{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T20:37:06Z","timestamp":1782506226324,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":51,"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\/3664647.3680726","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"6784-6792","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["MultiColor: Image Colorization by Learning from Multiple Color Spaces"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4268-6114","authenticated-orcid":false,"given":"Xiangcheng","family":"Du","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-6275","authenticated-orcid":false,"given":"Zhao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9146-051X","authenticated-orcid":false,"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6753-9267","authenticated-orcid":false,"given":"Yanlong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanxi University, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0670-3929","authenticated-orcid":false,"given":"Zhuoyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5590-9292","authenticated-orcid":false,"given":"Yingbin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Videt Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3063-1957","authenticated-orcid":false,"given":"Cheng","family":"Jin","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, 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. jantic\/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","volume-title":"International Conference on Learning Representations.","author":"Brock Andrew","year":"2019","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2019. Large scale GAN training for high fidelity natural image synthesis. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_10"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_7_1","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng, Alex Schwing, and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. In Advances in Neural Information Processing Systems, Vol. 34. 17864--17875.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103712"},{"key":"e_1_3_2_1_10_1","volume-title":"The structure and properties of color spaces and the representation of color images","author":"Dubois Eric","unstructured":"Eric Dubois. 2010. The structure and properties of color spaces and the representation of color images. Vol. 11. Springer."},{"key":"e_1_3_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Goodfellow Ian","year":"2014","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, Vol. 27."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_36"},{"key":"e_1_3_2_1_13_1","volume-title":"Human vision and electronic imaging VIII","author":"Hasler David","unstructured":"David Hasler and Sabine E Suesstrunk. 2003. Measuring colorfulness in natural images. In Human vision and electronic imaging VIII, Vol. 5007. SPIE, 87--95."},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"Deep exemplar-based colorization","volume":"37","author":"He Mingming","year":"2018","unstructured":"Mingming He, Dongdong Chen, Jing Liao, Pedro V Sander, and Lu Yuan. 2018. Deep exemplar-based colorization. ACM Transactions on Graphics, Vol. 37, 4 (2018), 1--16.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel Martin","year":"2017","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, Vol. 30."},{"key":"e_1_3_2_1_16_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, Vol. 44, 13 (2008), 800--801."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_2"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00037"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/146443.146479"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_21"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations.","author":"Kolesnikov Alexander","year":"2021","unstructured":"Alexander Kolesnikov, Alexey Dosovitskiy, Dirk Weissenborn, Georg Heigold, Jakob Uszkoreit, Lucas Beyer, Matthias Minderer, Mostafa Dehghani, Neil Houlsby, Sylvain Gelly, Thomas Unterthiner, and Xiaohua Zhai. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6599-8"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations.","author":"Kumar Manoj","year":"2021","unstructured":"Manoj Kumar, Dirk Weissenborn, and Nal Kalchbrenner. 2021. Colorization transformer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076367"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8483674"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_37"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315267"},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142017"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Learning Representations.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"e_1_3_2_1_38_1","volume-title":"Deep Image Harmonization in Dual Color Spaces. In ACM International Conference on Multimedia. 2159--2167","author":"Tan Linfeng","year":"2023","unstructured":"Linfeng Tan, Jiangtong Li, Li Niu, and Liqing Zhang. 2023. Deep Image Harmonization in Dual Color Spaces. In ACM International Conference on Multimedia. 2159--2167."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","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, Vol. 30."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093389"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976573"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01717"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00282"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_1"},{"key":"e_1_3_2_1_45_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Weng Shuchen","year":"2024","unstructured":"Shuchen Weng, Peixuan Zhang, Yu Li, et al. 2024. L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01411"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.864231"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_2_1_49_1","volume-title":"Yasar Abbas Ur Rehman, Mengyang Liu, Yujia Zhang, and Weifeng Ou.","author":"Zhao Yuzhi","year":"2022","unstructured":"Yuzhi Zhao, Lai-Man Po, Wing Yin Yu, Yasar Abbas Ur Rehman, Mengyang Liu, Yujia Zhang, and Weifeng Ou. 2022. VCGAN: video colorization with hybrid generative adversarial network. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_1_51_1","volume-title":"Aggregated text transformer for scene text detection. arXiv preprint arXiv:2211.13984","author":"Zhou Zhao","year":"2022","unstructured":"Zhao Zhou, Xiangcheng Du, Yingbin Zheng, and Cheng Jin. 2022. Aggregated text transformer for scene text detection. arXiv preprint arXiv:2211.13984 (2022)."}],"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\/3664647.3680726","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:24Z","timestamp":1750291584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":51,"alternative-id":["10.1145\/3664647.3680726","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680726","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"}}]}}