{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:22Z","timestamp":1763192602560,"version":"3.45.0"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228306","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["HACL: A Hybrid Adaptive Curriculum Learning Framework for Multi-modal Sarcasm Detection"],"prefix":"10.1109","author":[{"given":"Kefan","family":"Shen","sequence":"first","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China"}]},{"given":"Yukang","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China"}]},{"given":"Wenyao","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Melbourne,Faculty of Engineering and IT,Australia"}]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China"}]},{"given":"Zhihong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1767","article-title":"Multi-modal sarcasm detection via cross-modal graph convolutional network","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Liang"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/3474085.3475190"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP48485.2024.10446922"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/3664647.3681623"},{"volume-title":"Proc. of IJCAI","author":"Zhu","article-title":"Tfcd: Towards multi-modal sarcasm detection via training-free counterfactual debiasing","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"ref7","first-page":"10 834","article-title":"MMSD2.0: Towards a reliable multi-modal sarcasm detection system","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Qin"},{"key":"ref8","first-page":"2506","article-title":"Multi-modal sarcasm detection in Twitter with hierarchical fusion model","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Cai"},{"key":"ref9","first-page":"3777","article-title":"Reasoning with multimodal sarcastic tweets via modeling cross-modality contrast and semantic association","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Xu"},{"key":"ref10","first-page":"1383","article-title":"Modeling intra and inter-modality incongruity for multi-modal sarcasm detection","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Pan"},{"key":"ref11","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhuang","article-title":"UnicoTT: A unified framework for structural chain-of-thought distillation","key":"ref12"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.333","article-title":"Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement","author":"Liu","year":"2022"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/3776561"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TPAMI.2021.3069908"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.18653\/v1\/2021.acl-long.234"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/s11263-022-01611-x"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/3589335.3641257"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/1553374.1553380"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPRW63382.2024.00266"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR52729.2023.00115"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/s11263-023-01748-3"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/TAI.2024.3396125"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.18653\/v1\/N19-1119"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/3581783.3612468"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.18653\/v1\/2022.emnlp-main.209"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TNNLS.2020.2978386"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP49660.2025.10889632"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.18653\/v1\/2024.emnlp-main.170"},{"key":"ref31","first-page":"751","article-title":"From baby steps to leapfrog: How \"less is more\" in unsupervised dependency parsing","volume-title":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Spitkovsky"},{"key":"ref32","first-page":"4308","article-title":"Superloss: A generic loss for robust curriculum learning","volume":"33","author":"Castells","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Self-paced learning for latent variable models","volume":"23","author":"Kumar","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","volume-title":"International conference on machine learning","author":"Hacohen"},{"key":"ref35","first-page":"21 653","article-title":"Curriculum by smoothing","volume":"33","author":"Sinha","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Data parameters: A new family of parameters for learning a differentiable curriculum","volume":"32","author":"Saxena","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/cvpr.2016.90"},{"volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/ICIP46576.2022.9897323"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref41","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"proceedings of the IEEE conference on computer vision and pattern recognition","author":"Ross"},{"key":"ref42","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Kim"},{"issue":"5","key":"ref43","first-page":"602","article-title":"Framewise phoneme classification with bidirectional lstm and other neural network architectures","volume-title":"Neural Networks","volume":"18","author":"Graves","year":"2005"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1145\/3308558.3313735"},{"key":"ref45","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/CVPR52729.2023.00250"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1609\/aaai.v38i8.28766"},{"volume-title":"International Conference on Learning Representations","author":"Loshchilov","article-title":"Decoupled weight decay regularization","key":"ref48"},{"year":"2024","author":"Yao","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","key":"ref49"},{"key":"ref50","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.18653\/v1\/2022.acl-long.26"},{"year":"2023","author":"Bai","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","key":"ref52"},{"year":"2023","author":"Ye","article-title":"mplug-owl: Modularization empowers large language models with multimodality","key":"ref53"},{"year":"2023","author":"Achiam","article-title":"Gpt-4 technical report","key":"ref54"},{"key":"ref55","first-page":"1754","article-title":"Multi-view incongruity learning for multimodal sarcasm detection","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Guo"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.18653\/v1\/P19-1656"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1145\/3394171.3413678"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/TAFFC.2022.3172360"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1609\/aaai.v35i12.17289"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.18653\/v1\/2023.acl-long.421"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228306.pdf?arnumber=11228306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:39:53Z","timestamp":1763192393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228306","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}