{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:20:49Z","timestamp":1761895249903,"version":"build-2065373602"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208996","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Hateful Meme Detection via Modality Enhancement and Multi-View Fusion"],"prefix":"10.1109","author":[{"given":"Ying","family":"Zeng","sequence":"first","affiliation":[{"name":"Northeast Forestry University,College of Computer and Control Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiling","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeast Forestry University,College of Computer and Control Engineering,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Lieber Institute for Brain Development,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Auckland,Computer Science Department,Auckland,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"year":"2019","key":"ref2","article-title":"Facebook Hateful Meme Challenge Dataset"},{"key":"ref3","first-page":"2611","article-title":"Hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Kiela"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27824"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599769"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4pi-1.20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592254"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"ref15","first-page":"32","article-title":"Multimodal meme dataset for identifying offensive content in image and text","volume-title":"Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying","author":"Suryawanshi"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref18","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"VisualBERT: A simple and performant baseline for vision and language","year":"2019","author":"Li","key":"ref19"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref21","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref22","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208996.pdf?arnumber=11208996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:46:27Z","timestamp":1761889587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208996","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}