{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:45:22Z","timestamp":1792514722063,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":49,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332010"],"award-info":[{"award-number":["62332010"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680662","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T02:59:27Z","timestamp":1729911567000},"page":"10939-10947","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["COCO-LC: Colorfulness Controllable Language-based Colorization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6653-4996","authenticated-orcid":false,"given":"Yifan","family":"Li","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0649-2304","authenticated-orcid":false,"given":"Yuhang","family":"Bai","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5576-8629","authenticated-orcid":false,"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9576","authenticated-orcid":false,"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jason Antic. 2019. DeOldify: A Deep Learning Based Project for Colorizing and Restoring Old Images (and Video!). https:\/\/github.com\/jantic\/DeOldify"},{"key":"e_1_3_2_1_2_1","unstructured":"Arpit Bansal Eitan Borgnia Hong-Min Chu Jie Li Hamid Kazemi Furong Huang Micah Goldblum Jonas Geiping and Tom Goldstein. 2024. Cold diffusion: Inverting arbitrary image transforms without noise. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_3_1","volume-title":"Coco-stuff: Thing and stuff classes in context","author":"Caesar Holger","year":"2018","unstructured":"Holger Caesar, Jasper Uijlings, and Vittorio Ferrari. 2018. Coco-stuff: Thing and stuff classes in context. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_10"},{"key":"e_1_3_2_1_5_1","volume-title":"L-CoDer: Language-based Colorization with Color-object Decoupling Transformer. In European Conference on Computer Vision.","author":"Chang Zheng","year":"2022","unstructured":"Zheng Chang, Shuchen Weng, Yu Li, Si Li, and Boxin Shi. 2022. L-CoDer: Language-based Colorization with Color-object Decoupling Transformer. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Zheng Chang Shuchen Weng Peixuan Zhang Yu Li Si Li and Boxin Shi. 2023. L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors. In Advances in Neural Information Processing Systems.","DOI":"10.1109\/CVPR52729.2023.01842"},{"key":"e_1_3_2_1_7_1","volume-title":"L-CoIns: Language-based Colorization with Instance Awareness","author":"Chang Zheng","unstructured":"Zheng Chang, Shuchen Weng, Peixuan Zhang, Yu Li, Si Li, and Boxin Shi. 2023. L-CoIns: Language-based Colorization with Instance Awareness. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_8_1","volume-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng Bowen","unstructured":"Bowen Cheng, Ishan Misra, Alexander G Schwing, Alexander Kirillov, and Rohit Girdhar. 2022. Masked-attention mask transformer for universal image segmentation. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_12_1","volume-title":"Pixcolor: Pixel recursive colorization. arXiv:1705.07208","author":"Guadarrama Sergio","year":"2017","unstructured":"Sergio Guadarrama, Ryan Dahl, David Bieber, Mohammad Norouzi, Jonathon Shlens, and Kevin Murphy. 2017. Pixcolor: Pixel recursive colorization. arXiv:1705.07208 (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"David Hasler and Sabine E Suesstrunk. 2003. Measuring colorfulness in natural images. In Human Vision and Electronic Imaging VIII.","DOI":"10.1117\/12.477378"},{"key":"e_1_3_2_1_14_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555471"},{"key":"e_1_3_2_1_17_1","volume-title":"Scope of validity of PSNR in image\/video quality assessment. Electronics Letters","author":"Huynh-Thu Quan","year":"2008","unstructured":"Quan Huynh-Thu and Mohammed Ghanbari. 2008. Scope of validity of PSNR in image\/video quality assessment. Electronics Letters (2008)."},{"key":"e_1_3_2_1_18_1","volume-title":"ACM Transactions on Graphics","volume":"35","author":"Iizuka Satoshi","year":"2016","unstructured":"Satoshi Iizuka, Edgar Simo-Serra, and Hiroshi Ishikawa. 2016. Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Transactions on Graphics, Vol. 35 (2016)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_2"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481544"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00037"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_21"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_25_1","volume-title":"Colorization Transformer. In Proc. Int'l Conf. Learning Representations.","author":"Kumar Manoj","year":"2021","unstructured":"Manoj Kumar, Dirk Weissenborn, and Nal Kalchbrenner. 2021. Colorization Transformer. In Proc. Int'l Conf. Learning Representations."},{"key":"e_1_3_2_1_26_1","volume-title":"IEEE International Conference on Machine Learning.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In IEEE International Conference on Machine Learning."},{"key":"e_1_3_2_1_27_1","volume-title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization. In European Conference on Computer Vision.","author":"Li Zekun","year":"2022","unstructured":"Zekun Li, Zhengyang Geng, Zhao Kang, Wenyu Chen, and Yibo Yang. 2022. Eliminating Gradient Conflict in Reference-based Line-Art Colorization. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_28_1","volume-title":"Control Color: Multimodal Diffusion-based Interactive Image Colorization. arXiv:2402.10855","author":"Liang Zhexin","year":"2024","unstructured":"Zhexin Liang, Zhaochen Li, Shangchen Zhou, Chongyi Li, and Chen Change Loy. 2024. Control Color: Multimodal Diffusion-based Interactive Image Colorization. arXiv:2402.10855 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Diffbir: Towards blind image restoration with generative diffusion prior. arXiv:2308.15070","author":"Lin Xinqi","year":"2023","unstructured":"Xinqi Lin, Jingwen He, Ziyan Chen, Zhaoyang Lyu, Ben Fei, Bo Dai, Wanli Ouyang, Yu Qiao, and Chao Dong. 2023. Diffbir: Towards blind image restoration with generative diffusion prior. arXiv:2308.15070 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Semantic Image Synthesis With Spatially-Adaptive Normalization","author":"Park Taesung","unstructured":"Taesung Park, Ming-Yu Liu, Ting-Chun Wang, and Jun-Yan Zhu. 2019. Semantic Image Synthesis With Spatially-Adaptive Normalization. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_31_1","volume-title":"IEEE International Conference on Machine Learning.","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 IEEE International Conference on Machine Learning."},{"key":"e_1_3_2_1_32_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 (2022)."},{"key":"e_1_3_2_1_33_1","volume-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach Robin","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_34_1","volume-title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz Nataniel","year":"2023","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_35_1","volume-title":"Instance-aware Image Colorization","author":"Su Jheng-Wei","unstructured":"Jheng-Wei Su, Hung-Kuo Chu, and Jia-Bin Huang. 2020. Instance-aware Image Colorization. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_37_1","volume-title":"ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution. In IEEE\/CVF Winter Conference on Applications of Computer Vision.","author":"Vitoria Patricia","year":"2020","unstructured":"Patricia Vitoria, Lara Raad, and Coloma Ballester. 2020. ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution. In IEEE\/CVF Winter Conference on Applications of Computer Vision."},{"key":"e_1_3_2_1_38_1","volume-title":"PalGAN: Image Colorization with Palette Generative Adversarial Networks. In European Conference on Computer Vision.","author":"Wang Yi","year":"2022","unstructured":"Yi Wang, Menghan Xia, Lu Qi, Jing Shao, and Yu Qiao. 2022. PalGAN: Image Colorization with Palette Generative Adversarial Networks. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_39_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing (2004)."},{"key":"e_1_3_2_1_40_1","volume-title":"European Conference on Computer Vision.","author":"Weng Shuchen","year":"2022","unstructured":"Shuchen Weng, Jimeng Sun, Yu Li, Si Li, and Boxin Shi. 2022. CT2: Colorization Transformer via Color Tokens. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_41_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Weng Shuchen","year":"2022","unstructured":"Shuchen Weng, Hao Wu, Zheng Chang, Jiajun Tang, Si Li, and Boxin Shi. 2022. L-CoDe: Language-based colorization using color-object decoupled conditions. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612182"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00183"},{"key":"e_1_3_2_1_45_1","volume-title":"Diffusing Colors: Image Colorization with Text Guided Diffusion. In ACM SIGGPRAH Asia.","author":"Zabari Nir","year":"2023","unstructured":"Nir Zabari, Aharon Azulay, Alexey Gorkor, Tavi Halperin, and Ohad Fried. 2023. Diffusing Colors: Image Colorization with Text Guided Diffusion. In ACM SIGGPRAH Asia."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_2_1_48_1","volume-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang Richard","unstructured":"Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE\/CVF International Conferece on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01271-4"}],"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\/3664647.3680662","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:17:57Z","timestamp":1750281477000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":49,"alternative-id":["10.1145\/3664647.3680662","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680662","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"}}]}}