{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:06:45Z","timestamp":1776881205424,"version":"3.51.2"},"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52102400"],"award-info":[{"award-number":["52102400"]}],"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\/3664647.3680781","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"9709-9718","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["TGCA-PVT: Topic-Guided Context-Aware Pyramid Vision Transformer for Sticker Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4570-2271","authenticated-orcid":false,"given":"Jian","family":"Chen","sequence":"first","affiliation":[{"name":"Sun Yat-sen University & Shenzhen MSU-BIT University, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1717-5785","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen MSU-BIT University & Beijing Institute of Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0448-739X","authenticated-orcid":false,"given":"Yuzhu","family":"Hu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University & Shenzhen MSU-BIT University, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4745-8361","authenticated-orcid":false,"given":"Junxin","family":"Chen","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6921-2050","authenticated-orcid":false,"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen MSU-BIT University & Beijing Institute of Technology, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502282"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274299"},{"key":"e_1_3_2_2_3_1","unstructured":"Tao Chen Damian Borth Trevor Darrell and Shih-Fu Chang. 2014. Deepsentibank: visual sentiment concept classification with deep convolutional neural networks. arXiv preprint arXiv:1410.8586."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Daantje Derks Agneta H Fischer and Arjan ER Bos. 2008. The role of emotion in computer-mediated communication: a review. Computers in human behavior 24 3 766--785.","DOI":"10.1016\/j.chb.2007.04.004"},{"key":"e_1_3_2_2_6_1","unstructured":"Alexey Dosovitskiy et al. 2020. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Eli Dresner and Susan C Herring. 2010. Functions of the nonverbal in cmc: emoticons and illocutionary force. Communication theory 20 3 249--268.","DOI":"10.1111\/j.1468-2885.2010.01362.x"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"e_1_3_2_2_9_1","unstructured":"Dongchen Han Tianzhu Ye Yizeng Han Zhuofan Xia Shiji Song and Gao Huang. 2023. Agent attention: on the integration of softmax and linear attention. arXiv preprint arXiv:2312.08874."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","volume-title":"A multi-attentive pyramidal model for visual sentiment analysis. In 2019 international joint conference on neural networks (IJCNN)","author":"He Xiaohao","unstructured":"Xiaohao He, Huijun Zhang, Ningyun Li, Ling Feng, and Feng Zheng. 2019. A multi-attentive pyramidal model for visual sentiment analysis. In 2019 international joint conference on neural networks (IJCNN). IEEE, 1--8."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.073"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Susan Herring and Ashley Dainas. 2017. 'nice picture comment!' graphicons in facebook comment threads.","DOI":"10.24251\/HICSS.2017.264"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_15_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2957265.2961858"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548407"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873965"},{"key":"e_1_3_2_2_19_1","unstructured":"Adam Paszke et al. 2019. Pytorch: an imperative style high-performance deep learning library. Advances in neural information processing systems 32."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298687"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116256"},{"key":"e_1_3_2_2_22_1","volume-title":"Learning multi-level deep representations for image emotion classification. Neural processing letters, 51","author":"Rao Tianrong","year":"2043","unstructured":"Tianrong Rao, Xiaoxu Li, and Min Xu. 2020. Learning multi-level deep representations for image emotion classification. Neural processing letters, 51, 2043--2061."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.053"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413907"},{"key":"e_1_3_2_2_25_1","unstructured":"Catherine Shu. 2015. The secret language of line stickers. (2015)."},{"key":"e_1_3_2_2_26_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_3_2_2_27_1","first-page":"27","article-title":"Emoticon, emoji, and sticker use in computer-mediated communication: a review of theories and research findings","volume":"13","author":"Tang Ying","year":"2019","unstructured":"Ying Tang and Khe Foon Hew. 2019. Emoticon, emoji, and sticker use in computer-mediated communication: a review of theories and research findings. International Journal of Communication, 13, 27.","journal-title":"International Journal of Communication"},{"key":"e_1_3_2_2_28_1","volume-title":"New Media for Educational Change: Selected Papers from HKAECT 2018 International Conference","author":"Tang Ying","unstructured":"Ying Tang and Khe Foon Hew. 2018. Emoticon, emoji, and sticker use in computer-mediated communications: understanding its communicative function, impact, user behavior, and motive. In New Media for Educational Change: Selected Papers from HKAECT 2018 International Conference. Springer, 191--201."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1177\/17504813211017707"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1177\/0894439315590209"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3118983"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4237--4246","author":"Yang Jingyuan","year":"2021","unstructured":"Jingyuan Yang, Jie Li, Leida Li, Xiumei Wang, and Xinbo Gao. 2021. A circularstructured representation for visual emotion distribution learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4237--4246."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00791"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11275"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Jufeng Yang Dongyu She and Ming Sun. 2017. Joint image emotion classification and distribution learning via deep convolutional neural network. In IJCAI 3266--3272.","DOI":"10.24963\/ijcai.2017\/456"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2803520"},{"key":"e_1_3_2_2_39_1","unstructured":"Kun Yi et al. 2024. Frequency-domain mlps are more effective learners in time series forecasting. Advances in Neural Information Processing Systems 36."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Amir Zadeh Minghai Chen Soujanya Poria Erik Cambria and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250.","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16081-7"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928998"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654930"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351062"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00446"},{"key":"e_1_3_2_2_48_1","volume-title":"Places: a 10 million image database for scene recognition","author":"Zhou Bolei","unstructured":"Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: a 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence, 40, 6, 1452--1464."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Xinge Zhu Liang Li Weigang Zhang Tianrong Rao Min Xu Qingming Huang and Dong Xu. 2017. Dependency exploitation: a unified cnn-rnn approach for visual emotion recognition. In IJCAI 3595--3601.","DOI":"10.24963\/ijcai.2017\/503"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680781","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:42Z","timestamp":1750294662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":49,"alternative-id":["10.1145\/3664647.3680781","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680781","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"}}]}}