{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:58Z","timestamp":1774419958626,"version":"3.50.1"},"reference-count":48,"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\/icassp49660.2025.10887877","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["MHSDB: A Comprehensive Benchmark for Multimodal Humor and Sarcasm Detection Leveraging Foundation Models"],"prefix":"10.1109","author":[{"given":"Zhongren","family":"Dong","sequence":"first","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghao","family":"Wang","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ciqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"BTECH Robotics Corp,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"CMMA: benchmarking multi-affection detection in chinese multi-modal conversations","volume-title":"Proc. 37th NeurIPS","author":"Zhang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447592"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3396345"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111457"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3298328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479959"},{"key":"ref10","first-page":"6752","article-title":"A sentiment and emotion aware multimodal multiparty humor recognition in multilingual conversational setting","volume-title":"Proc. 29th COLING","author":"Chauhan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3606039.3613112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3606039.3613110"},{"key":"ref13","first-page":"6992","article-title":"A multimodal corpus for emotion recognition in sarcasm","volume-title":"Proc. 13th LREC","author":"Ray"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.988"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","article-title":"Towards general text embeddings with multi-stage contrastive learning","author":"Li","year":"2023"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th ICML","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1211"},{"key":"ref19","article-title":"Sarcasm in sight and sound: Benchmarking and expansion to improve multimodal sarcasm detection","author":"Bhosale","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10908"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref22","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. 39th ICML","author":"Baevski"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-280"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref26","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th ICML","author":"Radford"},{"key":"ref27","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref28","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"Yang","year":"2019"},{"key":"ref29","article-title":"DeBERTa: Decoding-enhanced bert with disentangled attention","author":"He","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref32","article-title":"Text embeddings by weakly-supervised contrastive pre-training","author":"Wang","year":"2022"},{"key":"ref33","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref34","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref35","first-page":"10 078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. 36th NeurIPS","author":"Tong"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref38","article-title":"MERBench: A unified evaluation benchmark for multimodal emotion recognition","author":"Lian","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681527"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102663"},{"key":"ref46","article-title":"SpeechPrompt v2: Prompt tuning for speech classification tasks","author":"Chang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.105"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446795"}],"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\/10887877.pdf?arnumber=10887877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:38Z","timestamp":1774416338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887877","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}