{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T20:12:33Z","timestamp":1779394353934,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3681758.3698022","type":"proceedings-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T19:12:11Z","timestamp":1732043531000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5249-6100","authenticated-orcid":false,"given":"Yuki","family":"Hirakawa","sequence":"first","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1586-7530","authenticated-orcid":false,"given":"Takashi","family":"Wada","sequence":"additional","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6465-2908","authenticated-orcid":false,"given":"Kazuya","family":"Morishita","sequence":"additional","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4841-1824","authenticated-orcid":false,"given":"Ryotaro","family":"Shimizu","sequence":"additional","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9521-6514","authenticated-orcid":false,"given":"Takuya","family":"Furusawa","sequence":"additional","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8803-5842","authenticated-orcid":false,"given":"Sai Htaung","family":"Kham","sequence":"additional","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0492-414X","authenticated-orcid":false,"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"ZOZO Research, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00310"},{"key":"e_1_3_3_2_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in NeurIPS 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_4_1","volume-title":"ICLR","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 ICLR. Online."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Ralf Herbrich Tom Minka and Thore Graepel. 2006. TrueSkill\u2122: a Bayesian skill rating system. Advances in NeurIPS 19 (2006) 569\u2013576.","DOI":"10.7551\/mitpress\/7503.003.0076"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Vivek Joshy. 2024. OpenSkill: A faster asymmetric multi-team multiplayer rating system. Journal of Open Source Software 9 93 (2024) 5901.","DOI":"10.21105\/joss.05901"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_31"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Sharron Lennon. 2009. Effects of Clothing Attractiveness on Perceptions. Home Economics Research Journal 18 (2009) 303\u2013310.","DOI":"10.1177\/1077727X9001800403"},{"key":"e_1_3_3_2_9_1","volume-title":"KDD Workshops","author":"Neuberger Assaf","year":"2017","unstructured":"Assaf Neuberger, Sharon Alpert, Eli Alshan, Nati Bubis, and Eduard Oks. 2017. Learning fashion traits with label uncertainty. In KDD Workshops."},{"key":"e_1_3_3_2_10_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_11_1","first-page":"8748","volume-title":"Proceedings of ICML","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of ICML , Vol.\u00a0139. 8748\u20138763."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"C Spearman. 2010. The proof and measurement of association between two things. International Journal of Epidemiology 39 5 (2010) 1137\u20131150.","DOI":"10.1093\/ije\/dyq191"},{"key":"e_1_3_3_2_13_1","unstructured":"Peiyi Wang Lei Li Liang Chen Zefan Cai Dawei Zhu Binghuai Lin Yunbo Cao Qi Liu Tianyu Liu and Zhifang Sui. 2023. Large language models are not fair evaluators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.17926 (2023)."},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"e_1_3_3_2_15_1","unstructured":"Zhengyuan Yang Linjie Li Kevin Lin Jianfeng Wang Chung-Ching Lin Zicheng Liu and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.17421 (2023)."},{"key":"e_1_3_3_2_16_1","unstructured":"Xinlu Zhang Yujie Lu Weizhi Wang An Yan Jun Yan Lianke Qin Heng Wang Xifeng Yan William\u00a0Yang Wang and Linda\u00a0Ruth Petzold. 2023. Gpt-4v (ision) as a generalist evaluator for vision-language tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.01361 (2023)."},{"key":"e_1_3_3_2_17_1","volume-title":"ICLR","author":"Zheng Chujie","year":"2024","unstructured":"Chujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou, and Minlie Huang. 2024. Large Language Models Are Not Robust Multiple Choice Selectors. In ICLR. Online."}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Technical Communications","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Technical Communications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3681758.3698022","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3681758.3698022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:16Z","timestamp":1750295896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3681758.3698022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":16,"alternative-id":["10.1145\/3681758.3698022","10.1145\/3681758"],"URL":"https:\/\/doi.org\/10.1145\/3681758.3698022","relation":{},"subject":[],"published":{"date-parts":[[2024,11,19]]},"assertion":[{"value":"2024-11-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}