{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:39:40Z","timestamp":1772120380329,"version":"3.50.1"},"reference-count":49,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3535694","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:46:46Z","timestamp":1738090006000},"page":"42530-42546","source":"Crossref","is-referenced-by-count":3,"title":["CAMFusion: Context-Aware Multi-Modal Fusion Framework for Detecting Sarcasm and Humor Integrating Video and Textual Cues"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3859-8832","authenticated-orcid":false,"given":"Musfequa","family":"Rahman","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1203-3331","authenticated-orcid":false,"given":"Md.","family":"Al-Mamun Provath","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7345-0999","authenticated-orcid":false,"given":"Kaushik","family":"Deb","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9664-3056","authenticated-orcid":false,"given":"Pranab","family":"Kumar Dhar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7874-3467","authenticated-orcid":false,"given":"Tetsuya","family":"Shimamura","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Sciences, Saitama University, Saitama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctim.2011.05.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1093"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1211"},{"key":"ref6","first-page":"1875","article-title":"Exploiting syntactic structures for humor recognition","volume-title":"Proc. COLING","author":"Liu"},{"key":"ref7","first-page":"1","article-title":"Jose E Med-\u2019 ina Pagola, and Paolo Rosso. UO UPV: Deep linguistic humor detection in Spanish social media","volume-title":"Proc. Workshop Eval. Human Lang. Technol. Iberian Lang.","author":"Ortega-Bueno"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479959"},{"key":"ref11","first-page":"45","article-title":"Memotion: A dataset for multimodal sentiment analysis and humor detection in memes","volume-title":"Proc. Workshop Lang. Technol.","author":"Kumar"},{"key":"ref12","first-page":"167","article-title":"ColBERT: Using BERT sentence embedding for humor detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Annamoradnejad"},{"key":"ref13","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL Conf.","author":"Devlin"},{"key":"ref14","first-page":"578","article-title":"Multimodal sarcasm detection: An analysis of gestures, tone, and text","volume":"28","author":"Jain","year":"2021","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"ref15","first-page":"123","article-title":"Cultural and linguistic challenges in multimodal emotion recognition for Bangla","volume":"42","author":"Banerjee","year":"2019","journal-title":"J. Human-Comput. Interact."},{"key":"ref16","first-page":"459","article-title":"Spatio-temporal feature extraction using 3D CNNs for emotion detection in video data","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Reddy"},{"issue":"4","key":"ref17","first-page":"862","article-title":"X3D networks for efficient spatiotemporal learning","volume":"44","author":"Kim","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref18","first-page":"1241","article-title":"Keyframe selection for video text extraction: A comparative study","volume":"19","author":"Doe","year":"2017","journal-title":"IEEE Trans. Multimedia"},{"key":"ref19","first-page":"103","article-title":"Challenges in optical character recognition for multimodal video frames","volume-title":"Proc. Int. Conf. Vis. Image Process.","author":"Singh"},{"key":"ref20","article-title":"Align before attend: Aligning visual and textual features for multimodal hateful content detection","author":"Hossain","year":"2024","journal-title":"arXiv:2402.09738"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT60459.2023.10441342"},{"key":"ref22","first-page":"95","article-title":"Affect-GCN: A multimodal graph convolutional network for multi-emotion with intensity recognition","volume":"11","author":"Firdaus","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref23","first-page":"89","article-title":"Interpretable multimodal emotion recognition using hybrid fusion of speech and image data","volume":"29","author":"Kumar","year":"2023","journal-title":"J. Artif. Intell. Res."},{"key":"ref24","first-page":"56","article-title":"A multimodal graph convolutional network for humor detection","volume":"12","author":"Firdaus","year":"2023","journal-title":"IEEE Trans. Cognit. Neural Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3419004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4914-4_11"},{"key":"ref27","first-page":"35","article-title":"Humor in intercultural interaction: A source for misunderstanding or a common ground builder?","volume":"32","author":"Ladilova","year":"2022","journal-title":"Int. J. Cross-Cultural Stud."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-65358-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484448"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref32","first-page":"1","article-title":"Computationally recognizing wordplay in jokes","volume":"12","author":"Taylor","year":"2004","journal-title":"J. Artif. Intell. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2018"},{"key":"ref34","first-page":"1","article-title":"A multimodal emotion recognition model integrating speech","volume":"14","author":"Jia","year":"2022","journal-title":"J. Multimodal AI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746418"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref37","first-page":"56","article-title":"Towards multimodal sarcasm detection","volume":"13","author":"Castro","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554802"},{"key":"ref39","first-page":"156","article-title":"Towards multimodal prediction of time-continuous emotion using pose feature engineering","volume-title":"Proc. Int. Conf. Pattern Recognit.","author":"Park"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1372"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08836-3"},{"key":"ref42","first-page":"67","article-title":"Memotion 2: Dataset on sentiment and emotion analysis of memes","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Ramamoorthy"},{"key":"ref43","first-page":"98","article-title":"Lets all laugh together: A novel multitask framework for humor detection in Internet memes","volume":"29","author":"Kumari","year":"2024","journal-title":"J. Comput. Linguistics"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-srw.5"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.06.010"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101386"},{"key":"ref49","first-page":"1542","article-title":"MemoSen: A multimodal dataset for sentiment analysis of memes","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Hossain"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10856108.pdf?arnumber=10856108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:48:15Z","timestamp":1741801695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3535694","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}