{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:12:16Z","timestamp":1767262336857,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Pujiang Program","award":["22PJ1406800"],"award-info":[{"award-number":["22PJ1406800"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301310, 62225112, 623B2073"],"award-info":[{"award-number":["62301310, 62225112, 623B2073"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2024NSFSC1426"],"award-info":[{"award-number":["2024NSFSC1426"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681152","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"7375-7384","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["G-Refine: A General Quality Refiner for Text-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0634-1710","authenticated-orcid":false,"given":"Chunyi","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-8101","authenticated-orcid":false,"given":"Haoning","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4270-8455","authenticated-orcid":false,"given":"Hongkun","family":"Hao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1510-027X","authenticated-orcid":false,"given":"Tengchuan","family":"Kou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6137-5162","authenticated-orcid":false,"given":"Chaofeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3378-7201","authenticated-orcid":false,"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_2_1","volume-title":"TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment. arxiv: 2308.03060 [cs.CV]","author":"Chen Chaofeng","year":"2023","unstructured":"Chaofeng Chen, Jiadi Mo, Jingwen Hou, Haoning Wu, Liang Liao, Wenxiu Sun, Qiong Yan, and Weisi Lin. 2023. TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment. arxiv: 2308.03060 [cs.CV]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02130"},{"key":"e_1_3_2_1_4_1","first-page":"00426","article-title":"PixArt-\u03b1","volume":"2310","author":"Chen Junsong","year":"2023","unstructured":"Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. 2023. PixArt-\u03b1: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis. 2310.00426.","journal-title":"Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis."},{"key":"e_1_3_2_1_5_1","unstructured":"Zijian Chen Wei Sun Haoning Wu Zicheng Zhang Jun Jia Zhongpeng Ji Fengyu Sun Shangling Jui Xiongkuo Min Guangtao Zhai and Wenjun Zhang. 2024. Exploring the Naturalness of AI-Generated Images. arxiv: 2312.05476 [cs.CV]"},{"key":"e_1_3_2_1_6_1","volume-title":"European Conference on Computer Vision. Springer, 669--687","author":"Conde Marcos V","year":"2022","unstructured":"Marcos V Conde, Ui-Jin Choi, Maxime Burchi, and Radu Timofte. 2022. Swin2sr: Swinv2 transformer for compressed image super-resolution and restoration. In European Conference on Computer Vision. Springer, 669--687."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Marcos V. Conde Gregor Geigle and Radu Timofte. 2024. InstructIR: High-Quality Image Restoration Following Human Instructions. arxiv: 2401.16468 [cs.CV]","DOI":"10.1007\/978-3-031-72764-1_1"},{"key":"e_1_3_2_1_8_1","unstructured":"DeepFloyd. 2023. IF-I-XL-v1.0. https:\/\/www.deepfloyd.ai."},{"key":"e_1_3_2_1_9_1","unstructured":"dreamlike art. 2023. dreamlike-photoreal-2.0. https:\/\/dreamlike.art."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Learning Representations","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00081"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Kirstain Yuval","year":"2024","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2024. Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Tengchuan Kou Xiaohong Liu Zicheng Zhang Chunyi Li Haoning Wu Xiongkuo Min Guangtao Zhai and Ning Liu. 2024. Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment. arxiv: 2403.11956 [cs.CV]"},{"key":"e_1_3_2_1_17_1","unstructured":"Chunyi Li Tengchuan Kou Yixuan Gao Yuqin Cao Wei Sun Zicheng Zhang Yingjie Zhou Zhichao Zhang Weixia Zhang Haoning Wu Xiaohong Liu Xiongkuo Min and Guangtao Zhai. 2024. AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment. arxiv: 2404.03407 [cs.CV]"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00286"},{"key":"e_1_3_2_1_19_1","volume-title":"MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model. arxiv: 2402.16749 [cs.CV]","author":"Li Chunyi","year":"2024","unstructured":"Chunyi Li, Guo Lu, Donghui Feng, Haoning Wu, Zicheng Zhang, Xiaohong Liu, Guangtao Zhai, Weisi Lin, and Wenjun Zhang. 2024. MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model. arxiv: 2402.16749 [cs.CV]"},{"key":"e_1_3_2_1_20_1","unstructured":"Chunyi Li Haoning Wu Zicheng Zhang Hongkun Hao Kaiwei Zhang Lei Bai Xiaohong Liu Xiongkuo Min Weisi Lin and Guangtao Zhai. 2024 d. Q-Refine: A Perceptual Quality Refiner for AI-Generated Image. arxiv: 2401.01117 [cs.CV]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949270"},{"key":"e_1_3_2_1_22_1","volume-title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","author":"Li Chunyi","year":"2023","unstructured":"Chunyi Li, Zicheng Zhang, Haoning Wu, Wei Sun, Xiongkuo Min, Xiaohong Liu, Guangtao Zhai, and Weisi Lin. 2023. AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_23_1","unstructured":"Yanyu Li Xian Liu Anil Kag Ju Hu Yerlan Idelbayev Dhritiman Sagar Yanzhi Wang Sergey Tulyakov and Jian Ren. 2024. TextCraftor: Your Text Encoder Can be Image Quality Controller. arxiv: 2403.18978 [cs.CV]"},{"key":"e_1_3_2_1_24_1","unstructured":"Yi Li Hualiang Wang Yiqun Duan and Xiaomeng Li. 2023. CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks. arxiv: 2304.05653 [cs.CV]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Xinqi Lin Jingwen He Ziyan Chen Zhaoyang Lyu Bo Dai Fanghua Yu Wanli Ouyang Yu Qiao and Chao Dong. 2024. DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior. arxiv: 2308.15070 [cs.CV]","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_2"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00637"},{"key":"e_1_3_2_1_28_1","volume-title":"Perceptual video quality assessment: A survey. arXiv preprint arXiv:2402.03413","author":"Min Xiongkuo","year":"2024","unstructured":"Xiongkuo Min, Huiyu Duan, Wei Sun, Yucheng Zhu, and Guangtao Zhai. 2024. Perceptual video quality assessment: A survey. arXiv preprint arXiv:2402.03413 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_1_33_1","volume-title":"W\u00fcrstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models. In The Twelfth International Conference on Learning Representations.","author":"Pernias Pablo","year":"2024","unstructured":"Pablo Pernias, Dominic Rampas, Mats Leon Richter, Christopher Pal, and Marc Aubreville. 2024. W\u00fcrstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arxiv: 2307.01952 [cs.CV]","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arxiv: 2307.01952 [cs.CV]"},{"key":"e_1_3_2_1_35_1","unstructured":"Leigang Qu Wenjie Wang Yongqi Li Hanwang Zhang Liqiang Nie and Tat-Seng Chua. 2024. Discriminative Probing and Tuning for Text-to-Image Generation. arxiv: 2403.04321 [cs.CV]"},{"key":"e_1_3_2_1_36_1","volume-title":"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, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_37_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. 2204.06125."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_40_1","unstructured":"Robin Rombach Andreas Blattmann and Bj\u00f6rn Ommer. 2022. Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models. 2207.13038."},{"key":"e_1_3_2_1_41_1","unstructured":"Chenyang Si Ziqi Huang Yuming Jiang and Ziwei Liu. 2023. FreeU: Free Lunch in Diffusion U-Net. arxiv: 2309.11497 [cs.CV]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_43_1","volume-title":"NIMA: Neural image assessment","author":"Talebi Hossein","year":"2018","unstructured":"Hossein Talebi and Peyman Milanfar. 2018. NIMA: Neural image assessment. IEEE transactions on image processing, Vol. 27, 8 (2018), 3998--4011."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Jianyi Wang Zongsheng Yue Shangchen Zhou Kelvin C. K. Chan and Chen Change Loy. 2023 d. Exploiting Diffusion Prior for Real-World Image Super-Resolution. arxiv: 2305.07015 [cs.CV]","DOI":"10.1007\/s11263-024-02168-7"},{"key":"e_1_3_2_1_46_1","first-page":"4577","article-title":"Active fine-tuning from gMAD examples improves blind image quality assessment","volume":"44","author":"Wang Zhihua","year":"2021","unstructured":"Zhihua Wang and Kede Ma. 2021. Active fine-tuning from gMAD examples improves blind image quality assessment. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4577--4590.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01599"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262424"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01318"},{"key":"e_1_3_2_1_51_1","unstructured":"Haoning Wu Zicheng Zhang Erli Zhang Chaofeng Chen Liang Liao Annan Wang Chunyi Li Wenxiu Sun Qiong Yan Guangtao Zhai et al. 2023 d. Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision. arxiv: 2309.14181 [cs.CV]"},{"key":"e_1_3_2_1_52_1","unstructured":"Haoning Wu Zicheng Zhang Erli Zhang Chaofeng Chen Liang Liao Annan Wang Kaixin Xu Chunyi Li Jingwen Hou Guangtao Zhai et al. 2023 e. Q-instruct: Improving low-level visual abilities for multi-modality foundation models. arxiv: 2311.06783 [cs.CV]"},{"key":"e_1_3_2_1_53_1","unstructured":"Haoning Wu Zicheng Zhang Weixia Zhang Chaofeng Chen Liang Liao Chunyi Li Yixuan Gao Annan Wang Erli Zhang Wenxiu Sun et al. 2023. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. arxiv: 2312.17090 [cs.CV]"},{"key":"e_1_3_2_1_54_1","unstructured":"Haoning Wu Hanwei Zhu Zicheng Zhang Erli Zhang Chaofeng Chen Liang Liao Chunyi Li Annan Wang Wenxiu Sun Qiong Yan Xiaohong Liu Guangtao Zhai Shiqi Wang and Weisi Lin. 2024. Towards Open-ended Visual Quality Comparison. arxiv: 2402.16641 [cs.CV]"},{"key":"e_1_3_2_1_55_1","unstructured":"Xiaoshi Wu Yiming Hao Keqiang Sun Yixiong Chen Feng Zhu Rui Zhao and Hongsheng Li. 2023. Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis. arxiv: 2306.09341 [cs.CV]"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"e_1_3_2_1_57_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2024. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"Aigcoiqa2024: Perceptual quality assessment of ai generated omnidirectional images. arXiv preprint arXiv:2404.01024","author":"Yang Liu","year":"2024","unstructured":"Liu Yang, Huiyu Duan, Long Teng, Yucheng Zhu, Xiaohong Liu, Menghan Hu, Xiongkuo Min, Guangtao Zhai, and Patrick Le Callet. 2024. Aigcoiqa2024: Perceptual quality assessment of ai generated omnidirectional images. arXiv preprint arXiv:2404.01024 (2024)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Tao Yang Rongyuan Wu Peiran Ren Xuansong Xie and Lei Zhang. 2024. Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization. arxiv: 2308.14469 [cs.CV]","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"e_1_3_2_1_65_1","volume-title":"Gms-3dqa: Projection-based grid mini-patch sampling for 3d model quality assessment. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Zhang Zicheng","year":"2023","unstructured":"Zicheng Zhang, Wei Sun, Haoning Wu, Yingjie Zhou, Chunyi Li, Zijian Chen, Xiongkuo Min, Guangtao Zhai, and Weisi Lin. 2023. Gms-3dqa: Projection-based grid mini-patch sampling for 3d model quality assessment. ACM Transactions on Multimedia Computing, Communications and Applications (2023)."},{"key":"e_1_3_2_1_66_1","unstructured":"Zicheng Zhang Wei Sun Yingjie Zhou Haoning Wu Chunyi Li Xiongkuo Min Xiaohong Liu Guangtao Zhai and Weisi Lin. 2023. Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation. arxiv: 2307.02808 [eess.IV]"},{"key":"e_1_3_2_1_67_1","unstructured":"Zicheng Zhang Haoning Wu Zhongpeng Ji Chunyi Li Erli Zhang Wei Sun Xiaohong Liu Xiongkuo Min Fengyu Sun Shangling Jui et al. 2023 d. Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models. arxiv: 2312.15300 [cs.CV]"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3345656"},{"key":"e_1_3_2_1_69_1","volume-title":"Light-VQA: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance. arXiv preprint arXiv:2405.03333","author":"Zhou Xunchu","year":"2024","unstructured":"Xunchu Zhou, Xiaohong Liu, Yunlong Dong, Tengchuan Kou, Yixuan Gao, Zicheng Zhang, Chunyi Li, Haoning Wu, and Guangtao Zhai. 2024. Light-VQA: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance. arXiv preprint arXiv:2405.03333 (2024)."},{"key":"e_1_3_2_1_70_1","volume-title":"THQA: A Perceptual Quality Assessment Database for Talking Heads. arXiv preprint arXiv:2404.09003","author":"Zhou Yingjie","year":"2024","unstructured":"Yingjie Zhou, Zicheng Zhang, Wei Sun, Xiaohong Liu, Xiongkuo Min, Zhihua Wang, Xiao-Ping Zhang, and Guangtao Zhai. 2024. THQA: A Perceptual Quality Assessment Database for Talking Heads. arXiv preprint arXiv:2404.09003 (2024)."},{"key":"e_1_3_2_1_71_1","volume-title":"Levine (Eds.)","volume":"36","author":"Zhu Mingjian","year":"2023","unstructured":"Mingjian Zhu, Hanting Chen, Qiangyu YAN, Xudong Huang, Guanyu Lin, Wei Li, Zhijun Tu, Hailin Hu, Jie Hu, and Yunhe Wang. 2023. GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image. In Advances in Neural Information Processing Systems, A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 77771--77782."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681152","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":71,"alternative-id":["10.1145\/3664647.3681152","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681152","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}