{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T02:26:29Z","timestamp":1770690389252,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":45,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-6957-1_20","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:45:33Z","timestamp":1770633933000},"page":"276-289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DAHM: A Dual-Stream Attention Fusion Model for\u00a0Hate Content Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9101-7622","authenticated-orcid":false,"given":"Qingguan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6451-0524","authenticated-orcid":false,"given":"Jiawei","family":"Cong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9859-8471","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Arya, G., et al.: Multimodal hate speech detection in memes using contrastive language-image pre-training. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3361322"},{"key":"20_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2024.102378","volume":"123","author":"EF Ayetiran","year":"2024","unstructured":"Ayetiran, E.F., \u00d6zg\u00f6bek, \u00d6.: An inter-modal attention-based deep learning framework using unified modality for multimodal fake news, hate speech and offensive language detection. Inf. Syst. 123, 102378 (2024)","journal-title":"Inf. Syst."},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Badjatiya, P., Gupta, S., Gupta, M., Varma, V.: Deep learning for hate speech detection in tweets. In: Proceedings of the 26th International Conference on World Wide Web Companion, pp. 759\u2013760 (2017)","DOI":"10.1145\/3041021.3054223"},{"key":"20_CR4","unstructured":"Brown, T.B.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Cao, R., Lee, R.K.W., Hoang, T.A.: Deephate: hate speech detection via multi-faceted text representations. In: Proceedings of the 12th ACM Conference on Web Science, pp. 11\u201320 (2020)","DOI":"10.1145\/3394231.3397890"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Chatzakou, D., Kourtellis, N., Blackburn, J., De\u00a0Cristofaro, E., Stringhini, G., Vakali, A.: Mean birds: detecting aggression and bullying on twitter. In: Proceedings of the 2017 ACM on Web Science Conference, pp. 13\u201322 (2017)","DOI":"10.1145\/3091478.3091487"},{"key":"20_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108980","volume":"132","author":"C Chen","year":"2022","unstructured":"Chen, C., Han, D., Chang, C.C.: CAAN: context-aware attention network for visual question answering. Pattern Recogn. 132, 108980 (2022)","journal-title":"Pattern Recogn."},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhou, Y., Zhu, S., Xu, H.: Detecting offensive language in social media to protect adolescent online safety. In: 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Conference on Social Computing, pp. 71\u201380. IEEE (2012)","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"key":"20_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106991","volume":"126","author":"A Chhabra","year":"2023","unstructured":"Chhabra, A., Vishwakarma, D.K.: Multimodal hate speech detection via multi-scale visual kernels and knowledge distillation architecture. Eng. Appl. Artif. Intell. 126, 106991 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the International AAAI Conference on Web and Social Media, vol.\u00a011, pp. 512\u2013515 (2017)","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"20_CR11","unstructured":"Devlin, J.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Djuric, N., Zhou, J., Morris, R., Grbovic, M., Radosavljevic, V., Bhamidipati, N.: Hate speech detection with comment embeddings. In: Proceedings of the 24th International Conference on World Wide Web, pp. 29\u201330 (2015)","DOI":"10.1145\/2740908.2742760"},{"key":"20_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"23","key":"20_CR14","doi-asserted-by":"publisher","first-page":"36279","DOI":"10.1007\/s11042-023-14850-y","volume":"82","author":"V Dwivedy","year":"2023","unstructured":"Dwivedy, V., Roy, P.K.: Deep feature fusion for hate speech detection: a transfer learning approach. Multimed. Tools Appl. 82(23), 36279\u201336301 (2023)","journal-title":"Multimed. Tools Appl."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Gamb\u00e4ck, B., Sikdar, U.K.: Using convolutional neural networks to classify hate-speech. In: Proceedings of the First Workshop on Abusive Language Online, pp. 85\u201390 (2017)","DOI":"10.18653\/v1\/W17-3013"},{"issue":"14s","key":"20_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3583067","volume":"55","author":"J Govers","year":"2023","unstructured":"Govers, J., Feldman, P., Dant, A., Patros, P.: Down the rabbit hole: detecting online extremism, radicalisation, and politicised hate speech. ACM Comput. Surv. 55(14s), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Gr\u00f6ndahl, T., Pajola, L., Juuti, M., Conti, M., Asokan, N.: All you need is \u201clove\u201d evading hate speech detection. In: Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security, pp. 2\u201312 (2018)","DOI":"10.1145\/3270101.3270103"},{"key":"20_CR18","unstructured":"Kiela, D., Bhooshan, S., Firooz, H., Perez, E., Testuggine, D.: Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019)"},{"key":"20_CR19","unstructured":"Kiela, D., et al.: The hateful memes challenge: detecting hate speech in multimodal memes. In: Advances in Neural Information Processing Systems, vol. 33, pp. 2611\u20132624 (2020)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Kumar, G.K., Nandakumar, K.: Hate-clipper: multimodal hateful meme classification based on cross-modal interaction of clip features. In: 2nd Workshop on NLP for Positive Impact, NLP4PI 2022 Held in Conjunction with the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, pp. 171\u2013183. Association for Computational Linguistics (ACL) (2022)","DOI":"10.18653\/v1\/2022.nlp4pi-1.20"},{"key":"20_CR21","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":"20_CR22","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 preprint arXiv:1908.03557 (2019)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Lin, H., Luo, Z., Gao, W., Ma, J., Wang, B., Yang, R.: Towards explainable harmful meme detection through multimodal debate between large language models. In: Proceedings of the ACM on Web Conference 2024, pp. 2359\u20132370 (2024)","DOI":"10.1145\/3589334.3645381"},{"key":"20_CR24","unstructured":"Lippe, P., et al.: A multimodal framework for the detection of hateful memes. arXiv preprint arXiv:2012.12871 (2020)"},{"key":"20_CR25","unstructured":"Liu, Y.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"20_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112011","volume":"164","author":"Z Liu","year":"2024","unstructured":"Liu, Z., Yang, T., Chen, W., Chen, J., Li, Q., Zhang, J.: Sentiment analysis of social media comments based on multimodal attention fusion network. Appl. Soft Comput. 164, 112011 (2024)","journal-title":"Appl. Soft Comput."},{"key":"20_CR27","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"2","key":"20_CR28","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1080\/0952813X.2017.1409284","volume":"30","author":"S Malmasi","year":"2018","unstructured":"Malmasi, S., Zampieri, M.: Challenges in discriminating profanity from hate speech. J. Exp. Theor. Artif. Intell. 30(2), 187\u2013202 (2018)","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Mehdad, Y., Tetreault, J.: Do characters abuse more than words? In: Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 299\u2013303 (2016)","DOI":"10.18653\/v1\/W16-3638"},{"key":"20_CR30","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.inffus.2023.03.015","volume":"96","author":"C Min","year":"2023","unstructured":"Min, C., et al.: Finding hate speech with auxiliary emotion detection from self-training multi-label learning perspective. Inf. Fusion 96, 214\u2013223 (2023)","journal-title":"Inf. Fusion"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Nobata, C., Tetreault, J., Thomas, A., Mehdad, Y., Chang, Y.: Abusive language detection in online user content. In: Proceedings of the 25th International Conference on World Wide Web, pp. 145\u2013153 (2016)","DOI":"10.1145\/2872427.2883062"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Park, J.H., Fung, P.: One-step and two-step classification for abusive language detection on twitter. arXiv preprint arXiv:1706.01206 (2017)","DOI":"10.18653\/v1\/W17-3006"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Pramanick, S., et al.: Detecting harmful memes and their targets. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 2783\u20132796 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"20_CR34","doi-asserted-by":"crossref","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 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"20_CR35","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 (2020)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Tekiro\u011flu, S.S., Chung, Y.L., Guerini, M.: Generating counter narratives against online hate speech: data and strategies. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1177\u20131190 (2020)","DOI":"10.18653\/v1\/2020.acl-main.110"},{"key":"20_CR37","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Waseem, Z.: Are you a racist or am i seeing things? Annotator influence on hate speech detection on twitter. In: Proceedings of the First Workshop on NLP and Computational Social Science, pp. 138\u2013142 (2016)","DOI":"10.18653\/v1\/W16-5618"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Waseem, Z., Hovy, D.: Hateful symbols or hateful people? Predictive features for hate speech detection on twitter. In: Proceedings of the NAACL Student Research Workshop, pp. 88\u201393 (2016)","DOI":"10.18653\/v1\/N16-2013"},{"issue":"4","key":"20_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103772","volume":"61","author":"F Wu","year":"2024","unstructured":"Wu, F., et al.: Fuser: an enhanced multimodal fusion framework with congruent reinforced perceptron for hateful memes detection. Inf. Process. Manag. 61(4), 103772 (2024)","journal-title":"Inf. Process. Manag."},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Xiang, G., Fan, B., Wang, L., Hong, J., Rose, C.: Detecting offensive tweets via topical feature discovery over a large scale twitter corpus. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management, pp. 1980\u20131984 (2012)","DOI":"10.1145\/2396761.2398556"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhu, F., Han, J., Hu, S.: Invariant meets specific: a scalable harmful memes detection framework. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4788\u20134797 (2023)","DOI":"10.1145\/3581783.3611761"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhu, F., Liu, G., Han, J., Hu, S.: Multimodal hate speech detection via cross-domain knowledge transfer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4505\u20134514 (2022)","DOI":"10.1145\/3503161.3548255"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: Tot: topology-aware optimal transport for multimodal hate detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 4884\u20134892 (2023)","DOI":"10.1609\/aaai.v37i4.25614"},{"key":"20_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1007\/978-3-319-93417-4_48","volume-title":"The Semantic Web","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Robinson, D., Tepper, J.: Detecting hate speech on twitter using a convolution-GRU based deep neural network. In: Gangemi, A., Navigli, R., Vidal, M.-E., Hitzler, P., Troncy, R., Hollink, L., Tordai, A., Alam, M. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 745\u2013760. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93417-4_48"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:45:44Z","timestamp":1770633944000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}