{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:35:49Z","timestamp":1775694949068,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62306061"],"award-info":[{"award-number":["62306061"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["No. 2023A1515140037"],"award-info":[{"award-number":["No. 2023A1515140037"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754549","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"5451-5460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["EmoSym: A Symbiotic Framework for Unified Emotional Understanding and Generation via Latent Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3601-7893","authenticated-orcid":false,"given":"Yijie","family":"Zhu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China and Great Bay University, Dongguan, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1562-804X","authenticated-orcid":false,"given":"Yibo","family":"Lyu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6505-3304","authenticated-orcid":false,"given":"Zitong","family":"Yu","sequence":"additional","affiliation":[{"name":"Great Bay University, Dongguan, Guangdong, China and Dongguan Key Laboratory for Intelligence and Information Technology, Dongguan, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0090-9604","authenticated-orcid":false,"given":"Rui","family":"Shao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8153-3903","authenticated-orcid":false,"given":"Kaiyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Qinsheng Zhang Karsten Kreis Miika Aittala Timo Aila Samuli Laine Bryan Catanzaro Tero Karras and Ming-Yu Liu. 2023. eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers. arXiv:2211.01324 [cs.CV] https:\/\/arxiv.org\/abs\/2211.01324"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502282"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2813524.2813530"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351656"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"e_1_3_2_1_7_1","volume-title":"Video ecommerce: Toward large scale online video advertising","author":"Cheng Zhi-Qi","year":"2017","unstructured":"Zhi-Qi Cheng, Xiao Wu, Yang Liu, and Xian-Sheng Hua. 2017a. Video ecommerce: Toward large scale online video advertising. IEEE transactions on multimedia, Vol. 19, 6 (2017), 1170-1183."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.444"},{"key":"e_1_3_2_1_9_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Ziqing Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al., 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed 14 April 2023), Vol. 2, 3 (2023), 6."},{"key":"e_1_3_2_1_10_1","volume-title":"InstructBLIP: towards general-purpose vision-language models with instruction tuning. ArXiv. Preprint posted online on June","author":"Dai W","year":"2023","unstructured":"W Dai, J Li, D Li, AMH Tiong, J Zhao, W Wang, B Li, P Fung, and S Hoi. 2023. InstructBLIP: towards general-purpose vision-language models with instruction tuning. ArXiv. Preprint posted online on June, Vol. 15, 2023 (2023), 4."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00129-1_15"},{"key":"e_1_3_2_1_12_1","volume-title":"Learning to compose diversified prompts for image emotion classification. Computational Visual Media","author":"Deng Sinuo","year":"2024","unstructured":"Sinuo Deng, Lifang Wu, Ge Shi, Lehao Xing, Meng Jian, Ye Xiang, and Ruihai Dong. 2024. Learning to compose diversified prompts for image emotion classification. Computational Visual Media (2024), 1-15."},{"key":"e_1_3_2_1_13_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","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 Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_14_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, Vol. 34 (2021), 8780-8794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123445"},{"key":"e_1_3_2_1_16_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation. arXiv preprint arXiv:2412.04432","author":"Ge Yuying","year":"2024","unstructured":"Yuying Ge, Yizhuo Li, Yixiao Ge, and Ying Shan. 2024. Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation. arXiv preprint arXiv:2412.04432 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"e_1_3_2_1_19_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_20_1","volume-title":"Weicheng Xie, Linlin Shen, and Zongyuan Ge.","author":"He Xilin","year":"2024","unstructured":"Xilin He, Cheng Luo, Xiaole Xian, Bing Li, Siyang Song, Muhammad Haris Khan, Weicheng Xie, Linlin Shen, and Zongyuan Ge. 2024. SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data. arXiv preprint arXiv:2410.09865 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_22_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6840-6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pec.2015.06.012"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18401\/2017.7.1.3"},{"key":"e_1_3_2_1_25_1","volume-title":"E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580","author":"Jiang Ting","year":"2024","unstructured":"Ting Jiang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, and Fuzhen Zhuang. 2024. E5-v: Universal embeddings with multimodal large language models. arXiv preprint arXiv:2407.12580 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOP.2015.7489424"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2158530"},{"key":"e_1_3_2_1_30_1","volume-title":"International conference on machine learning. PMLR","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 International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_31_1","volume-title":"Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition. arXiv preprint arXiv:2409.17576","author":"Li Shen","year":"2024","unstructured":"Shen Li, Jianqing Xu, Jiaying Wu, Miao Xiong, Ailin Deng, Jiazhen Ji, Yuge Huang, Wenjie Feng, Shouhong Ding, and Bryan Hooi. 2024. ID^3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition. arXiv preprint arXiv:2409.17576 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00308"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3573785"},{"key":"e_1_3_2_1_35_1","volume-title":"Patterns","volume":"5","author":"Lin Xun","year":"2024","unstructured":"Xun Lin, Wenzhong Tang, Haoran Wang, Yizhong Liu, Yakun Ju, Shuai Wang, and Zitong Yu. 2024. Exposing image splicing traces in scientific publications via uncertainty-guided refinement. Patterns, Vol. 5, 9 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451","author":"Liu Chris Yuhao","year":"2024","unstructured":"Chris Yuhao Liu, Liang Zeng, Jiacai Liu, Rui Yan, Jujie He, Chaojie Wang, Shuicheng Yan, Yang Liu, and Yahui Zhou. 2024b. Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755029"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873965"},{"key":"e_1_3_2_1_40_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612186"},{"key":"e_1_3_2_1_42_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703","author":"Paszke A","year":"2019","unstructured":"A Paszke. 2019. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"Detgpt: Detect what you need via reasoning. arXiv preprint arXiv:2305.14167","author":"Pi Renjie","year":"2023","unstructured":"Renjie Pi, Jiahui Gao, Shizhe Diao, Rui Pan, Hanze Dong, Jipeng Zhang, Lewei Yao, Jianhua Han, Hang Xu, Lingpeng Kong, et al., 2023. Detgpt: Detect what you need via reasoning. arXiv preprint arXiv:2305.14167 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Machine Learning. 8748-8763","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, et al., 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748-8763."},{"key":"e_1_3_2_1_45_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10033-9"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.053"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAECA52838.2021.9675688"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_51_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479-36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_52_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Diffusion feedback helps clip see better. arXiv preprint arXiv:2407.20171","author":"Wang Wenxuan","year":"2024","unstructured":"Wenxuan Wang, Quan Sun, Fan Zhang, Yepeng Tang, Jing Liu, and Xinlong Wang. 2024b. Diffusion feedback helps clip see better. arXiv preprint arXiv:2407.20171 (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848","author":"Wei Yuxiang","year":"2023","unstructured":"Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, and Wangmeng Zuo. 2023. Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW59127.2023.10388165"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"e_1_3_2_1_58_1","unstructured":"Can Xu Suleyman Cetintas Kuang-Chih Lee and Li-Jia Li. 2014. Visual Sentiment Prediction with Deep Convolutional Neural Networks. arXiv:1411.5731 [cs.CV] https:\/\/arxiv.org\/abs\/1411.5731"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00926"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102366"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3057270"},{"key":"e_1_3_2_1_62_1","volume-title":"European Conference on Computer Vision. Springer, 98-115","author":"Yan Cilin","year":"2024","unstructured":"Cilin Yan, Haochen Wang, Shilin Yan, Xiaolong Jiang, Yao Hu, Guoliang Kang, Weidi Xie, and Efstratios Gavves. 2024. Visa: Reasoning video object segmentation via large language models. In European Conference on Computer Vision. Springer, 98-115."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00608"},{"key":"e_1_3_2_1_64_1","volume-title":"EmoEdit: Evoking Emotions through Image Manipulation. arXiv preprint arXiv:2405.12661","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 preprint arXiv:2405.12661 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3118983"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4711701"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754773"},{"key":"e_1_3_2_1_70_1","volume-title":"CAT: Investigating and Enhancing Audio-visual Understanding in Large Language Models","author":"Ye Qilang","year":"2025","unstructured":"Qilang Ye, Zitong Yu, Rui Shao, Yawen Cui, Xiangui Kang, Xin Liu, Philip Torr, and Xiaochun Cao. 2025. CAT: Investigating and Enhancing Audio-visual Understanding in Large Language Models. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Yuhang Zang Xiaoyi Dong Pan Zhang Yuhang Cao Ziyu Liu Shengyuan Ding Shenxi Wu Yubo Ma Haodong Duan Wenwei Zhang et al. 2025. InternLM-XComposer2. 5-Reward: A Simple Yet Effective Multi-Modal Reward Model. arXiv preprint arXiv:2501.12368 (2025).","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"e_1_3_2_1_73_1","volume-title":"Advances in Intelligent Data Analysis X, Jo ao Gama, Elizabeth Bradley, and Jaakko Hollm\u00e9n (Eds.)","author":"Zhang He","unstructured":"He Zhang, Eimontas Augilius, Timo Honkela, Jorma Laaksonen, Hannes Gamper, and Henok Alene. 2011. Analyzing Emotional Semantics of Abstract Art Using Low-Level Image Features. In Advances in Intelligent Data Analysis X, Jo ao Gama, Elizabeth Bradley, and Jaakko Hollm\u00e9n (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 413-423."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928998"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_79_1","volume-title":"Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition. In International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:4963251","author":"Zhu Xinge","year":"2017","unstructured":"Xinge Zhu, L. Li, W. Zhang, Tianrong Rao, Min Xu, Qingming Huang, and Dong Xu. 2017. Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition. In International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:4963251"}],"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\/3746027.3754549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:12:39Z","timestamp":1765339959000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":79,"alternative-id":["10.1145\/3746027.3754549","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754549","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"}}]}}