{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:26:59Z","timestamp":1781281619621,"version":"3.54.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001420","name":"Institute of Information & Communications Technology Planning & Evaluation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001420","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government [Ministry of Science and Information Technology (MSIT)]","award":["2019-0-00231"],"award-info":[{"award-number":["2019-0-00231"]}]},{"name":"Information Technology Research Center (ITRC) Support Program","award":["IITP-2022-RS-2022-00156354"],"award-info":[{"award-number":["IITP-2022-RS-2022-00156354"]}]},{"name":"Basic Science Research Program through the National Research Foundation of Korea"},{"name":"Ministry of Education","award":["2020R1A6A1A03038540"],"award-info":[{"award-number":["2020R1A6A1A03038540"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3424883","type":"journal-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T17:41:32Z","timestamp":1720460492000},"page":"125993-126005","source":"Crossref","is-referenced-by-count":6,"title":["Meme Analysis Using LLM-Based Contextual Information and U-Net Encapsulated Transformer"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2145-934X","authenticated-orcid":false,"given":"Marvin","family":"John Ignacio","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Sejong University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6798-9808","authenticated-orcid":false,"given":"Thanh","family":"Tin Nguyen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6896-2498","authenticated-orcid":false,"given":"Hulin","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4645-1395","authenticated-orcid":false,"given":"Yong-Guk","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Sejong University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.99"},{"key":"ref2","first-page":"1","article-title":"Memotion 2: Dataset on sentiment and emotion analysis of memes","volume-title":"Proc. De-Factify, Workshop Multimodal Fact Checking Hate Speech Detection","author":"Ramamoorthy"},{"key":"ref3","article-title":"Memotion 3: Dataset on sentiment and emotion analysis of codemixed Hindi-English memes","author":"Mishra","year":"2022","journal-title":"arXiv:2303.09892"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18280\/mmep.090232"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.148"},{"key":"ref6","first-page":"0073","article-title":"Amazon pars at memotion 2.0 2022: Multi-modal multi-task learning for memotion 2.0 challenge","volume":"1613","author":"Lee","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.153"},{"key":"ref9","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"K Simonyan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.159"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.112"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.160"},{"key":"ref16","article-title":"Blue at memotion 2.0 2022: You have my image, my text and my transformer","author":"Bucur","year":"2022","journal-title":"arXiv:2202.07543"},{"key":"ref17","article-title":"NYCU-TWO at memotion 3: Good foundation, good teacher, then you have good meme analysis","author":"Tang","year":"2023","journal-title":"arXiv:2302.06078"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26166"},{"key":"ref19","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref20","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref21","first-page":"1","article-title":"Yet at memotion 2.0 2022: Hate speech detection combining BiLSTM and fully connected layers","volume-title":"Proc. De-Factify, Workshop Multimodal Fact Checking Hate Speech Detection","author":"Zhuang"},{"key":"ref22","first-page":"1","article-title":"Little flower at memotion 2.0 2022: Ensemble of multi-modal model using attention mechanism in memotion analysis","volume-title":"Proc. De-Factify, Workshop Multimodal Fact Checking Hate Speech Detection","author":"Phan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.154"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.149"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.150"},{"key":"ref26","first-page":"1","article-title":"Browallia at memotion 2.0 2022: Multimodal memotion analysis with modified OGB strategies","volume-title":"Proc. Workshop Multimodal Fact Checking Hate Speech Detection","author":"Duan"},{"key":"ref27","first-page":"1","article-title":"HCILab at memotion 2.0 2022: Analysis of sentiment, emotion and intensity of emotion classes from meme images using single and multi modalities","volume-title":"Proc. AAAI","author":"Nguyen"},{"key":"ref28","article-title":"NUAA-QMUL-AIIT at memotion 3: Multi-modal fusion with squeeze-and-excitation for Internet meme emotion analysis","author":"Guo","year":"2023","journal-title":"arXiv:2302.08326"},{"key":"ref29","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111778"},{"key":"ref32","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref33","volume-title":"GPT-4","year":"2023"},{"key":"ref34","volume-title":"KeyBERT","author":"Grootendorst","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref39","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref40","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref41","first-page":"1","article-title":"Findings of memotion 2: Sentiment and emotion analysis of memes","volume-title":"Proc. De-Factify, Workshop Multimodal Fact Checking Hate Speech Detection","author":"Patwa"},{"key":"ref42","article-title":"Overview of memotion 3: Sentiment and emotion analysis of codemixed hinglish memes","author":"Mishra","year":"2023","journal-title":"arXiv:2309.06517"},{"key":"ref43","article-title":"Wave-U-net: A multi-scale neural network for end-to-end audio source separation","author":"Stoller","year":"2018","journal-title":"arXiv:1806.03185"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.petrol.2021.109901"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10589379.pdf?arnumber=10589379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T06:21:59Z","timestamp":1726640519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10589379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3424883","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}