{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T09:24:36Z","timestamp":1780997076151,"version":"3.54.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["U22A2099"],"award-info":[{"award-number":["U22A2099"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62336003"],"award-info":[{"award-number":["62336003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/taffc.2024.3481419","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T17:59:40Z","timestamp":1729101580000},"page":"933-945","source":"Crossref","is-referenced-by-count":5,"title":["SCARE: A Novel Framework to Enhance Chinese Harmful Memes Detection"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1593-1292","authenticated-orcid":false,"given":"Tianlong","family":"Gu","sequence":"first","affiliation":[{"name":"College of Information Science and Technology\/ College of Cyber Security, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfeng","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer and Information Security, Guilin University of Electronic Science and Technology, Guilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1661-6590","authenticated-orcid":false,"given":"Xuan","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology\/ College of Cyber Security, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-8443","authenticated-orcid":false,"given":"Xuemin","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Science and Technology, Guilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3171091"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3219229"},{"key":"ref3","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kiela"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611761"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/665"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4pi-1.20"},{"key":"ref11","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"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.738"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455994"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.254"},{"key":"ref15","article-title":"Detecting hate speech in multi-modal memes","author":"Das","year":"2020"},{"key":"ref16","article-title":"Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge","author":"Velioglu","year":"2020"},{"key":"ref17","article-title":"Vilio: State-of-the-art visio-linguistic models applied to hateful memes","author":"Muennighoff","year":"2020"},{"key":"ref18","article-title":"A multimodal framework for the detection of hateful memes","author":"Lippe","year":"2020"},{"key":"ref19","article-title":"Hateful memes detection via complementary visual and linguistic networks","author":"Zhang","year":"2020"},{"key":"ref20","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref21","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref25","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref26","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref27","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Su"},{"key":"ref28","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref29","first-page":"1","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.552"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26263"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56069-9_68"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref39","article-title":"Supervised multimodal bitransformers for classifying images and text","author":"Kiela","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"ref41","article-title":"Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution","author":"Zhu","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3501247.3531557"},{"key":"ref43","first-page":"1","article-title":"Detecting hateful memes using a multimodal deep ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sandulescu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.118"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.157"},{"issue":"5","key":"ref46","article-title":"Rizzi, giulia and gasparini, francesca and saibene, aurora and rosso, paolo and fersini, elisabetta","volume":"60","author":"Rizzi","year":"2023","journal-title":"Inf. Process. Manage."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1004"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3204972"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.567"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref61","article-title":"Prompt tuning based adapter for vision-language model adaption","author":"Sun","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCS57501.2023.10151313"},{"key":"ref64","first-page":"1","article-title":"Consistency-guided prompt learning for vision-language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shuvendu Roy"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00556"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28568"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2012.031"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref70","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref71","first-page":"531","article-title":"MINE: Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648145"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648146"},{"key":"ref79","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11018643\/10720078.pdf?arnumber=10720078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T18:01:54Z","timestamp":1748887314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":79,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3481419","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}