:108883. https:\/\/doi.org\/10.1016\/j.patcog.2022.108883","journal-title":"Pattern Recognit"},{"key":"17594_CR73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICME52920.2022.9859766","volume":"2022","author":"H Li","year":"2022","unstructured":"Li H, Li X, Karimi B, Chen JSM (2022) Joint learning of object graph and relation graph for visual question answering. IEEE Int Conf Multimed Expo (ICME) 2022:1\u20136. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859766","journal-title":"IEEE Int Conf Multimed Expo (ICME)"},{"key":"17594_CR74","doi-asserted-by":"publisher","first-page":"103207","DOI":"10.1016\/j.ipm.2022.103207","volume":"60","author":"Z Xu","year":"2023","unstructured":"Xu Z, Gu J, Liu M et al (2023) A question-guided multi-hop reasoning graph network for visual question answering. Inf Process Manage 60:103207. https:\/\/doi.org\/10.1016\/j.ipm.2022.103207","journal-title":"Inf Process Manage"},{"key":"17594_CR75","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2018","unstructured":"Wang P, Wu Q, Shen C et al (2018) FVQA\u202f: Fact-Based Visual Question Answering. IEEE Trans Pattern Anal Mach Intell 40:2413\u20132427","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17594_CR76","doi-asserted-by":"publisher","first-page":"3190","DOI":"10.1109\/CVPR.2019.00331","volume":"2019","author":"K Marino","year":"2019","unstructured":"Marino K, Rastegari M, Farhadi A, Mottaghi R (2019) OK-VQA\u202f: A visual question answering benchmark requiring external knowledge. IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR) 2019:3190\u20133199. https:\/\/doi.org\/10.1109\/CVPR.2019.00331","journal-title":"IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"17594_CR77","first-page":"980","volume":"4971\u20134","author":"A Agrawal","year":"2018","unstructured":"Agrawal A, Batra D, Parikh D, Kembhavi A (2018) Overcoming Priors for Visual Question Answering. Proc IEEE Conf Comput Vis Pattern Recognit 4971\u20134:980","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"17594_CR78","doi-asserted-by":"publisher","unstructured":"Shah S, Mishra A, Yadati N, Talukdar PP (2019) KVQA: Knowledge-aware visual question answering. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, no 01. AAAI, pp 8876\u20138884. https:\/\/doi.org\/10.1609\/aaai.v33i01.33018876","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"17594_CR79","doi-asserted-by":"publisher","unstructured":"Biten AF, Tito R, Mafla A, Gomez L, Rusinol M, Valveny E, Jawahar CV, Karatzas D (2019) Scene text visual question answering. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4291\u20134301. https:\/\/doi.org\/10.1109\/ICCV.2019.00439","DOI":"10.1109\/ICCV.2019.00439"},{"key":"17594_CR80","doi-asserted-by":"publisher","unstructured":"Singh A, Natarajan V, Shah M, Jiang Y, Chen X, Batra D, Parikh D, Rohrbach M (2019) Towards VQA models that can read. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8317\u20138326. https:\/\/doi.org\/10.1109\/CVPR.2019.00851","DOI":"10.1109\/CVPR.2019.00851"},{"key":"17594_CR81","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O et al (2017) Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int J Comput Vision 123:32\u201373. https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int J Comput Vision"},{"key":"17594_CR82","doi-asserted-by":"publisher","unstructured":"Zhu Y, Groth O, Bernstein M, Fei-Fei L (2016) Visual7W: Grounded question answering in images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4995\u20135004. https:\/\/doi.org\/10.1109\/CVPR.2016.540","DOI":"10.1109\/CVPR.2016.540"},{"key":"17594_CR83","doi-asserted-by":"crossref","unstructured":"Mishra A, Nutting AW (2019) OCR-VQA\u202f: Visual question answering by reading text in images. 2019 Int Conf Doc Anal Recognit (ICDAR), Sydney, NSW, pp 947\u2013952","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"17594_CR84","doi-asserted-by":"publisher","unstructured":"Hudson DA, Manning CD (2019) GQA: A new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6700\u20136709. https:\/\/doi.org\/10.1109\/CVPR.2019.00686","DOI":"10.1109\/CVPR.2019.00686"},{"key":"17594_CR85","doi-asserted-by":"publisher","unstructured":"Goyal Y, Khot T, Summers-Stay D et al (2017) Making the V in VQA matter: Elevating the role of image understanding in visual question answering. Proc - 30th IEEE Conf Comput Vis Pattern Recognit, CVPR 2017 6325\u20136334. https:\/\/doi.org\/10.1109\/CVPR.2017.670","DOI":"10.1109\/CVPR.2017.670"},{"key":"17594_CR86","doi-asserted-by":"publisher","unstructured":"Johnson J, Hariharan B, Van Der Maaten L, Fei-Fei L, Lawrence Zitnick C, Girshick R (2017) CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2901\u20132910. https:\/\/doi.org\/10.1109\/CVPR.2017.215","DOI":"10.1109\/CVPR.2017.215"},{"key":"17594_CR87","unstructured":"Ishida T, Niu G, Hu W, Sugiyama M (2017) Learning from complementary Labels. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA 1\u201314"},{"key":"17594_CR88","doi-asserted-by":"publisher","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp 311\u2013318. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"17594_CR89","unstructured":"Tech V, Zitnick CL, Parikh D (2015) CIDEr\u202f: Consensus-based image description evaluation Ramakrishna Vedantam. In: Proceedings of the IEEE conference on computer vision and pattern recognition 4566\u20134575"},{"key":"17594_CR90","unstructured":"Banerjee S, Lavie A (2005) METEOR\u202f: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In: Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization 65\u201372"},{"key":"17594_CR91","unstructured":"Lin C, Rey M (2004) ROUGE\u202f: A package for automatic evaluation of summaries. In: Text Summarization Branches Out 74\u201381"},{"key":"17594_CR92","doi-asserted-by":"crossref","unstructured":"Ting KM (2011) Precision and Recall. In: Sammut, C, Webb, GI (eds) Encyclopedia of Machine Learning Springer, Boston, MA","DOI":"10.1007\/978-0-387-30164-8_652"},{"key":"17594_CR93","unstructured":"Kaiming H, Xiangyu Z, Shaoqing R, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition 770\u2013 778"},{"key":"17594_CR94","doi-asserted-by":"publisher","unstructured":"Schmidhuber SH, J (1997) Long short-term memory. Neural Comput 9:1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"17594_CR95","doi-asserted-by":"crossref","unstructured":"Graves A, Fern S (2005) Bidirectional LSTM networks for improved phoneme classification and recognition. International Conference on Artificial Neural Networks, Springer 799\u2013804","DOI":"10.1007\/11550907_126"},{"key":"17594_CR96","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. IEEE Comput Intell Maga 13:55\u201375","journal-title":"IEEE Comput Intell Maga"},{"key":"17594_CR97","doi-asserted-by":"crossref","unstructured":"Cao Y, Li A, Lou J et al (2021) An attention-based bidirectional gated recurrent unit network for location prediction. 13th International Conference on Wireless Communications and Signal Processing (WCSP) 2:21\u201325","DOI":"10.1109\/WCSP52459.2021.9613646"},{"key":"17594_CR98","unstructured":"Kenton MC, Kristina L, Devlin J (2019) BERT\u202f: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 4171\u20134186"},{"key":"17594_CR99","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) RoBERTa: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"17594_CR100","unstructured":"Kim JH, Jun J, Zhang BT (2018) Bilinear attention networks. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp 1571\u20131581"},{"key":"17594_CR101","doi-asserted-by":"crossref","unstructured":"Charikar M, Chen K (2002) Finding frequent items in data streams. International Colloquium on Automata, Languages, and Programming, Springer, Berlin, Heidelberg 693\u2013703","DOI":"10.1007\/3-540-45465-9_59"},{"key":"17594_CR102","doi-asserted-by":"crossref","unstructured":"Yu Z, Yu J, Fan J Tao D (2017) Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, pp 1839\u20131848","DOI":"10.1109\/ICCV.2017.202"},{"key":"17594_CR103","doi-asserted-by":"publisher","unstructured":"Doll P, Girshick R, Ai F (2017) Mask R-CNN. IEEE International Conference on Computer Vision 2980\u20132988. https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"17594_CR104","unstructured":"OpenAI (2021) ChatGPT. https:\/\/openai.com\/blog\/better-language-models\/.\u00a0Accessed 22 May 2023."},{"key":"17594_CR105","unstructured":"Lu, J., Batra, D., Parikh, D., & Lee S (2019) ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in neural information processing systems. p 32"},{"key":"17594_CR106","doi-asserted-by":"publisher","unstructured":"Tan H, Bansal M (2019) LXMert: Learning cross-modality encoder representations from transformers. EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference 5100\u20135111. https:\/\/doi.org\/10.18653\/v1\/d19-1514","DOI":"10.18653\/v1\/d19-1514"},{"key":"17594_CR107","doi-asserted-by":"crossref","unstructured":"Gurari D, Li Q, Stangl AJ, et al (2018) VizWiz grand challenge\u202f: answering visual questions from blind people. In: Proceedings of the IEEE conference on computer vision and pattern recognition 3608\u20133617","DOI":"10.1109\/CVPR.2018.00380"},{"key":"17594_CR108","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2020.113993","volume":"164","author":"D Gupta","year":"2021","unstructured":"Gupta D, Suman S, Ekbal A (2021) Hierarchical deep multi-modal network for medical visual question answering. Expert Syst Appl 164:1\u201354. https:\/\/doi.org\/10.1016\/j.eswa.2020.113993","journal-title":"Expert Syst Appl"},{"key":"17594_CR109","doi-asserted-by":"publisher","unstructured":"Davis E (2020) Unanswerable questions about images and texts. Front Artif Intell 3:1\u201310. https:\/\/doi.org\/10.3389\/frai.2020.00051","DOI":"10.3389\/frai.2020.00051"},{"key":"17594_CR110","doi-asserted-by":"publisher","unstructured":"Liu X, Su Y, Xu B (2021) The application of graph neural network in natural language processing and computer vision. Proceedings - 2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2021 708\u2013714. https:\/\/doi.org\/10.1109\/MLBDBI54094.2021.00140","DOI":"10.1109\/MLBDBI54094.2021.00140"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17594-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17594-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17594-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T10:12:33Z","timestamp":1715767953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17594-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,16]]},"references-count":110,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17594"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17594-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,16]]},"assertion":[{"value":"29 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2023","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}