{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:40:09Z","timestamp":1759236009221,"version":"3.44.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206267"],"award-info":[{"award-number":["62206267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3581795","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:29:00Z","timestamp":1750426140000},"page":"6397-6409","source":"Crossref","is-referenced-by-count":0,"title":["Flexible Optimal Transport With Contrastive Graphical Modeling for Multimodal Hate Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2631-0555","authenticated-orcid":false,"given":"Linhao","family":"Zhang","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-4862","authenticated-orcid":false,"given":"Li","family":"Jin","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0286-6660","authenticated-orcid":false,"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"given":"Zequn","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4728-5678","authenticated-orcid":false,"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7520-7799","authenticated-orcid":false,"given":"Zhicong","family":"Lu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Guangluan","family":"Xu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute and the Key Laboratory of Target Cognition and Application Technology (TCAT), Institute of Electronics, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260635"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"article-title":"Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution","year":"2020","author":"Zhu","key":"ref3"},{"article-title":"A multimodal framework for the detection of hateful memes","year":"2020","author":"Lippe","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157993"},{"article-title":"Detecting hate speech in multi-modal memes","year":"2020","author":"Das","key":"ref6"},{"article-title":"Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge","year":"2020","author":"Velioglu","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3201387"},{"key":"ref10","first-page":"1880","article-title":"Unsupervised alignment of embeddings with Wasserstein procrustes","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","volume":"89","author":"Grave","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"ref12","first-page":"29512","article-title":"Unified optimal transport framework for universal domain adaptation","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Chang","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3157139"},{"key":"ref14","first-page":"128","article-title":"Merging datasets for aggressive text identification","volume-title":"Proc. 1st Workshop Trolling, Aggression Cyberbullying","author":"Fortuna","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2017.1409284"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.110"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tetci.2024.3406691"},{"key":"ref20","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Kiela","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.woah-1.23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref23","first-page":"32","article-title":"Multimodal meme dataset (multioff) for identifying offensive content in image and text","volume-title":"Proc. 2nd Workshop Trolling, Aggression Cyberbullying","author":"Suryawanshi","year":"2020"},{"article-title":"UNITER: Learning universal image-text representations","year":"2019","author":"Chen","key":"ref24"},{"article-title":"VisualBERT: A simple and performant baseline for vision and language","year":"2019","author":"Li","key":"ref25"},{"key":"ref26","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Gan","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3230331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321535"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.571"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1512"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref34","article-title":"A trainable optimal transport embedding for feature aggregation and its relationship to attention","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Mialon","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2009.230"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"article-title":"RoBERTa: A robustly optimized BERT pretraining approach","year":"2019","author":"Liu","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Supervised multimodal bitransformers for classifying images and text","year":"2019","author":"Kiela","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25614"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11045556.pdf?arnumber=11045556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:19:41Z","timestamp":1759234781000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3581795","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}