{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:51:17Z","timestamp":1781772677346,"version":"3.54.5"},"reference-count":49,"publisher":"China Science Publishing & Media Ltd.","issue":"2","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.3724\/2096-7004.di.2025.0121","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T07:06:36Z","timestamp":1758524796000},"page":"20250121","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Hate Speech Detection Framework Based on Multi-level Cross-modal Attention and Gated Fusion"],"prefix":"10.3724","volume":"8","author":[{"given":"Rui","family":"Lv","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lirong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"null","unstructured":"Shelke S. and Attar V., \u201cSource detection of rumor in social network\u2014A review,\u201d Online Social Networks and Media, vol. 9, pp. 30\u201342, 2019."},{"key":"null","unstructured":"Plaza-del Arco F. M., Molina-Gonz\u00e1lez M. D., Urena-L\u00f3pez L. A., and Mart\u00edn-Valdivia M. T., \u201cComparing pretrained language models for Spanish hate speech detection,\u201d Expert Syst. Appl., vol. 166, p. 114120, 2021."},{"key":"null","unstructured":"Tsesis A., Destructive Messages: How Hate Speech Paves the Way for Harmful Social Movements. New York, NY, USA: NYU Press, 2002, vol. 27."},{"key":"null","unstructured":"Lupu Y. et al., \u201cOffline events and online hate,\u201d PLoS ONE, vol. 18, no. 1, p. e0278511, 2023."},{"key":"null","unstructured":"Arya G. et al., \u201cMultimodal hate speech detection in memes using contrastive language-image pre-training,\u201d IEEE Access, vol. 12, pp. 22359\u201322375, 2024."},{"key":"null","unstructured":"Masud S., Bedi M., Khan M. A., Akhtar M. S., and Chakraborty T., \u201cProactively reducing the hate intensity of online posts via hate speech normalization,\u201d in Proc. 28th ACM SIGKDD Conf. Knowl. Discovery Data Mining, 2022, pp. 3524\u20133534."},{"key":"null","unstructured":"Rajput G., Punn N. S., Sonbhadra S. K., and Agarwal S., \u201cHate speech detection using static BERT embeddings,\u201d in Big Data Analytics, 9th Int. Conf., BDA 2021, Virtual Event, Dec. 15\u201318, 2021, Proc. 9. Springer, 2021, pp. 67\u201377."},{"key":"null","unstructured":"Schmidt A. and Wiegand M., \u201cA survey on hate speech detection using natural language processing,\u201d in Proc. 5th Int. Workshop Natural Lang. Process. Social Media, 2017, pp. 1\u201310."},{"key":"null","unstructured":"Fortuna P., Soler-Company J., and Wanner L., \u201cHow well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets?\u201d Inf. Process. Manage., vol. 58, no. 3, p. 102524, 2021."},{"key":"null","unstructured":"Mathew B., Saha P., Yimam S. M., Biemann C., Goyal P., and Mukherjee A., \u201cHateXplain: A benchmark dataset for explainable hate speech detection,\u201d in Proc. AAAI Conf. Artif. Intell., vol. 35, 2021, pp. 14867\u201314875."},{"key":"null","unstructured":"Masud S., Khan M. A., Akhtar M. S., and Chakraborty T., \u201cOverview of the HASOC subtrack at FIRE 2023: Identification of tokens contributing to explicit hate in English by span detection,\u201d arXiv preprint, arXiv:2311.09834, 2023."},{"key":"null","unstructured":"Sap M., Gabriel S., Qin L., Jurafsky D., Smith N. A., and Choi Y., \u201cSocial bias frames: Reasoning about social and power implications of language,\u201d arXiv preprint, arXiv:1911.03891, 2019."},{"key":"null","unstructured":"Sharif W., Abdullah S., Iftikhar S., Al-Madani D., and Mumtaz S., \u201cEnhancing hate speech detection in the digital age: A novel model fusion approach leveraging a comprehensive dataset,\u201d IEEE Access, 2024."},{"key":"null","unstructured":"ElSherief M. et al., \u201cLatent hatred: A benchmark for understanding implicit hate speech,\u201d arXiv preprint, arXiv:2109.05322, 2021."},{"key":"null","unstructured":"Kim Y., Park S., and Han Y.-S., \u201cGeneralizable implicit hate speech detection using contrastive learning,\u201d in Proc. 29th Int. Conf. Comput. Linguistics, 2022, pp. 6667\u20136679."},{"key":"null","unstructured":"Ghosh S., Suri M., Chiniya P., Tyagi U., Kumar S., and Manocha D., \u201cCosyn: Detecting implicit hate speech in online conversations using a context synergized hyperbolic network,\u201d arXiv preprint, arXiv:2303.03387, 2023."},{"key":"null","unstructured":"Lu J. et al., \u201cHate speech detection via dual contrastive learning,\u201d IEEE\/ACM Trans. Audio, Speech, Lang. Process., vol. 31, pp. 2787\u20132795, 2023."},{"key":"null","unstructured":"Prabhu R. and Seethalakshmi V., \u201cA comprehensive framework for multi-modal hate speech detection in social media using deep learning,\u201d Sci. Rep., vol. 15, no. 1, p. 13020, 2025."},{"key":"null","unstructured":"Kiela D. et al., \u201cThe hateful memes challenge: Detecting hate speech in multimodal memes,\u201d Adv. Neural Inf. Process. Syst., vol. 33, pp. 2611\u20132624, 2020."},{"key":"null","unstructured":"Gomez R., Gibert J., Gomez L., and Karatzas D., \u201cExploring hate speech detection in multimodal publications,\u201d in Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV), 2020, pp. 1470\u20131478."},{"key":"null","unstructured":"Hosseinmardi H., Rafiq R. I., Han R., Lv Q., and Mishra S., \u201cPrediction of cyberbullying incidents in a media-based social network,\u201d in Proc. IEEE\/ACM Int. Conf. Adv. Social Netw. Anal. Mining (ASONAM), 2016, pp. 186\u2013192."},{"key":"null","unstructured":"Maity K., Jha P., Saha S., and Bhattacharyya P., \u201cA multitask framework for sentiment, emotion and sarcasm aware cyberbullying detection from multi-modal code-mixed memes,\u201d in Proc. 45th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr., 2022, pp. 1739\u20131749."},{"key":"null","unstructured":"Lee R. K.-W., Cao R., Fan Z., Jiang J., and Chong W.-H., \u201cDisentangling hate in online memes,\u201d in Proc. 29th ACM Int. Conf. Multimedia, 2021, pp. 5138\u20135147."},{"key":"null","unstructured":"Cao R., Hee M. S., Kuek A., Chong W.-H., Lee R. K.-W., and Jiang J., \u201cPro-Cap: Leveraging a frozen vision-language model for hateful meme detection,\u201d in Proc. 31st ACM Int. Conf. Multimedia, 2023, pp. 5244\u20135252."},{"key":"null","unstructured":"Ayetiran E. F. and \u00d6zg\u00f6bek \u00d6., \u201cAn inter-modal attention-based deep learning framework using unified modality for multimodal fake news, hate speech and offensive language detection,\u201d Inf. Syst., vol. 123, p. 102378, 2024."},{"key":"null","unstructured":"Xu B., Yu E., Zhou J., Lin H., and Zong L., \u201cHyperHatePrompt: A hypergraph-based prompting fusion model for multimodal hate detection,\u201d in Proc. 31st Int. Conf. Comput. Linguistics, 2025, pp. 3825\u20133835."},{"key":"null","unstructured":"Loureiro D. et al., \u201cTweet insights: A visualization platform to extract temporal insights from Twitter,\u201d arXiv preprint, arXiv:2308.02142, 2023."},{"key":"null","unstructured":"Liu Z. et al., \u201cSwin Transformer V2: Scaling up capacity and resolution,\u201d in Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 12009\u201312019."},{"key":"null","unstructured":"Liu Z. et al., \u201cSwin Transformer: Hierarchical vision transformer using shifted windows,\u201d in Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), 2021, pp. 10012\u201310022."},{"key":"null","unstructured":"Fersini E. et al., \u201cSemEval-2022 task 5: Multimedia automatic misogyny identification,\u201d in Proc. 16th Int. Workshop Semantic Eval. (SemEval-2022), 2022, pp. 533\u2013549."},{"key":"null","unstructured":"Bhandari A., Shah S. B., Thapa S., Naseem U., and Nasim M., \u201cCrisisHateMM: Multimodal analysis of directed and undirected hate speech in text-embedded images from Russia-Ukraine conflict,\u201d in Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2023, pp. 1994\u20132003."},{"key":"null","unstructured":"Devlin J., Chang M.-W., Lee K., and Toutanova K., \u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d in Proc. North Am. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol., Vol. 1 (Long and Short Papers), 2019, pp. 4171\u20134186."},{"key":"null","unstructured":"Liu Y. et al., \u201cRoBERTa: A robustly optimized BERT pretraining approach,\u201d arXiv preprint, arXiv:1907.11692, 2019."},{"key":"null","unstructured":"Lan Z., Chen M., Goodman S., Gimpel K., Sharma P., and Soricut R., \u201cALBERT: A lite BERT for self-supervised learning of language representations,\u201d arXiv preprint, arXiv:1909.11942, 2019."},{"key":"null","unstructured":"Sanh V., Debut L., Chaumond J., and Wolf T., \u201cDistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter,\u201d arXiv preprint, arXiv:1910.01108, 2019."},{"key":"null","unstructured":"Szegedy C., Vanhoucke V., Ioffe S., Shlens J., and Wojna W., \u201cRethinking the inception architecture for computer vision,\u201d in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818\u20132826."},{"key":"null","unstructured":"He K., Zhang X., Ren S., and Sun J., \u201cDeep residual learning for image recognition,\u201d in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770\u2013778."},{"key":"null","unstructured":"Huang G., Liu Z., Van Der Maaten L., and Weinberger K. Q., \u201cDensely connected convolutional networks,\u201d in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4700\u20134708."},{"key":"null","unstructured":"Li L. H., Yatskar M., Yin D., Hsieh C.-J., and Chang K.-W., \u201cVisualBERT: A simple and performant baseline for vision and language,\u201d arXiv preprint, arXiv:1908.03557, 2019."},{"key":"null","unstructured":"Radford A. et al., \u201cLearning transferable visual models from natural language supervision,\u201d in Proc. Int. Conf. Mach. Learn. (ICML), 2021, pp. 8748\u20138763."},{"key":"null","unstructured":"Kim W., Son B., and Kim I., \u201cViLT: Vision-and-language transformer without convolution or region supervision,\u201d in Proc. Int. Conf. Mach. Learn. (ICML), 2021, pp. 5583\u20135594."},{"key":"null","unstructured":"Singh A. et al., \u201cFLAVA: A foundational language and vision alignment model,\u201d in Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 15638\u201315650."},{"key":"null","unstructured":"Li J., Li D., Xiong C., and Hoi S., \u201cBLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,\u201d in Proc. Int. Conf. Mach. Learn. (ICML), 2022, pp. 12888\u201312900."},{"key":"null","unstructured":"Yamagishi Y., \u201cYYama@ Multimodal Hate Speech Event Detection 2024: Simpler prompts, better results\u2014Enhancing zero-shot detection with a large multimodal model,\u201d in Proc. 7th Workshop Challenges Appl. Automated Extraction Socio-Political Events Text (CASE 2024), 2024, pp. 60\u201366."},{"key":"null","unstructured":"Ganguly A., Emran A. N. B., Puspo S. S. C., Raihan M. N., Goswami D., and Zampieri M., \u201cMasonPerplexity at Multimodal Hate Speech Event Detection 2024: Hate speech and target detection using transformer ensembles,\u201d arXiv preprint, arXiv:2402.01967, 2024."},{"key":"null","unstructured":"Sahin U., Kucukkaya I. E., Ozcelik O., and Toraman C., \u201cARC-NLP at Multimodal Hate Speech Event Detection 2023: Multimodal methods boosted by ensemble learning, syntactical and entity features,\u201d arXiv preprint, arXiv:2307.13829, 2023."},{"key":"null","unstructured":"El-Sayed A. and Nasr O., \u201cAAST-NLP at Multimodal Hate Speech Event Detection 2024: A multimodal approach for classification of text-embedded images based on CLIP and BERT-based models,\u201d in Proc. 7th Workshop Challenges Appl. Automated Extraction Socio-Political Events Text (CASE 2024), 2024, pp. 139\u2013144."},{"key":"null","unstructured":"Wang Y. and Markov I., \u201cCLTL@ Multimodal Hate Speech Event Detection 2024: The winning approach to detecting multimodal hate speech and its targets,\u201d in Proc. 7th Workshop Challenges Appl. Automated Extraction Socio-Political Events Text (CASE 2024), 2024, pp. 73\u201378."},{"key":"null","unstructured":"Cao R., Lee R. K.-W., Chong W.-H., and Jiang J., \u201cPrompting for multimodal hateful meme classification,\u201d arXiv preprint, arXiv:2302.04156, 2023."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/FA46D8C4FD6845719C1ABBCABE6CEA21","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0121","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/FA46D8C4FD6845719C1ABBCABE6CEA21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:57:31Z","timestamp":1781769451000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":49,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,22]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0121","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}