{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T07:31:33Z","timestamp":1776238293196,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00460709"],"award-info":[{"award-number":["RS-2024-00460709"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Information & Communications Technology Planning & Evaluation","award":["RS-2024-00436936,RS-2023-00259497,RS-2025-25440264"],"award-info":[{"award-number":["RS-2024-00436936,RS-2023-00259497,RS-2025-25440264"]}]},{"name":"ETRI","award":["25ZT1100"],"award-info":[{"award-number":["25ZT1100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761180","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:36:36Z","timestamp":1762562196000},"page":"1508-1518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["BOVIS: Bias-Mitigated Object-Enhanced Visual Emotion Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4419-9185","authenticated-orcid":false,"given":"Yubeen","family":"Lee","sequence":"first","affiliation":[{"name":"Data eXperience Laboratory, Sungkyunkwan University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3828-6601","authenticated-orcid":false,"given":"Sangeun","family":"Lee","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5153-9668","authenticated-orcid":false,"given":"Junyeop","family":"Cha","sequence":"additional","affiliation":[{"name":"Data eXperience Laboratory, Sungkyunkwan University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0219-3443","authenticated-orcid":false,"given":"Jufeng","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3177-3538","authenticated-orcid":false,"given":"Eunil","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Applied Artificial Intelligence, Sungkyunkwan Universtiy, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_2_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_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502282"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-91305-2_20"},{"key":"e_1_3_2_2_4_1","unstructured":"Tao Chen Damian Borth Trevor Darrell and Shih-Fu Chang. 2014. DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks. https:\/\/arxiv.org\/abs\/1410.8586"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2388370"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: towards general-purpose vision-language models with instruction tuning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '23). Curran Associates Inc., Red Hook, NY, USA, Article 2142, 18 pages."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_8_1","volume-title":"International Conference on Learning Representations. 1-22","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, G Heigold, S Gelly, et al., 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. 1-22."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_10_1","first-page":"1","article-title":"A multi-attentive pyramidal model for visual sentiment analysis. In 2019 international joint conference on neural networks (IJCNN)","author":"He Xiaohao","year":"2019","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.","journal-title":"IEEE"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396330"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472195"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00328"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521707"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00560"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217414"},{"key":"e_1_3_2_2_19_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_2_20_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393384"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873965"},{"key":"e_1_3_2_2_23_1","volume-title":"Emotional category data on images from the International Affective Picture System. Behavior research methods","author":"Mikels Joseph A","year":"2005","unstructured":"Joseph A Mikels, Barbara L Fredrickson, Gregory R Larkin, Casey M Lindberg, Sam J Maglio, and Patricia A Reuter-Lorenz. 2005. Emotional category data on images from the International Affective Picture System. Behavior research methods, Vol. 37 (2005), 626-630."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1086\/209044"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3016837"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.053"},{"key":"e_1_3_2_2_28_1","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 6 (2016), 1137-1149."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2964549"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874060"},{"key":"e_1_3_2_2_31_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552961"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612051"},{"key":"e_1_3_2_2_34_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Yang Fan Kai Dang Mengfei Du Xuancheng Ren Rui Men Dayiheng Liu Chang Zhou Jingren Zhou and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. https:\/\/arxiv.org\/abs\/2409.12191"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00926"},{"key":"e_1_3_2_2_36_1","volume-title":"Mohamad Nizam Bin Ayub, Hannyzzura Binti Affal, and Nornazlita Binti Hussin.","author":"Yadegaridehkordi Elaheh","year":"2019","unstructured":"Elaheh Yadegaridehkordi, Nurul Fazmidar Binti Mohd Noor, Mohamad Nizam Bin Ayub, Hannyzzura Binti Affal, and Nornazlita Binti Hussin. 2019. Affective computing in education: A systematic review and future research. Computers & education, Vol. 142 (2019), 103649."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7218"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193749"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00422"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00791"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11275"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2803520"},{"key":"e_1_3_2_2_45_1","first-page":"38","article-title":"Enhancing health care via affective computing","volume":"5","author":"Yannakakis Georgios N","year":"2018","unstructured":"Georgios N Yannakakis. 2018. Enhancing health care via affective computing. Malta Journal of Health Sciences, Vol. 5, 1 (2018), 38-42.","journal-title":"Malta Journal of Health Sciences"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10501"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9179"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07139-y"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.062"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098712"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351062"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:04:06Z","timestamp":1765505046000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761180"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":52,"alternative-id":["10.1145\/3746252.3761180","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761180","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}