{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:48:44Z","timestamp":1775144924058,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301432,6230624"],"award-info":[{"award-number":["62301432,6230624"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2023 - JC - QN - 0685,QCYRCXM - 2023 - 057"],"award-info":[{"award-number":["2023 - JC - QN - 0685,QCYRCXM - 2023 - 057"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for Central Universities"},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2025A1515011119"],"award-info":[{"award-number":["2025A1515011119"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755471","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"6958-6966","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Text-Visual Semantic Constrained AI-Generated Image Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5749-0593","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1010-3540","authenticated-orcid":false,"given":"Qingsen","family":"Yan","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-712X","authenticated-orcid":false,"given":"Haojian","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-6798","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4336-5558","authenticated-orcid":false,"given":"Haokui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_4_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arxiv:2010:11929","author":"Dosovitskiy Alexey","year":"2020","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. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arxiv:2010:11929 (2020)."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"27","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 27."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3370633"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3464648"},{"key":"e_1_3_2_2_8_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. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33. 6840-6851.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_9_1","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain Yonatan","year":"2023","unstructured":"Yonatan Kirstain, Alex Polyak, Uri Singer, Shaked Matiana, Joao Penna, and Omer Levy. 2023. Pick-a-pic: An open dataset of user preferences for text-to-image generation. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36. 36652-36663.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 12888-12900","author":"Li Jin","unstructured":"Jin Li, Dong Li, Caiming Xiong, and Steven C. H. Hoi. 2022. Blip: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In Proceedings of the International Conference on Machine Learning. PMLR, 12888-12900."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245991"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1974.1055250"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2147325"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00644"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25302"},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models from Natural Language Supervision. In Proceedings of the International Conference on Machine Learning. PMLR, 8748-8763."},{"key":"e_1_3_2_2_22_1","first-page":"25278","article-title":"Laion-5b: An Open Large-Scale Dataset for Training Next Generation Image-Text Models","volume":"35","author":"Schuhmann Christian","year":"2022","unstructured":"Christian Schuhmann, Ross Beaumont, Robert Vencu, Conrad Gordon, Ross Wightman, Mehdi Cherti, Alexander Kolesnikov, Bernt Schiele, Sylvain Gelly, and Jaroslav Jitsev. 2022. Laion-5b: An Open Large-Scale Dataset for Training Next Generation Image-Text Models. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 35. 25278-25294.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the IEEE International Conference on Multimedia and Expo. IEEE, 1-6.","author":"Tang Zhenchen","year":"2024","unstructured":"Zhenchen Tang, Zichuan Wang, Bo Peng, and Jing Dong. 2024. Bringing textual prompt to ai-generated image quality assessment. In Proceedings of the IEEE International Conference on Multimedia and Expo. IEEE, 1-6."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78125-4_4"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2025.3538862"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of the CAAI International Conference on Artificial Intelligence. Springer Nature Singapore, 46-57","author":"Wang Jiarui","year":"2023","unstructured":"Jiarui Wang, Huiyu Duan, Jing Liu, Shi Chen, Xiongkuo Min, and Guangtao Zhai. 2023b. Aigciqa2023: A large-scale image quality assessment database for ai generated images: from the perspectives of quality, authenticity and correspondence. In Proceedings of the CAAI International Conference on Artificial Intelligence. Springer Nature Singapore, 46-57."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681471"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"e_1_3_2_2_31_1","volume-title":"AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity. arXiv preprint arXiv:2411.16087","author":"Xia Jili","year":"2024","unstructured":"Jili Xia, Lihuo He, Fei Gao, Kaifan Zhang, Leida Li, and Xinbo Gao. 2024. AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity. arXiv preprint arXiv:2411.16087 (2024)."},{"key":"e_1_3_2_2_32_1","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36. 15903-15935.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00641"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00663"},{"key":"e_1_3_2_2_35_1","volume-title":"TIER: Text-Image Encoder-based Regression for AIGC Image Quality Assessment. arXiv preprint arXiv:2401.03854","author":"Yuan Jiquan","year":"2024","unstructured":"Jiquan Yuan, Xinyan Cao, Jinming Che, Qinyuan Wang, Sen Liang, Wei Ren, Jinlong Lin, and Xixin Cao. 2024. TIER: Text-Image Encoder-based Regression for AIGC Image Quality Assessment. arXiv preprint arXiv:2401.03854 (2024)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445770"}],"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\/3746027.3755471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T01:46:45Z","timestamp":1769996805000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":40,"alternative-id":["10.1145\/3746027.3755471","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755471","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"}}]}}