{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T12:52:55Z","timestamp":1770382375674,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":83,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192712"],"award-info":[{"award-number":["62192712"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755699","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"8815-8824","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Gamma: Toward Generic Image Assessment with Mixture of Assessment Experts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0514-0905","authenticated-orcid":false,"given":"Hantao","family":"Zhou","sequence":"first","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7184-6929","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2704-3718","authenticated-orcid":false,"given":"Longxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8414-9870","authenticated-orcid":false,"given":"Guanyi","family":"Qin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6366-3763","authenticated-orcid":false,"given":"Runze","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00565"},{"key":"e_1_3_2_1_2_1","volume-title":"Topiq: A top-down approach from semantics to distortions for image quality assessment","author":"Chen Chaofeng","year":"2024","unstructured":"Chaofeng Chen, Jiadi Mo, Jingwen Hou, Haoning Wu, Liang Liao, Wenxiu Sun, Qiong Yan, and Weisi Lin. 2024a. Topiq: A top-down approach from semantics to distortions for image quality assessment. IEEE Transactions on Image Processing (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3121875"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01591"},{"key":"e_1_3_2_1_5_1","volume-title":"PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts. arXiv preprint arXiv:2403.04993","author":"Chen Zewen","year":"2024","unstructured":"Zewen Chen, Haina Qin, Juan Wang, Chunfeng Yuan, Bing Li, Weiming Hu, and Liang Wang. 2024b. PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts. arXiv preprint arXiv:2403.04993 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456502"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111560"},{"key":"e_1_3_2_1_8_1","volume-title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066","author":"Dai Damai","year":"2024","unstructured":"Damai Dai, Chengqi Deng, Chenggang Zhao, RX Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Y Wu, et al., 2024. Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01588"},{"key":"e_1_3_2_1_10_1","first-page":"3677","article-title":"Perceptual quality assessment of smartphone photography","author":"Fang Yuming","year":"2020","unstructured":"Yuming Fang, Hanwei Zhu, Yan Zeng, Kede Ma, and Zhou Wang. 2020. Perceptual quality assessment of smartphone photography. In CVPR. 3677-3686.","journal-title":"CVPR."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"e_1_3_2_1_12_1","first-page":"372","article-title":"Massive online crowdsourced study of subjective and objective picture quality","volume":"25","author":"Ghadiyaram Deepti","year":"2015","unstructured":"Deepti Ghadiyaram and Alan C Bovik. 2015. Massive online crowdsourced study of subjective and objective picture quality. IEEE TIP, Vol. 25, 1 (2015), 372-387.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1167\/17.1.32"},{"key":"e_1_3_2_1_14_1","volume-title":"Learning a no-reference quality assessment model of enhanced images with big data","author":"Gu Ke","year":"2017","unstructured":"Ke Gu, Dacheng Tao, Jun-Fei Qiao, and Weisi Lin. 2017. Learning a no-reference quality assessment model of enhanced images with big data. IEEE transactions on neural networks and learning systems, Vol. 29, 4 (2017), 1301-1313."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168438"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25147"},{"key":"e_1_3_2_1_17_1","first-page":"942","article-title":"Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks","author":"He Shuai","year":"2022","unstructured":"Shuai He, Yongchang Zhang, Rui Xie, Dongxiang Jiang, and Anlong Ming. 2022. Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks.. In IJCAI. 942-948.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"e_1_3_2_1_19_1","first-page":"4041","article-title":"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment","volume":"29","author":"Hosu Vlad","year":"2020","unstructured":"Vlad Hosu, Hanhe Lin, Tamas Sziranyi, and Dietmar Saupe. 2020. KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment. IEEE TIP, Vol. 29 (2020), 4041-4056.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_20_1","volume-title":"Kyu Park, and Sungeun Hong. 2023. IFQA: interpretable face quality assessment. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 3444-3453","author":"Jo Byungho","unstructured":"Byungho Jo, Donghyeon Cho, In Kyu Park, and Sungeun Hong. 2023. IFQA: interpretable face quality assessment. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 3444-3453."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"e_1_3_2_1_23_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_24_1","volume-title":"Photo aesthetics ranking network with attributes and content adaptation","author":"Kong Shu","unstructured":"Shu Kong, Xiaohui Shen, Zhe Lin, Radomir Mech, and Charless Fowlkes. 2016. Photo aesthetics ranking network with attributes and content adaptation. In ECCV. Springer, 662-679."},{"key":"e_1_3_2_1_25_1","article-title":"Most apparent distortion: full-reference image quality assessment and the role of strategy","volume":"19","author":"Larson Eric C","year":"2010","unstructured":"Eric C Larson and Damon M Chandler. 2010. Most apparent distortion: full-reference image quality assessment and the role of strategy. Journal of electronic imaging, Vol. 19, 1 (2010), 011006-011006.","journal-title":"Journal of electronic imaging"},{"key":"e_1_3_2_1_26_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. 2023b. 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_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2875354"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02444"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680994"},{"key":"e_1_3_2_1_33_1","unstructured":"Yukang Lin Yan Hong Zunnan Xu Xindi Li Chao Xu Chuanbiao Song Ronghui Li Haoxing Chen Jun Lan Huijia Zhu et al. 2025b. InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation. arXiv preprint arXiv:2504.10905 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Liu Limin","year":"2024","unstructured":"Limin Liu, Shuai He, Anlong Ming, Rui Xie, and Huadong Ma. 2024a. ELTA: an enhancer against long-tail for aesthetics-oriented models. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2900941"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657722"},{"key":"e_1_3_2_1_37_1","volume-title":"UIQI: A comprehensive quality evaluation index for underwater images","author":"Liu Yutao","year":"2023","unstructured":"Yutao Liu, Ke Gu, Jingchao Cao, Shiqi Wang, Guangtao Zhai, Junyu Dong, and Sam Kwong. 2023. UIQI: A comprehensive quality evaluation index for underwater images. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2868771"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_1_41_1","first-page":"2408","article-title":"AVA: A large-scale database for aesthetic visual analysis","author":"Murray Naila","year":"2012","unstructured":"Naila Murray, Luca Marchesotti, and Florent Perronnin. 2012. AVA: A large-scale database for aesthetic visual analysis. In CVPR. IEEE, 2408-2415.","journal-title":"CVPR. IEEE"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00758"},{"key":"e_1_3_2_1_43_1","unstructured":"Wensheng Pan Timin Gao Yan Zhang Runze Hu Xiawu Zheng Enwei Zhang Yuting Gao Yutao Liu Yunhang Shen Ke Li et al. 2024. Multi-Modal Prompt Learning on Blind Image Quality Assessment. arXiv preprint arXiv:2404.14949 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"European workshop on visual information processing (EUVIP). IEEE, 106-111","author":"Ponomarenko Nikolay","year":"2013","unstructured":"Nikolay Ponomarenko, Oleg Ieremeiev, Vladimir Lukin, Karen Egiazarian, Lina Jin, Jaakko Astola, Benoit Vozel, Kacem Chehdi, Marco Carli, Federica Battisti, et al., 2013. Color image database TID2013: Peculiarities and preliminary results. In European workshop on visual information processing (EUVIP). IEEE, 106-111."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25302"},{"key":"e_1_3_2_1_46_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_47_1","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme Carlos","year":"2021","unstructured":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, Andr\u00e9 Susano Pinto, Daniel Keysers, and Neil Houlsby. 2021. Scaling vision with sparse mixture of experts. Advances in Neural Information Processing Systems, Vol. 34 (2021), 8583-8595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_49_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_1_50_1","first-page":"3440","article-title":"A statistical evaluation of recent full reference image quality assessment algorithms","volume":"15","author":"Sheikh Hamid R","year":"2006","unstructured":"Hamid R Sheikh, Muhammad F Sabir, and Alan C Bovik. 2006. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE TIP, Vol. 15, 11 (2006), 3440-3451.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_51_1","volume-title":"Going the extra mile in face image quality assessment: A novel database and model","author":"Su Shaolin","year":"2023","unstructured":"Shaolin Su, Hanhe Lin, Vlad Hosu, Oliver Wiedemann, Jinqiu Sun, Yu Zhu, Hantao Liu, Yanning Zhang, and Dietmar Saupe. 2023. Going the extra mile in face image quality assessment: A novel database and model. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"e_1_3_2_1_54_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_55_1","volume-title":"European Conference on Computer Vision. Springer, 346-365","author":"Tang Longxiang","year":"2024","unstructured":"Longxiang Tang, Zhuotao Tian, Kai Li, Chunming He, Hantao Zhou, Hengshuang Zhao, Xiu Li, and Jiaya Jia. 2024. Mind the interference: Retaining pre-trained knowledge in parameter efficient continual learning of vision-language models. In European Conference on Computer Vision. Springer, 346-365."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_58_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2022","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al., 2022. Image as a foreign language: Beit pretraining for all vision and vision-language tasks. arXiv preprint arXiv:2208.10442 (2022)."},{"key":"e_1_3_2_1_59_1","volume-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090","author":"Wu Haoning","year":"2023","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 preprint arXiv:2312.17090 (2023)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096319"},{"key":"e_1_3_2_1_62_1","volume-title":"Haploomni: Unified single transformer for multimodal video understanding and generation. arXiv preprint arXiv:2506.02975","author":"Xiao Yicheng","year":"2025","unstructured":"Yicheng Xiao, Lin Song, Rui Yang, Cheng Cheng, Zunnan Xu, Zhaoyang Zhang, Yixiao Ge, Xiu Li, and Ying Shan. 2025. Haploomni: Unified single transformer for multimodal video understanding and generation. arXiv preprint arXiv:2506.02975 (2025)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00257"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2491020"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116218"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116218"},{"key":"e_1_3_2_1_68_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang Rui","year":"2024","unstructured":"Rui Yang, Lin Song, Yanwei Li, Sijie Zhao, Yixiao Ge, Xiu Li, and Ying Shan. 2024a. Gpt4tools: Teaching large language model to use tools via self-instruction. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_69_1","volume-title":"Haplovl: A single-transformer baseline for multi-modal understanding. arXiv preprint arXiv:2503.14694","author":"Yang Rui","year":"2025","unstructured":"Rui Yang, Lin Song, Yicheng Xiao, Runhui Huang, Yixiao Ge, Ying Shan, and Hengshuang Zhao. 2025. Haplovl: A single-transformer baseline for multi-modal understanding. arXiv preprint arXiv:2503.14694 (2025)."},{"key":"e_1_3_2_1_70_1","first-page":"3575","article-title":"From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality","author":"Ying Zhenqiang","year":"2020","unstructured":"Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, and Alan Bovik. 2020. From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality. In CVPR. 3575-3585.","journal-title":"CVPR."},{"key":"e_1_3_2_1_71_1","volume-title":"Depicting beyond scores: Advancing image quality assessment through multi-modal language models. arXiv preprint arXiv:2312.08962","author":"You Zhiyuan","year":"2023","unstructured":"Zhiyuan You, Zheyuan Li, Jinjin Gu, Zhenfei Yin, Tianfan Xue, and Chao Dong. 2023. Depicting beyond scores: Advancing image quality assessment through multi-modal language models. arXiv preprint arXiv:2312.08962 (2023)."},{"key":"e_1_3_2_1_72_1","volume-title":"Pscr: Patches sampling-based contrastive regression for aigc image quality assessment. arXiv preprint arXiv:2312.05897","author":"Yuan Jiquan","year":"2023","unstructured":"Jiquan Yuan, Xinyan Cao, Linjing Cao, Jinlong Lin, and Xixin Cao. 2023. Pscr: Patches sampling-based contrastive regression for aigc image quality assessment. arXiv preprint arXiv:2312.05897 (2023)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3260212"},{"key":"e_1_3_2_1_74_1","first-page":"36","volume-title":"IEEE TCSVT","volume":"30","author":"Zhang Weixia","year":"2018","unstructured":"Weixia Zhang, Kede Ma, Jia Yan, Dexiang Deng, and Zhou Wang. 2018. Blind image quality assessment using a deep bilinear convolutional neural network. IEEE TCSVT, Vol. 30, 1 (2018), 36-47."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_1_77_1","volume-title":"Quality assessment in the era of large models: A survey. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Zhang Zicheng","year":"2024","unstructured":"Zicheng Zhang, Yingjie Zhou, Chunyi Li, Baixuan Zhao, Xiaohong Liu, and Guangtao Zhai. 2024. Quality assessment in the era of large models: A survey. ACM Transactions on Multimedia Computing, Communications and Applications (2024)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2995264"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060873"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687816"},{"key":"e_1_3_2_1_81_1","volume-title":"UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment. arXiv preprint arXiv:2406.01069","author":"Zhou Hantao","year":"2024","unstructured":"Hantao Zhou, Longxiang Tang, Rui Yang, Guanyi Qin, Yan Zhang, Runze Hu, and Xiu Li. 2024b. UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment. arXiv preprint arXiv:2406.01069 (2024)."},{"key":"e_1_3_2_1_82_1","volume-title":"Etdnet: Efficient transformer-based detection network for surface defect detection","author":"Zhou Hantao","year":"2023","unstructured":"Hantao Zhou, Rui Yang, Runze Hu, Chang Shu, Xiaochu Tang, and Xiu Li. 2023. Etdnet: Efficient transformer-based detection network for surface defect detection. IEEE transactions on instrumentation and measurement, Vol. 72 (2023), 1-14."},{"key":"e_1_3_2_1_83_1","volume-title":"Unihead: unifying multi-perception for detection heads","author":"Zhou Hantao","year":"2024","unstructured":"Hantao Zhou, Rui Yang, Yachao Zhang, Haoran Duan, Yawen Huang, Runze Hu, Xiu Li, and Yefeng Zheng. 2024c. Unihead: unifying multi-perception for detection heads. IEEE Transactions on Neural Networks and Learning Systems (2024)."}],"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\/3746027.3755699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:45Z","timestamp":1765339845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":83,"alternative-id":["10.1145\/3746027.3755699","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755699","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"}}]}}