{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:30:48Z","timestamp":1770975048937,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681621","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"2671-2680","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Learning A Low-Level Vision Generalist via Visual Task Prompt"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2156-4959","authenticated-orcid":false,"given":"Xiangyu","family":"Chen","sequence":"first","affiliation":[{"name":"University of Macau & Shanghai Artificial Intelligence Laboratory, & Shenzhen Institutes of Advanced Technology, CAS, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9874-0602","authenticated-orcid":false,"given":"Yihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory & Shenzhen Institute of Advanced Technology, CAS, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3764-0370","authenticated-orcid":false,"given":"Yuandong","family":"Pu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-260X","authenticated-orcid":false,"given":"Wenlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory & The Hong Kong Polytechnic University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6015-2618","authenticated-orcid":false,"given":"Jiantao","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory & Shenzhen Institute of Advanced Technology, CAS, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2260-8079","authenticated-orcid":false,"given":"Chao","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory & Shenzhen Institutes of Advanced Technology, CAS, & Shenzhen University of Advanced Technology, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings, Part X 16","author":"Abuolaim Abdullah","year":"2020","unstructured":"Abdullah Abuolaim and Michael S Brown. 2020. Defocus deblurring using dual-pixel data. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part X 16. Springer, 111--126."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2629645","article-title":"Fast local laplacian filters: Theory and applications","volume":"33","author":"Aubry Mathieu","year":"2014","unstructured":"Mathieu Aubry, Sylvain Paris, Samuel W Hasinoff, Jan Kautz, and Fr\u00e9do Durand. 2014. Fast local laplacian filters: Theory and applications. ACM Transactions on Graphics (TOG), Vol. 33, 5 (2014), 1--14.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_3_1","first-page":"25005","article-title":"Visual prompting via image inpainting","volume":"35","author":"Bar Amir","year":"2022","unstructured":"Amir Bar, Yossi Gandelsman, Trevor Darrell, Amir Globerson, and Alexei Efros. 2022. Visual prompting via image inpainting. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25005--25017.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_5_1","volume-title":"CVPR","author":"Bychkovsky Vladimir","year":"2011","unstructured":"Vladimir Bychkovsky, Sylvain Paris, Eric Chan, and Fr\u00e9do Durand. 2011. Learning photographic global tonal adjustment with a database of input\/output image pairs. In CVPR 2011. IEEE, 97--104."},{"key":"e_1_3_2_1_6_1","volume-title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement. arXiv preprint arXiv:2303.06705","author":"Cai Yuanhao","year":"2023","unstructured":"Yuanhao Cai, Hao Bian, Jing Lin, Haoqian Wang, Radu Timofte, and Yulun Zhang. 2023. Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement. arXiv preprint arXiv:2303.06705 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00347"},{"key":"e_1_3_2_1_8_1","volume-title":"A Comparative Study of Image Restoration Networks for General Backbone Network Design. arXiv preprint arXiv:2310.11881","author":"Chen Xiangyu","year":"2023","unstructured":"Xiangyu Chen, Zheyuan Li, Yuandong Pu, Yihao Liu, Jiantao Zhou, Yu Qiao, and Chao Dong. 2023. A Comparative Study of Image Restoration Networks for General Backbone Network Design. arXiv preprint arXiv:2310.11881 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00045"},{"key":"e_1_3_2_1_10_1","volume-title":"HAT: Hybrid Attention Transformer for Image Restoration. arXiv preprint arXiv:2309.05239","author":"Chen Xiangyu","year":"2023","unstructured":"Xiangyu Chen, Xintao Wang, Wenlong Zhang, Xiangtao Kong, Yu Qiao, Jiantao Zhou, and Chao Dong. 2023. HAT: Hybrid Attention Transformer for Image Restoration. arXiv preprint arXiv:2309.05239 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00446"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.73"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy","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 International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_17_1","volume-title":"Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM transactions on graphics (TOG)","author":"Farbman Zeev","year":"2008","unstructured":"Zeev Farbman, Raanan Fattal, Dani Lischinski, and Richard Szeliski. 2008. Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM transactions on graphics (TOG), Vol. 27, 3 (2008), 1--10."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073592"},{"key":"e_1_3_2_1_19_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00837"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings, Part II 14","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part II 14. Springer, 694--711."},{"key":"e_1_3_2_1_23_1","volume-title":"arXiv:2304.02643","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Doll\u00e1r, and Ross Girshick. 2023. Segment Anything. arXiv:2304.02643 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01693"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867951"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2955241"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"e_1_3_2_1_29_1","volume-title":"Unifying image processing as visual prompting question answering. arXiv preprint arXiv:2310.10513","author":"Liu Yihao","year":"2023","unstructured":"Yihao Liu, Xiangyu Chen, Xianzheng Ma, Xintao Wang, Jiantao Zhou, Yu Qiao, and Chao Dong. 2023. Unifying image processing as visual prompting question answering. arXiv preprint arXiv:2310.10513 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2330147.2330161"},{"key":"e_1_3_2_1_31_1","volume-title":"ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration. arXiv preprint arXiv:2306.13653","author":"Ma Jiaqi","year":"2023","unstructured":"Jiaqi Ma, Tianheng Cheng, Guoli Wang, Qian Zhang, Xinggang Wang, and Lefei Zhang. 2023. ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration. arXiv preprint arXiv:2306.13653 (2023)."},{"key":"e_1_3_2_1_32_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 1923--1932","author":"Poma Xavier Soria","year":"2020","unstructured":"Xavier Soria Poma, Edgar Riba, and Angel Sappa. 2020. Dense extreme inception network: Towards a robust cnn model for edge detection. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 1923--1932."},{"key":"e_1_3_2_1_34_1","volume-title":"Salman Khan, and Fahad Shahbaz Khan.","author":"Potlapalli Vaishnav","year":"2023","unstructured":"Vaishnav Potlapalli, Syed Waqas Zamir, Salman Khan, and Fahad Shahbaz Khan. 2023. PromptIR: Prompting for All-in-One Blind Image Restoration. arXiv preprint arXiv:2306.13090 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"A comprehensive overview of image enhancement techniques. Archives of Computational Methods in Engineering","author":"Qi Yunliang","year":"2021","unstructured":"Yunliang Qi, Zhen Yang, Wenhao Sun, Meng Lou, Jing Lian, Wenwei Zhao, Xiangyu Deng, and Yide Ma. 2021. A comprehensive overview of image enhancement techniques. Archives of Computational Methods in Engineering (2021), 1--25."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSA.62.000055"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01044"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"e_1_3_2_1_41_1","volume-title":"Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560","author":"Wei Chen","year":"2018","unstructured":"Chen Wei, Wenjing Wang, Wenhan Yang, and Jiaying Liu. 2018. Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560 (2018)."},{"key":"e_1_3_2_1_42_1","unstructured":"Jerry Wei Jason Wei Yi Tay Dustin Tran Albert Webson Yifeng Lu Xinyun Chen Hanxiao Liu Da Huang Denny Zhou et al. 2023. Larger language models do in-context learning differently. arXiv preprint arXiv:2303.03846 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Structure extraction from texture via relative total variation. ACM transactions on graphics (TOG)","author":"Xu Li","year":"2012","unstructured":"Li Xu, Qiong Yan, Yang Xia, and Jiaya Jia. 2012. Structure extraction from texture via relative total variation. ACM transactions on graphics (TOG), Vol. 31, 6 (2012), 1--10."},{"key":"e_1_3_2_1_44_1","volume-title":"Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968","author":"Yang Jinyu","year":"2023","unstructured":"Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, and Feng Zheng. 2023. Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.183"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.183"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00475"},{"key":"e_1_3_2_1_49_1","volume-title":"Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising","author":"Zhang Kai","year":"2017","unstructured":"Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE transactions on image processing, Vol. 26, 7 (2017), 3142--3155."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681621","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":50,"alternative-id":["10.1145\/3664647.3681621","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681621","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"}}]}}