{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:38:56Z","timestamp":1775068736159,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","funder":[{"name":"NSSFC","award":["22ZD05"],"award-info":[{"award-number":["22ZD05"]}]},{"name":"NNSFC","award":["62472178"],"award-info":[{"award-number":["62472178"]}]},{"name":"the Natural Science Foundation of Shanghai Municipality","award":["24ZR1418300"],"award-info":[{"award-number":["24ZR1418300"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754921","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"6615-6624","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Music2Palette: Emotion-aligned Color Palette Generation via Cross-Modal Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1606-5832","authenticated-orcid":false,"given":"Jiayun","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7550-0918","authenticated-orcid":false,"given":"Yueyi","family":"He","sequence":"additional","affiliation":[{"name":"School of Software Engineering, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8372-8379","authenticated-orcid":false,"given":"Tianyi","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8940-6418","authenticated-orcid":false,"given":"Changbo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9835-2650","authenticated-orcid":false,"given":"Chenhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"1121","article-title":"A Generalized Study on Data Mining and Clustering Algorithms. Springer International Publishing","author":"Ahmed Syed Thouheed","year":"2020","unstructured":"Syed Thouheed Ahmed, S. Sreedhar Kumar, B. Anusha, P. Bhumika, M. Gunashree, and B. Ishwarya. 2020. A Generalized Study on Data Mining and Clustering Algorithms. Springer International Publishing, Cham, 1121-1129.","journal-title":"Cham"},{"key":"e_1_3_2_1_2_1","volume-title":"Benchmarking music emotion recognition systems. PloS one","author":"Alajanki Anna","year":"2016","unstructured":"Anna Alajanki, Yi-Hsuan Yang, and Mohammad Soleymani. 2016. Benchmarking music emotion recognition systems. PloS one (2016), 835-838."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2015.03.004"},{"key":"e_1_3_2_1_4_1","volume-title":"Munich","volume":"459","author":"Bahng Hyojin","year":"2018","unstructured":"Hyojin Bahng, Seungjoo Yoo, Wonwoong Cho, David Keetae Park, Ziming Wu, Xiaojuan Ma, and Jaegul Choo. 2018. Coloring with Words: Guiding Image Colorization Through Text-Based Palette Generation. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XII (Lecture Notes in Computer Science, Vol. 11216). Springer, 443-459."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03196892"},{"key":"e_1_3_2_1_6_1","unstructured":"Roberto Bresin. 2005. What is the color of that music performance?. In ICMC."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.12.003"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766978"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02533"},{"key":"e_1_3_2_1_11_1","unstructured":"SeungHeon Doh Keunwoo Choi Jongpil Lee and Juhan Nam. 2023. LP-MusicCaps: LLM-Based Pseudo Music Captioning. (2023) 409-416."},{"key":"e_1_3_2_1_12_1","first-page":"1","volume-title":"Toward Universal Text-To-Music Retrieval. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Doh Seungheon","year":"2022","unstructured":"Seungheon Doh, Minz Won, Keunwoo Choi, and Juhan Nam. 2022. Toward Universal Text-To-Music Retrieval. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2022), 1-5."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01214"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"e_1_3_2_1_15_1","volume-title":"Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. 2021. Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-021-00658-5"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2632307"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621452"},{"key":"e_1_3_2_1_19_1","volume-title":"Crossmodal Correspondence between Music and Ambient Color Is Mediated by Emotion. Multisensory research","author":"Hauck Pia","year":"2022","unstructured":"Pia Hauck, Christoph von Castell, and Heiko Hecht. 2022. Crossmodal Correspondence between Music and Ambient Color Is Mediated by Emotion. Multisensory research, Vol. 35 5 (2022), 407-446."},{"key":"e_1_3_2_1_20_1","volume-title":"Methodology for stage lighting control based on music emotions. Information sciences","author":"Hsiao Shih-Wen","year":"2017","unstructured":"Shih-Wen Hsiao, Shih-Kai Chen, and Chu-Hsuan Lee. 2017. Methodology for stage lighting control based on music emotions. Information sciences, Vol. 412 (2017), 14-35."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2502935"},{"key":"e_1_3_2_1_22_1","volume-title":"CCSUMSP: A cross-subject Chinese speech decoding framework with unified topology and multi-modal semantic pre-training. Information Fusion","author":"Huang Shuai","year":"2025","unstructured":"Shuai Huang, Yongxiong Wang, and Huan Luo. 2025a. CCSUMSP: A cross-subject Chinese speech decoding framework with unified topology and multi-modal semantic pre-training. Information Fusion (2025), 103022."},{"key":"e_1_3_2_1_23_1","volume-title":"A dual-branch generative adversarial network with self-supervised enhancement for robust auditory attention decoding. Engineering Applications of Artificial Intelligence","author":"Huang Shuai","year":"2025","unstructured":"Shuai Huang, Yongxiong Wang, and Huan Luo. 2025b. A dual-branch generative adversarial network with self-supervised enhancement for robust auditory attention decoding. Engineering Applications of Artificial Intelligence (2025), 111122."},{"key":"e_1_3_2_1_24_1","volume-title":"Allebach","author":"Jahanian Ali","year":"2015","unstructured":"Ali Jahanian, S. V. N. Vishwanathan, and Jan P. Allebach. 2015. Autonomous color theme extraction from images using saliency. In Imaging and Multimedia Analytics in a Web and Mobile World 2015, San Francisco, California, USA, February 8-12, 2015 (SPIE Proceedings, Vol. 9408). SPIE, 940807."},{"key":"e_1_3_2_1_25_1","volume-title":"Do we feel colours? A systematic review of 128 years of psychological research linking colours and emotions. Psychonomic bulletin & review","author":"Jonauskaite Domicele","year":"2025","unstructured":"Domicele Jonauskaite and Christina Mohr. 2025. Do we feel colours? A systematic review of 128 years of psychological research linking colours and emotions. Psychonomic bulletin & review (2025)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206037"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2827782"},{"key":"e_1_3_2_1_28_1","volume-title":"State of the Art Report: Music Emotion Recognition: A State of the Art Review. In International Society for Music Information Retrieval Conference.","author":"Kim Youngmoo E.","year":"2010","unstructured":"Youngmoo E. Kim, Erik M. Schmidt, Raymond Migneco, Brandon G. Morton, Patrick Richardson, Jeffrey J. Scott, Jacquelin A. Speck, and Douglas Turnbull. 2010. State of the Art Report: Music Emotion Recognition: A State of the Art Review. In International Society for Music Information Retrieval Conference."},{"key":"e_1_3_2_1_29_1","unstructured":"Shigenobu Kobayashi. 1992. Color Image Scale."},{"key":"e_1_3_2_1_30_1","volume-title":"Emotion-Guided Image to Music Generation. ArXiv","author":"Kundu Souraja","year":"2024","unstructured":"Souraja Kundu, Saket Singh, and Yuji Iwahori. 2024. Emotion-Guided Image to Music Generation. ArXiv, Vol. abs\/2410.22299 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11747-010-0245-y"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413624"},{"key":"e_1_3_2_1_33_1","first-page":"694","article-title":"Text2Palette: Text-Driven Color Palette Generation Using Internet Images","volume":"33","author":"Lei Kaixiang","year":"2021","unstructured":"Kaixiang Lei, Zhengning Liu, and Kun Xu. 2021. Text2Palette: Text-Driven Color Palette Generation Using Internet Images. Journal of Computer-Aided Design & Computer Graphics, Vol. 33, 5 (2021), 694-703.","journal-title":"Journal of Computer-Aided Design & Computer Graphics"},{"key":"e_1_3_2_1_34_1","first-page":"27338","volume-title":"Diff-BGM: A Diffusion Model for Video Background Music Generation. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li Sizhe","year":"2024","unstructured":"Sizhe Li, Yiming Qin, Minghang Zheng, Xin Jin, and Yang Liu. 2024. Diff-BGM: A Diffusion Model for Video Background Music Generation. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024), 27338-27347."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3233\/JCM-247551"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3678698.3687189"},{"key":"e_1_3_2_1_37_1","volume-title":"Image-Driven Harmonious Color Palette Generation for Diverse Information Visualization","author":"Liu Shuqi","year":"2022","unstructured":"Shuqi Liu, Mingtian Tao, Yifei Huang, Changbo Wang, and Chenhui Li. 2022. Image-Driven Harmonious Color Palette Generation for Diverse Information Visualization. IEEE Transactions on Visualization and Computer Graphics (2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-023-3064-6"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Brian McFee Colin Raffel Dawen Liang Daniel P. W. Ellis Matt McVicar Eric Battenberg and Oriol Nieto. 2015. librosa: Audio and Music Signal Analysis in Python. In SciPy.","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03192732"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Ahmad Moussa and Hiroshi Watanabe. 2021. Generation and Extraction of Color Palettes with Adversarial Variational Auto-Encoders. In International Congress on Information and Communication Technology. https:\/\/api.semanticscholar.org\/CorpusID:238232832","DOI":"10.1007\/978-981-16-2380-6_78"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"James R. Munkres. 1957. ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS*.","DOI":"10.1137\/0105003"},{"key":"e_1_3_2_1_43_1","first-page":"2173","volume-title":"Content-Based Music-Image Retrieval Using Self- and Cross-Modal Feature Embedding Memory. 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Nakatsuka Takayuki","year":"2023","unstructured":"Takayuki Nakatsuka, Masahiro Hamasaki, and Masataka Goto. 2023. Content-Based Music-Image Retrieval Using Self- and Cross-Modal Feature Embedding Memory. 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2023), 2173-2183."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-021-00776-6"},{"key":"e_1_3_2_1_45_1","unstructured":"Niels Alexander Nijdam. 2005. Mapping emotion to color."},{"key":"e_1_3_2_1_46_1","volume-title":"Conference of the International Society for Research on Emotion (ISRE 2015 Geneva).","author":"Oberfeld Daniel","year":"2015","unstructured":"Daniel Oberfeld and Lisa Wilms. 2015. Effects of color on emotion: Evidence from self-report ratings and physiological measures. In Conference of the International Society for Research on Emotion (ISRE 2015 Geneva)."},{"key":"e_1_3_2_1_47_1","volume-title":"Openai models- gpt-4-vision. https:\/\/openai.com\/index\/gpt-4v-system-card\/","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. Openai models- gpt-4-vision. https:\/\/openai.com\/index\/gpt-4v-system-card\/ (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Openai models- gpt-4o-system-card. https:\/\/openai.com\/index\/gpt-4o-system-card\/","author":"AI.","year":"2024","unstructured":"OpenAI. 2024a. Openai models- gpt-4o-system-card. https:\/\/openai.com\/index\/gpt-4o-system-card\/ (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"Openai models- text-embedding-3-large-vision. https:\/\/openai.com\/index\/new-embedding-models-and-api-updates\/","author":"AI.","year":"2024","unstructured":"OpenAI. 2024b. Openai models- text-embedding-3-large-vision. https:\/\/openai.com\/index\/new-embedding-models-and-api-updates\/ (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1002\/col.20010"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1163\/22134808-00002486"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1212562110"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2017.1333518"},{"key":"e_1_3_2_1_54_1","volume-title":"Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation. ArXiv","author":"Rinaldi Ivan","year":"2024","unstructured":"Ivan Rinaldi, Nicola Fanelli, Giovanna Castellano, and Gennaro Vessio. 2024. Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation. ArXiv, Vol. abs\/2410.04906 (2024)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"e_1_3_2_1_57_1","volume-title":"Three dimensions of emotion. Psychological review","author":"Schlosberg Harold","year":"1954","unstructured":"Harold Schlosberg. 1954. Three dimensions of emotion. Psychological review, Vol. 61 2 (1954), 81-8."},{"key":"e_1_3_2_1_58_1","volume-title":"The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Research & Application: Endorsed by Inter-Society Color Council","author":"Sharma Gaurav","year":"2005","unstructured":"Gaurav Sharma, Wencheng Wu, and Edul N Dalal. 2005. The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Research & Application: Endorsed by Inter-Society Color Council, The Colour Group (Great Britain), Canadian Society for Color, Color Science Association of Japan, Dutch Society for the Study of Color, The Swedish Colour Centre Foundation, Colour Society of Australia, Centre Fran\u00e7ais de la Couleur, Vol. 30, 1 (2005), 21-30."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581070"},{"key":"e_1_3_2_1_60_1","first-page":"8135","volume-title":"Emotion-Aligned Contrastive Learning Between Images and Music. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Stewart Shanti","year":"2023","unstructured":"Shanti Stewart, Tiantian Feng, Kleanthis Avramidis, and Shrikanth S. Narayanan. 2023. Emotion-Aligned Contrastive Learning Between Images and Music. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023), 8135-8139."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.002"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.123.4.394"},{"key":"e_1_3_2_1_63_1","volume-title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation. ArXiv","author":"Wang Baisen","year":"2024","unstructured":"Baisen Wang, Le Zhuo, Zhaokai Wang, Chenxi Bao, Chengjing Wu, Xuecheng Nie, Jiao Dai, Jizhong Han, Yue Liao, and Si Liu. 2024b. Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation. ArXiv, Vol. abs\/2412.09428 (2024)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338089"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471735"},{"key":"e_1_3_2_1_66_1","volume-title":"Aesthetic Matters in Music Perception for Image Stylization: A Emotion-driven Music-to-Visual Manipulation. ArXiv","author":"Xu Junjie","year":"2025","unstructured":"Junjie Xu, Xingjiao Wu, Tanren Yao, Zihao Zhang, Jiayang Bei, Wen Wu, and Liang He. 2025. Aesthetic Matters in Music Perception for Image Stylization: A Emotion-driven Music-to-Visual Manipulation. ArXiv, Vol. abs\/2501.01700 (2025)."},{"key":"e_1_3_2_1_67_1","article-title":"Image Emotion Recognition Using Visual and Semantic Features Reflecting Emotional and Similar Objects. IEICE","volume":"1691","author":"Yamamoto Takahisa","year":"2021","unstructured":"Takahisa Yamamoto, Shiki Takeuchi, and Atsushi Nakazawa. 2021. Image Emotion Recognition Using Visual and Semantic Features Reflecting Emotional and Similar Objects. IEICE Trans. Inf. Syst., Vol. 104-D (2021), 1691-1701.","journal-title":"Trans. Inf. Syst."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02472-8"},{"key":"e_1_3_2_1_69_1","first-page":"6358","volume-title":"EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yang Jingyuan","year":"2024","unstructured":"Jingyuan Yang, Jiawei Feng, and Hui Huang. 2024a. EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024), 6358-6368."},{"key":"e_1_3_2_1_70_1","volume-title":"EmoEdit: Evoking Emotions through Image Manipulation. ArXiv","author":"Yang Jingyuan","year":"2024","unstructured":"Jingyuan Yang, Jiawei Feng, Weibin Luo, Dani Lischinski, Daniel Cohen-Or, and Hui Huang. 2024b. EmoEdit: Evoking Emotions through Image Manipulation. ArXiv, Vol. abs\/2405.12661 (2024)."},{"key":"e_1_3_2_1_71_1","volume-title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","author":"Yang Jingyuan","year":"2023","unstructured":"Jingyuan Yang, Qiruin Huang, Tingting Ding, Dani Lischinski, Daniel Cohen-Or, and Hui Huang. 2023. EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023), 20326-20337."},{"key":"e_1_3_2_1_72_1","article-title":"Machine Recognition of Music Emotion","volume":"3","author":"Yang Yi-Hsuan","year":"2012","unstructured":"Yi-Hsuan Yang and Homer H. Chen. 2012. Machine Recognition of Music Emotion: A Review. ACM Trans. Intell. Syst. Technol., Vol. 3 (2012), 40:1-40:30.","journal-title":"A Review. ACM Trans. Intell. Syst. Technol."},{"key":"e_1_3_2_1_73_1","volume-title":"Behavior, & Immunity - Health","author":"Zaatar Muriel T.","year":"2023","unstructured":"Muriel T. Zaatar, Kenda Alhakim, Mohammad Enayeh, and Ribal Tamer. 2023. The transformative power of music: Insights into neuroplasticity, health, and disease. Brain, Behavior, & Immunity - Health, Vol. 35 (2023)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1037\/1528-3542.8.4.494"},{"key":"e_1_3_2_1_75_1","volume-title":"Chaojie Shentu, Hao Tian, Yutong Liu, Jiangjun Wan, Xinyue Zhang, and Jinghui Li.","author":"Zhang Chengyan","year":"2024","unstructured":"Chengyan Zhang, Youjia Chen, Bart Julien Dewancker, Chaojie Shentu, Hao Tian, Yutong Liu, Jiangjun Wan, Xinyue Zhang, and Jinghui Li. 2024. Emotional Landscapes in Urban Design: Analyzing Color Emotional Responses of the Elderly to Community Outdoor Spaces in Yi Jie Qu. Buildings (2024)."},{"key":"e_1_3_2_1_76_1","volume-title":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery","volume":"8","author":"Zhang Lei","year":"2018","unstructured":"Lei Zhang, Shuai Wang, and B. Liu. 2018. Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, Vol. 8 (2018)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413776"},{"key":"e_1_3_2_1_78_1","volume-title":"An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos. In AAAI Conference on Artificial Intelligence.","author":"Zhao Sicheng","year":"2020","unstructured":"Sicheng Zhao, Yunsheng Ma, Yang Gu, Jufeng Yang, Tengfei Xing, Pengfei Xu, Runbo Hu, Hua Chai, and Kurt Keutzer. 2020b. An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2628787"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617741"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:18:56Z","timestamp":1765340336000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":80,"alternative-id":["10.1145\/3746027.3754921","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754921","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}