{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:30:08Z","timestamp":1774420208016,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887864","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Intra-modal Relation and Emotional Incongruity Learning using Graph Attention Networks for Multimodal Sarcasm Detection"],"prefix":"10.1109","author":[{"given":"Devraj","family":"Raghuvanshi","sequence":"first","affiliation":[{"name":"Brown University,USA"}]},{"given":"Xiyuan","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Groningen,the Netherlands"}]},{"given":"Zhu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Groningen,the Netherlands"}]},{"given":"Shubhi","family":"Bansal","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Indore,India"}]},{"given":"Matt","family":"Coler","sequence":"additional","affiliation":[{"name":"University of Groningen,the Netherlands"}]},{"given":"Nagendra","family":"Kumar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Indore,India"}]},{"given":"Shekhar","family":"Nayak","sequence":"additional","affiliation":[{"name":"University of Groningen,the Netherlands"}]}],"member":"263","reference":[{"key":"ref1","first-page":"143","article-title":"Irony and the use-mention distinction","volume":"3","author":"Sperber","year":"1981","journal-title":"Philosophy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.115.1.3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3380375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112109"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28766"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1455"},{"key":"ref8","first-page":"6992","article-title":"A multimodal corpus for emotion recognition in sarcasm","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Ray"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.988"},{"key":"ref10","article-title":"Sarcasm in sight and sound: Benchmarking and expansion to improve multimodal sarcasm detection","author":"Bhosale","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1066"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109924"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.01.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/2.0001918"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref16","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref17","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref21","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref22","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00129"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_66"},{"key":"ref26","first-page":"18 661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887864.pdf?arnumber=10887864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:27:05Z","timestamp":1774416425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887864","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}