{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:17:21Z","timestamp":1774369041133,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T00:00:00Z","timestamp":1685404800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T00:00:00Z","timestamp":1685404800000},"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":["No.2018YFC1604000"],"award-info":[{"award-number":["No.2018YFC1604000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-15272-6","type":"journal-article","created":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T06:02:27Z","timestamp":1685426547000},"page":"36629-36644","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multimodal visual-textual object graph attention network for propaganda detection in memes"],"prefix":"10.1007","volume":"83","author":[{"given":"Pengyuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangheran","family":"Piao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,30]]},"reference":[{"issue":"5","key":"15272_CR1","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1016\/j.ipm.2019.03.005","volume":"56","author":"A Barr\u00f3n-Cedeno","year":"2019","unstructured":"Barr\u00f3n-Cedeno A, Jaradat I, Da San Martino G, Nakov P (2019) Proppy: organizing the news based on their propagandistic content. Inform Process Manag 56(5):1849\u20131864","journal-title":"Inform Process Manag"},{"key":"15272_CR2","doi-asserted-by":"crossref","unstructured":"Chen P, Ye K, Cui X (2021) Integrating n-gram features into pre-trained model: a novel ensemble model for multi-target stance detection. In: International conference on artificial neural networks. Springer, pp 269\u2013279","DOI":"10.1007\/978-3-030-86365-4_22"},{"key":"15272_CR3","doi-asserted-by":"crossref","unstructured":"Da San Martino G, Yu S, Barr\u00f3n-Cedeno A, Petrov R, Nakov P (2019) Fine-grained analysis of propaganda in news article. 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 5636\u20135646","DOI":"10.18653\/v1\/D19-1565"},{"key":"15272_CR4","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15272_CR5","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pp 4171\u20134186"},{"key":"15272_CR6","doi-asserted-by":"crossref","unstructured":"Dimitrov D, Ali B B, Shaar S, Alam F, Silvestri F, Firooz H, Nakov P, Da San Martino G (2021) Detecting propaganda techniques in memes. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers), pp 6603\u20136617","DOI":"10.18653\/v1\/2021.acl-long.516"},{"key":"15272_CR7","doi-asserted-by":"crossref","unstructured":"Gori M, Monfardini G, Scarselli F (2005) A new model for learning in graph domains. In: Proceedings. 2005 IEEE international joint conference on neural networks, 2005., vol 2. IEEE, pp 729\u2013734","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"15272_CR8","doi-asserted-by":"crossref","unstructured":"Habernal I, Hannemann R, Pollak C, Klamm C, Pauli P, Gurevych I (2017) Argotario: computational argumentation meets serious games. arXiv:1707.06002","DOI":"10.18653\/v1\/D17-2002"},{"key":"15272_CR9","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, 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":"15272_CR10","unstructured":"He P, Liu X, Gao J, Chen W (2020) Deberta: decoding-enhanced bert with disentangled attention. arXiv:2006.03654"},{"key":"15272_CR11","doi-asserted-by":"crossref","unstructured":"Hu Z, Wei J, Huang Q, Liang H, Zhang X, Liu Q (2020) Graph convolutional network for visual question answering based on fine-grained question representation. In: 2020 IEEE Fifth International conference on Data Science in Cyberspace (DSC). IEEE, pp 218\u2013224","DOI":"10.1109\/DSC50466.2020.00040"},{"key":"15272_CR12","unstructured":"Kiela D, Bhooshan S, Firooz H, Perez E, Testuggine D (2019) Supervised multimodal bitransformers for classifying images and text. arXiv:1909.02950"},{"key":"15272_CR13","unstructured":"Kiela D, Firooz H, Mohan A, Goswami V, Singh A, Ringshia P, Testuggine D (2020) The hateful memes challenge: detecting hate speech in multimodal memes. Adv Neural Inf Process Syst, 33"},{"key":"15272_CR14","unstructured":"Kipf T N, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"issue":"1","key":"15272_CR15","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, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L-J, Shamma D A et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis 123(1):32\u201373","journal-title":"Int J Comput Vis"},{"issue":"2","key":"15272_CR16","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1086\/219744","volume":"51","author":"AM Lee","year":"1945","unstructured":"Lee A M (1945) The analysis of propaganda: a clinical summary. Am J Sociol 51(2):126\u2013135","journal-title":"Am J Sociol"},{"key":"15272_CR17","doi-asserted-by":"crossref","unstructured":"Lee R K-W, Cao R, Fan Z, Jiang J, Chong W-H (2021) Disentangling hate in online memes. In: Proceedings of the 29th ACM international conference on multimedia, pp 5138\u20135147","DOI":"10.1145\/3474085.3475625"},{"key":"15272_CR18","doi-asserted-by":"crossref","unstructured":"Li K, Zhang Y, Li K, Li Y, Fu Y (2019) Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4654\u20134662","DOI":"10.1109\/ICCV.2019.00475"},{"key":"15272_CR19","unstructured":"Li L H, Yatskar M, Yin D, Hsieh C-J, Chang K-W (2019) Visualbert: a simple and performant baseline for vision and language. arXiv:1908.03557"},{"key":"15272_CR20","doi-asserted-by":"crossref","unstructured":"Liang W, Jiang Y, Liu Z (2021) Graghvqa: language-guided graph neural networks for graph-based visual question answering. In: Proceedings of the third workshop on multimodal artificial intelligence, pp 79\u201386","DOI":"10.18653\/v1\/2021.maiworkshop-1.12"},{"key":"15272_CR21","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick C L (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"15272_CR22","doi-asserted-by":"crossref","unstructured":"Liu T, Zhao R, Lam K-M (2021) Multimodal-semantic context-aware graph neural network for group activity recognition. In: 2021 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp 1\u20136","DOI":"10.1109\/ICME51207.2021.9428377"},{"key":"15272_CR23","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:1907.11692"},{"key":"15272_CR24","unstructured":"Lu J, Batra D, Parikh D, Lee S (2019) Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Proceedings of the 33rd international conference on neural information processing systems, pp 13\u201323"},{"issue":"2","key":"15272_CR25","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1109\/TMM.2019.2930344","volume":"22","author":"L Lu","year":"2019","unstructured":"Lu L, Lu Y, Yu R, Di H, Zhang L, Wang S (2019) Gaim: graph attention interaction model for collective activity recognition. IEEE Trans Multimed 22(2):524\u2013539","journal-title":"IEEE Trans Multimed"},{"key":"15272_CR26","doi-asserted-by":"crossref","unstructured":"Martino G D S, Cresci S, Barr\u00f3n-Cede\u00f1o A, Yu S, Di Pietro R, Nakov P (2020) A survey on computational propaganda detection. arXiv:2007.08024","DOI":"10.24963\/ijcai.2020\/672"},{"issue":"3","key":"15272_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3003433","volume":"17","author":"SM Mohammad","year":"2017","unstructured":"Mohammad S M, Sobhani P, Kiritchenko S (2017) Stance and sentiment in tweets. ACM Transactions on Internet Technology (TOIT) 17(3):1\u201323","journal-title":"ACM Transactions on Internet Technology (TOIT)"},{"key":"15272_CR28","doi-asserted-by":"crossref","unstructured":"Pramanick S, Sharma S, Dimitrov D, Akhtar M S, Nakov P, Chakraborty T (2021) Momenta: a multimodal framework for detecting harmful memes and their targets. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp 4439\u20134455","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"15272_CR29","doi-asserted-by":"crossref","unstructured":"Qi P, Zhang Y, Zhang Y, Bolton J, Manning C D (2020) Stanza: a python natural language processing toolkit for many human languages. In: Proceedings of the 58th annual meeting of the association for computational linguistics: system demonstrations, pp 101\u2013108","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"15272_CR30","first-page":"T2","volume":"2","author":"A Radford","year":"2021","unstructured":"Radford A, Kim J W, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. Image 2:T2","journal-title":"Image"},{"key":"15272_CR31","doi-asserted-by":"crossref","unstructured":"Rashkin H, Choi E, Jang J Y, Volkova S, Choi Y (2017) Truth of varying shades: analyzing language in fake news and political fact-checking. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp 2931\u20132937","DOI":"10.18653\/v1\/D17-1317"},{"key":"15272_CR32","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neur Inform Process Syst 28:91\u201399","journal-title":"Adv Neur Inform Process Syst"},{"key":"15272_CR33","doi-asserted-by":"crossref","unstructured":"Sharma C, Bhageria D, Scott W, Srinivas PYKL, Das A, Chakraborty T, Pulabaigari V, Gamb\u00e4ck B (2020) Semeval-2020 task 8: memotion analysis-the visuo-lingual metaphor!. In: Proceedings of the fourteenth workshop on semantic evaluation, pp 759\u2013773","DOI":"10.18653\/v1\/2020.semeval-1.99"},{"key":"15272_CR34","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 A S (2021) Visual question answering model based on graph neural network and contextual attention. Image Vis Comput 110:104165","journal-title":"Image Vis Comput"},{"key":"15272_CR35","doi-asserted-by":"crossref","unstructured":"Sharma P, Ding N, Goodman S, Soricut R (2018) Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long papers), pp 2556\u20132565","DOI":"10.18653\/v1\/P18-1238"},{"key":"15272_CR36","first-page":"4","volume":"1050","author":"P Velickovic","year":"2018","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. stat 1050:4","journal-title":"stat"},{"key":"15272_CR37","first-page":"0","volume":"24","author":"R Wang","year":"2020","unstructured":"Wang R, Tang D, Duan N, Zhong W, Wei Z, Huang X, Jiang D, Zhou M (2020) Leveraging declarative knowledge in text and first-order logic for fine-grained propaganda detection. Red Herring 24:0","journal-title":"Red Herring"},{"key":"15272_CR38","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2018) Exploring visual relationship for image captioning. In: Proceedings of the European conference on computer vision (ECCV), pp 684\u2013699","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"15272_CR39","doi-asserted-by":"crossref","unstructured":"Zhou Y, Chen Z, Yang H (2021) Multimodal learning for hateful memes detection. In: 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, pp 1\u20136","DOI":"10.1109\/ICMEW53276.2021.9455994"},{"key":"15272_CR40","unstructured":"Zhu R (2020) Enhance multimodal transformer with external label and in-domain pretrain: hateful meme challenge winning solution. arXiv:2012.08290"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15272-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15272-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15272-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T13:13:36Z","timestamp":1712063616000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15272-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,30]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["15272"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15272-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,30]]},"assertion":[{"value":"7 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 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 known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}