{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:08:38Z","timestamp":1783105718939,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"NSFC62431015, the Fundamental Research Funds for the Central Universities, Shanghai Key Laboratory of Digital Media Processing and Transmission under Grant","award":["22DZ2229005, 111 project BP0719010"],"award-info":[{"award-number":["22DZ2229005, 111 project BP0719010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755524","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"6682-6690","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AnimeColor: Reference-based Animation Colorization with Diffusion Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8902-0013","authenticated-orcid":false,"given":"Yuhong","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2670-5397","authenticated-orcid":false,"given":"Liyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0995-0092","authenticated-orcid":false,"given":"Han","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3954-590X","authenticated-orcid":false,"given":"Danni","family":"Wu","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1281-6814","authenticated-orcid":false,"given":"Zuzeng","family":"Lin","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7669-2547","authenticated-orcid":false,"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"CreateAI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7124-5182","authenticated-orcid":false,"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"AnimeDiffusion: anime diffusion colorization","author":"Cao Yu","year":"2024","unstructured":"Yu Cao, Xiangqiao Meng, PY Mok, Tong-Yee Lee, Xueting Liu, and Ping Li. 2024. AnimeDiffusion: anime diffusion colorization. IEEE Transactions on Visualization and Computer Graphics (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Caroline Chan Fredo Durand and Phillip Isola. 2022. Learning to generate line drawings that convey geometry and semantics. (2022).","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"e_1_3_2_1_4_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et al. 2023. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3009949"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02413"},{"key":"e_1_3_2_1_7_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780-8794."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104190"},{"key":"e_1_3_2_1_9_1","volume-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725","author":"Guo Yuwei","year":"2023","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"In-context lora for diffusion transformers. arXiv preprint arXiv:2410.23775","author":"Huang Lianghua","year":"2024","unstructured":"Lianghua Huang, Wei Wang, Zhi-Fan Wu, Yupeng Shi, Huanzhang Dou, Chen Liang, Yutong Feng, Yu Liu, and Jingren Zhou. 2024a. In-context lora for diffusion transformers. arXiv preprint arXiv:2410.23775 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687910"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00915"},{"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":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_16_1","unstructured":"Zhimin Li Jianwei Zhang Qin Lin Jiangfeng Xiong Yanxin Long Xinchi Deng Yingfang Zhang Xingchao Liu Minbin Huang Zedong Xiao et al. 2024. Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding. arXiv preprint arXiv:2405.08748 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Zhiheng Liu, Yujun Shen, and Huamin Qu.","author":"Meng Yihao","year":"2024","unstructured":"Yihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Zhiheng Liu, Yujun Shen, and Huamin Qu. 2024. AniDoc: Animation Creation Made Easier. arXiv preprint arXiv:2412.14173 (2024)."},{"key":"e_1_3_2_1_18_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_19_1","unstructured":"Alibaba pai. 2024. CogVideoX-Fun. https:\/\/github.com\/aigc-apps\/CogVideoX-Fun"},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3146000"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2019.00033"},{"key":"e_1_3_2_1_25_1","volume-title":"ICLR 2019 Workshop DeepGenStruct","author":"Unterthiner Thomas","year":"2019","unstructured":"Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Rapha\u00ebl Marinier, Marcin Michalski, and Sylvain Gelly. 2019. FVD: A new metric for video generation. ICLR 2019 Workshop DeepGenStruct (2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109562"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2012.03.004"},{"key":"e_1_3_2_1_29_1","unstructured":"Xiaoyu Xiang Ding Liu Xiao Yang Yiheng Zhu and Xiaohui Shen. 2021. Anime2Sketch: A Sketch Extractor for Anime Arts with Deep Networks. https:\/\/github.com\/Mukosame\/Anime2Sketch."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687761"},{"key":"e_1_3_2_1_31_1","volume-title":"EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture. arXiv preprint arXiv:2405.18991","author":"Xu Jiaqi","year":"2024","unstructured":"Jiaqi Xu, Xinyi Zou, Kunzhe Huang, Yunkuo Chen, Bo Liu, MengLi Cheng, Xing Shi, and Jun Huang. 2024b. EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture. arXiv preprint arXiv:2405.18991 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"See Kiong Ng, and Jiashi Feng","author":"Xu Lin","year":"2024","unstructured":"Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, and Jiashi Feng. 2024a. Pllava: Parameter-free llava extension from images to videos for video dense captioning. arXiv preprint arXiv:2404.16994 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Colorizediffusion: Adjustable sketch colorization with reference image and text. arXiv preprint arXiv:2401.01456","author":"Yan Dingkun","year":"2024","unstructured":"Dingkun Yan, Liang Yuan, Erwin Wu, Yuma Nishioka, Issei Fujishiro, and Suguru Saito. 2024. Colorizediffusion: Adjustable sketch colorization with reference image and text. arXiv preprint arXiv:2401.01456 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"LayerAnimate: Layer-specific Control for Animation. arXiv preprint arXiv:2501.08295","author":"Yang Yuxue","year":"2025","unstructured":"Yuxue Yang, Lue Fan, Zuzen Lin, Feng Wang, and Zhaoxiang Zhang. 2025. LayerAnimate: Layer-specific Control for Animation. arXiv preprint arXiv:2501.08295 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072","author":"Yang Zhuoyi","year":"2024","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2229"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275090"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00392"},{"key":"e_1_3_2_1_41_1","volume-title":"Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404","author":"Zheng Zangwei","year":"2024","unstructured":"Zangwei Zheng, Xiangyu Peng, Tianji Yang, Chenhui Shen, Shenggui Li, Hongxin Liu, Yukun Zhou, Tianyi Li, and Yang You. 2024. Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356561"}],"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\/3746027.3755524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:14:41Z","timestamp":1765307681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755524"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":42,"alternative-id":["10.1145\/3746027.3755524","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755524","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"}}]}}