{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:08:34Z","timestamp":1765357714780,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangdong Provincial Fund for Basic and Applied Basic Research?Regional Joint Fund Project (Key Project)","award":["2023B1515120078"],"award-info":[{"award-number":["2023B1515120078"]}]},{"name":"the Hong Kong Polytechnic University?s Postdoc Matching Fund","award":["P0049003"],"award-info":[{"award-number":["P0049003"]}]},{"name":"the Science and Technology Planning Project of Guangdong Province","award":["2020B0101100002"],"award-info":[{"award-number":["2020B0101100002"]}]},{"name":"Guangdong Provincial Natural Science Foundation for Outstanding Youth Team Project","award":["2024B1515040010"],"award-info":[{"award-number":["2024B1515040010"]}]},{"name":"the China Computer Federation (CCF)-Zhipu AI Large Model Fund"},{"name":"the Fundamental Research Funds for the Central Universities, South China University of Technology","award":["x2rjD2240100"],"award-info":[{"award-number":["x2rjD2240100"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076100"],"award-info":[{"award-number":["62076100"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681522","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3084-3093","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Deconfounded Emotion Guidance Sticker Selection with Causal Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8064-1577","authenticated-orcid":false,"given":"Jiali","family":"Chen","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7737-1738","authenticated-orcid":false,"given":"Ruohang","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-6507","authenticated-orcid":false,"given":"Jiexin","family":"Wang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-7879","authenticated-orcid":false,"given":"Jiayuan","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3054717"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2107"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2017"},{"key":"e_1_3_2_1_5_1","volume-title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction. In Proc. of ACL, Anna Korhonen, David R","author":"Bosselut Antoine","year":"2019","unstructured":"Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019. COMET: Commonsense Transformers for Automatic Knowledge Graph Construction. In Proc. of ACL, Anna Korhonen, David R. Traum, and Llu\u00eds M\u00e0rquez (Eds.). Association for Computational Linguistics, 4762--4779."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.498"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612536"},{"key":"e_1_3_2_1_8_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. of NAACL","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. of NAACL, Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 4171--4186."},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. of ICLR. OpenReview.net.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proc. of ICLR. OpenReview.net."},{"key":"e_1_3_2_1_10_1","volume-title":"PP-OCR: A Practical Ultra Lightweight OCR System. CoRR","author":"Du Yuning","year":"2020","unstructured":"Yuning Du, Chenxia Li, Ruoyu Guo, Xiaoting Yin, Weiwei Liu, Jun Zhou, Yifan Bai, Zilin Yu, Yehua Yang, Qingqing Dang, and Haoshuang Wang. 2020. PP-OCR: A Practical Ultra Lightweight OCR System. CoRR, Vol. abs\/2009.09941 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00511"},{"key":"e_1_3_2_1_13_1","volume-title":"Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark. CoRR","author":"Fei Zhengcong","year":"1839","unstructured":"Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, and Jie Zhou. 2021. Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark. CoRR, Vol. abs\/2109.01839 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3015491"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380191"},{"key":"e_1_3_2_1_16_1","unstructured":"Feng Ge Weizhao Li Haopeng Ren and Yi Cai. 2022. Towards Exploiting Sticker for Multimodal Sentiment Analysis in Social Media: A New Dataset and Baseline. In Proc. of COLING Nicoletta Calzolari Chu-Ren Huang Hansaem Kim James Pustejovsky Leo Wanner Key-Sun Choi Pum-Mo Ryu Hsin-Hsi Chen Lucia Donatelli Heng Ji Sadao Kurohashi Patrizia Paggio Nianwen Xue Seokhwan Kim Younggyun Hahm Zhong He Tony Kyungil Lee Enrico Santus Francis Bond and Seung-Hoon Na (Eds.). International Committee on Computational Linguistics 6795--6804."},{"key":"e_1_3_2_1_17_1","volume-title":"Girshick","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In Proc. of CVPR. Computer Vision Foundation \/ IEEE, 9726--9735."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00682"},{"key":"e_1_3_2_1_19_1","volume-title":"Bidirectional LSTM-CRF Models for Sequence Tagging. CoRR","author":"Huang Zhiheng","year":"1991","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF Models for Sequence Tagging. CoRR, Vol. abs\/1508.01991 (2015)."},{"volume-title":"Proc","author":"Huo Jing","key":"e_1_3_2_1_20_1","unstructured":"Jing Huo, Wenbin Li, Yinghuan Shi, Yang Gao, and Hujun Yin. 2018. WebCaricature: a benchmark for caricature recognition. In Proc, of BMVC. BMVA Press, 223."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2013.09.007"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580990"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3191973"},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. of ICML (Proceedings of Machine Learning Research","volume":"5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In Proc. of ICML (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 5583--5594."},{"key":"e_1_3_2_1_25_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proc. of ICLR."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of ICML. 17283--17300","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. 2023. Grounding Language Models to Images for Multimodal Inputs and Outputs. In Proc. of ICML. 17283--17300."},{"volume-title":"Proc","author":"Laddha Abhishek","key":"e_1_3_2_1_27_1","unstructured":"Abhishek Laddha, Mohamed Hanoosh, Debdoot Mukherjee, Parth Patwa, and Ankur Narang. 2020. Understanding Chat Messages for Sticker Recommendation in Messaging Apps. In Proc. of AAAI. AAAI Press, 13156--13163."},{"key":"e_1_3_2_1_28_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proc. of ACL, Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R","author":"Lewis Mike","year":"2020","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proc. of ACL, Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault (Eds.). Association for Computational Linguistics, 7871--7880."},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of ICML. 19730--19742","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In Proc. of ICML. 19730--19742."},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of NAACL, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-T\u00fcr","author":"Liu Xiao","year":"1928","unstructured":"Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, and Dongyan Zhao. 2021. Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis. In Proc. of NAACL, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-T\u00fcr, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou (Eds.). Association for Computational Linguistics, 1928--1941."},{"key":"e_1_3_2_1_31_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR, Vol. abs\/1907.11692 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_38"},{"key":"e_1_3_2_1_34_1","volume-title":"Cambridge, UK","author":"Judea Pearl","year":"2000","unstructured":"Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: CambridgeUniversityPress, Vol. 19, 2 (2000), 3."},{"key":"e_1_3_2_1_35_1","unstructured":"Judea Pearl and Dana Mackenzie. 2018. The book of why: the new science of cause and effect. Basic books."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. of ICML (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proc. of ICML (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763."},{"key":"e_1_3_2_1_38_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_39_1","volume-title":"Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi.","author":"Sap Maarten","year":"2019","unstructured":"Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi. 2019. ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. In Proc. of AAAI. AAAI Press, 3027--3035."},{"key":"e_1_3_2_1_40_1","volume-title":"Tigwell","author":"Shandilya Esha","year":"2022","unstructured":"Esha Shandilya, Mingming Fan, and Garreth W. Tigwell. 2022. \"I need to be professional until my new team uses emoji, GIFs, or memes first\u201d: New Collaborators' Perspectives on Using Non-Textual Communication in Virtual Workspaces. In Proc. of CHI, Simone D. J. Barbosa, Cliff Lampe, Caroline Appert, David A. Shamma, Steven Mark Drucker, Julie R. Williamson, and Koji Yatani (Eds.). ACM, 528:1--528:13."},{"key":"e_1_3_2_1_41_1","volume-title":"Motivation and justification: A dual-process model of culture in action. American journal of sociology","author":"Vaisey Stephen","year":"2009","unstructured":"Stephen Vaisey. 2009. Motivation and justification: A dual-process model of culture in action. American journal of sociology, Vol. 114, 6 (2009), 1675--1715."},{"key":"e_1_3_2_1_42_1","volume-title":"Proc. of NeurIPS, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proc. of NeurIPS, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.276"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3231352"},{"key":"e_1_3_2_1_46_1","volume-title":"Neural Emoji Recommendation in Dialogue Systems. CoRR","author":"Xie Ruobing","year":"2016","unstructured":"Ruobing Xie, Zhiyuan Liu, Rui Yan, and Maosong Sun. 2016. Neural Emoji Recommendation in Dialogue Systems. CoRR, Vol. abs\/1612.04609 (2016)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.514"},{"key":"e_1_3_2_1_48_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona T. Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. CoRR, Vol. abs\/2205.01068 (2022)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.241"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681522","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681522"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":49,"alternative-id":["10.1145\/3664647.3681522","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681522","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}