{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T14:48:58Z","timestamp":1780066138021,"version":"3.54.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416750","type":"print"},{"value":"9783031416767","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-41676-7_31","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"534-551","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["MemeGraphs: Linking Memes to\u00a0Knowledge Graphs"],"prefix":"10.1007","author":[{"given":"Vasiliki","family":"Kougia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Fetzel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Kirchmair","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erion","family":"\u00c7ano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sina Moayed","family":"Baharlou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahand","family":"Sharifzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Roth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"31_CR1","doi-asserted-by":"publisher","unstructured":"Aggarwal, P., Liman, M.E., Gold, D., Zesch, T.: VL-BERT+: detecting protected groups in hateful multimodal memes. In: Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pp. 207\u2013214. Online, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.woah-1.22","DOI":"10.18653\/v1\/2021.woah-1.22"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Henrique Luz de Araujo, P., Roth, B.: Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection. In: Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, pp. 75\u201383. Dublin, Ireland (2022)","DOI":"10.18653\/v1\/2022.nlppower-1.8"},{"key":"31_CR3","unstructured":"Behera, P., Mamta, Ekbal, A.: Only text? Only image? Or both? Predicting sentiment of internet memes. In: Proceedings of the 17th International Conference on Natural Language Processing (ICON), pp. 444\u2013452. Indian Institute of Technology Patna, Patna, India (2020). https:\/\/aclanthology.org\/2020.icon-main.60"},{"key":"31_CR4","doi-asserted-by":"publisher","unstructured":"Blaier, E., Malkiel, I., Wolf, L.: Caption enriched samples for improving hateful memes detection. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 9350\u20139358. Online and Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.738","DOI":"10.18653\/v1\/2021.emnlp-main.738"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Aguilar, G., Neves, L., Solorio, T.: Can images help recognize entities? A study of the role of images for multimodal NER. In: Proceedings of the 2021 EMNLP Workshop W-NUT: The Seventh Workshop on Noisy User-Generated Text, pp. 87\u201396. Online and Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.wnut-1.11"},{"key":"31_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"31_CR7","unstructured":"Das, A., Wahi, J.S., Li, S.: Detecting hate speech in multi-modal memes. arXiv preprint: arXiv:2012.14891 (2020)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Miami Beach, FL, USA (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"31_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: 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. Minneapolis, Minnesota, USA (2019)"},{"key":"31_CR10","doi-asserted-by":"publisher","unstructured":"Dimitrov, D., et al.: 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. Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.516","DOI":"10.18653\/v1\/2021.acl-long.516"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Fersini, E., et al.: SemEval-2022 task 5: Multimedia automatic misogyny identification. In: Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pp. 533\u2013549. Seattle, United States (2022)","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"31_CR12","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. arXiv:2006.06195 (2020)"},{"key":"31_CR13","first-page":"2611","volume":"33","author":"D Kiela","year":"2020","unstructured":"Kiela, D., et al.: The hateful memes challenge: detecting hate speech in multimodal memes. Adv. Neural. Inf. Process. Syst. 33, 2611\u20132624 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR14","doi-asserted-by":"publisher","unstructured":"Kougia, V., Pavlopoulos, J.: Multimodal or text? Retrieval or BERT? Benchmarking classifiers for the shared task on hateful memes. In: Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pp. 220\u2013225. Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.woah-1.24","DOI":"10.18653\/v1\/2021.woah-1.24"},{"issue":"1","key":"31_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., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Lee, R.K.W., Cao, R., Fan, Z., Jiang, J., Chong, W.H.: Disentangling hate in online memes. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5138\u20135147 (2021)","DOI":"10.1145\/3474085.3475625"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Ataman, D., Sennrich, R.: Vision matters when it should: sanity checking multimodal machine translation models. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 8556\u20138562. Online and Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.673"},{"key":"31_CR18","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv:1908.03557 (2019)"},{"key":"31_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"31_CR20","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv:1908.02265 (2019)"},{"key":"31_CR21","doi-asserted-by":"publisher","unstructured":"Mathias, L., et al.: Findings of the WOAH 5 shared task on fine grained hateful memes detection. In: Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pp. 201\u2013206. Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.woah-1.21","DOI":"10.18653\/v1\/2021.woah-1.21"},{"key":"31_CR22","unstructured":"Mozes, M., Schmitt, M., Golkov, V., Sch\u00fctze, H., Cremers, D.: Scene graph generation for better image captioning? arXiv:2109.11398 (2021)"},{"key":"31_CR23","doi-asserted-by":"publisher","unstructured":"Pramanick, S., Sharma, S., Dimitrov, D., Akhtar, M.S., Nakov, P., Chakraborty, T.: MOMENTA: a multimodal framework for detecting harmful memes and their targets. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 4439\u20134455. Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.379","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"31_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"issue":"2","key":"31_CR25","first-page":"2189","volume":"36","author":"S Sharifzadeh","year":"2022","unstructured":"Sharifzadeh, S., Baharlou, S.M., Schmitt, M., Sch\u00fctze, H., Tresp, V.: Improving scene graph classification by exploiting knowledge from texts. Proc. AAAI Conf. Artif. Intell. 36(2), 2189\u20132197 (2022)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Sharifzadeh, S., Baharlou, S.M., Tresp, V.: Classification by attention: scene graph classification with prior knowledge. In: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), pp. 5025\u20135033. Online (2021)","DOI":"10.1609\/aaai.v35i6.16636"},{"key":"31_CR27","unstructured":"Su, W., et al.: Vl-BERT: pre-training of generic visual-linguistic representations. arXiv:1908.08530 (2019)"},{"key":"31_CR28","unstructured":"Suryawanshi, S., Chakravarthi, B.R., Arcan, M., Buitelaar, P.: Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text. In: Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, pp. 32\u201341. Marseille, France (2020). https:\/\/aclanthology.org\/2020.trac-1.6"},{"key":"31_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01246-5_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Yang","year":"2018","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Graph R-CNN for scene graph\u00a0generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_41"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694. Long Beach, CA, USA (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Yin, Y., Meng, F., Su, J., Zhou, C., Yang, Z., Zhou, J., Luo, J.: A novel graph-based multi-modal fusion encoder for neural machine translation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 3025\u20133035. Online and Punta Cana, Dominican Republic (2020)","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"31_CR33","unstructured":"Zhu, R.: Enhance multimodal transformer with external label and in-domain pretrain: hateful meme challenge winning solution. arXiv:2012.08290 (2020)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41676-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:09:10Z","timestamp":1692342550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41676-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416750","9783031416767"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41676-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}