{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:50:12Z","timestamp":1765309812178,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","funder":[{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["9678295"],"award-info":[{"award-number":["9678295"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["UGC\/FDS11\/E02\/23"],"award-info":[{"award-number":["UGC\/FDS11\/E02\/23"]}],"id":[{"id":"10.13039\/501100002920","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\/3746027.3755761","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"8891-8900","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ColorDiffuser: Video Colorization with Pretrained Text-to-Image Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3336-0686","authenticated-orcid":false,"given":"Hanyuan","family":"Liu","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6288-1611","authenticated-orcid":false,"given":"Minshan","family":"Xie","sequence":"additional","affiliation":[{"name":"Centre for Perceptual and Interactive Intelligence (CPII) Limited, Sha Tin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2181-1879","authenticated-orcid":false,"given":"Jinbo","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Sha Tin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1519-750X","authenticated-orcid":false,"given":"Chengze","family":"Li","sequence":"additional","affiliation":[{"name":"Saint Francis University, Tseung Kwan O, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0962-6723","authenticated-orcid":false,"given":"Chi-Sing","family":"Leung","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Kowloon Tong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7792-9307","authenticated-orcid":false,"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"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. https:\/\/github.com\/jantic\/DeOldify"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_27"},{"key":"e_1_3_2_1_3_1","volume-title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In IEEE International Conference on Computer Vision.","author":"Bain Max","year":"2021","unstructured":"Max Bain, Arsha Nagrani, G\u00fcl Varol, and Andrew Zisserman. 2021. Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. In IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_4_1","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation. arXiv:2302.08113 [cs.CV]"},{"key":"e_1_3_2_1_5_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. arXiv:2311.15127 [cs.CV]"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818107"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657509"},{"key":"e_1_3_2_1_8_1","volume-title":"Efros","author":"Brooks Tim","year":"2023","unstructured":"Tim Brooks, Aleksander Holynski, and Alexei A. Efros. 2023. InstructPix2Pix: Learning to Follow Image Editing Instructions. arXiv:2211.09800 [cs.CV]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2288929"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766978"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.72"},{"key":"e_1_3_2_1_12_1","volume-title":"Deepprop: Extracting deep features from a single image for edit propagation. In Computer Graphics Forum (CGF).","author":"Endo Yuki","year":"2016","unstructured":"Yuki Endo, Satoshi Iizuka, Yoshihiro Kanamori, and Jun Mitani. 2016. Deepprop: Extracting deep features from a single image for edit propagation. In Computer Graphics Forum (CGF)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Patrick Esser Johnathan Chiu Parmida Atighehchian Jonathan Granskog and Anastasis Germanidis. 2023. Structure and Content-Guided Video Synthesis with Diffusion Models. arXiv:2302.03011 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"volume-title":"Human vision and electronic imaging VIII","author":"Hasler David","key":"e_1_3_2_1_15_1","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_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201365"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292482"},{"key":"e_1_3_2_1_18_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS).","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 Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_19_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS).","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356570"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.336"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_2"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00037"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_21"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","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 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Kumar Manoj","year":"2021","unstructured":"Manoj Kumar, Dirk Weissenborn, and Nal Kalchbrenner. 2021. Colorization transformer. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_30_1","volume-title":"Trung Bui, and Daisuke Kihara.","author":"Lai Tuan","year":"2019","unstructured":"Tuan Lai, Quan Hung Tran, Trung Bui, and Daisuke Kihara. 2019. A Gated Self-attention Memory Network for Answer Selection. arXiv:1909.09696 [cs.CL]"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"e_1_3_2_1_32_1","volume-title":"Learning Blind Video Temporal Consistency. In European Conference on Computer Vision.","author":"Lai Wei-Sheng","year":"2018","unstructured":"Wei-Sheng Lai, Jia-Bin Huang, Oliver Wang, Eli Shechtman, Ersin Yumer, and Ming-Hsuan Yang. 2018b. Learning Blind Video Temporal Consistency. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_33_1","unstructured":"Gustav Larsson Carl Doersch Aaron Sarna and Kevin Murphy. 2017. PixColor: Pixel Recursive Colorization. arXiv:1705.07208 [cs.CV]"},{"key":"e_1_3_2_1_34_1","volume-title":"Fully Automatic Video Colorization With Self-Regularization and Diversity. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Lei Chenyang","year":"2019","unstructured":"Chenyang Lei and Qifeng Chen. 2019. Fully Automatic Video Colorization With Self-Regularization and Diversity. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186562.1015780"},{"key":"e_1_3_2_1_36_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. arXiv:2201.12086 [cs.CV]","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. arXiv:2201.12086 [cs.CV]"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681356"},{"key":"e_1_3_2_1_38_1","unstructured":"Hanyuan Liu Jinbo Xing Minshan Xie Chengze Li and Tien-Tsin Wong. 2023. Improved Diffusion-based Image Colorization via Piggybacked Models. arXiv:2304.11105 [cs.CV]"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_6"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Xiaopei Liu Liang Wan Yingge Qu Tien-Tsin Wong Stephen Lin Chi-Sing Leung and Pheng-Ann Heng. 2008. Intrinsic colorization. In ACM SIGGRAPH Asia 2008 papers. 1-9.","DOI":"10.1145\/1457515.1409105"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687621"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506422"},{"key":"e_1_3_2_1_43_1","volume-title":"Yu Qiao, and Chao Dong.","author":"Liu Yihao","year":"2021","unstructured":"Yihao Liu, Hengyuan Zhao, Kelvin C. K. Chan, Xintao Wang, Chen Change Loy, Yu Qiao, and Chao Dong. 2021b. Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning. arXiv:2110.04562 [cs.CV]"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. doi:10.48550\/ARXIV.1711.05101","DOI":"10.48550\/ARXIV.1711.05101"},{"key":"e_1_3_2_1_45_1","unstructured":"Cheng Lu Yuhao Zhou Fan Bao Jianfei Chen Chongxuan Li and Jun Zhu. 2023. DPM-Solver: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv:2211.01095 [cs.LG]"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Chong Mou Xintao Wang Liangbin Xie Yanze Wu Jian Zhang Zhongang Qi Ying Shan and Xiaohu Qie. 2023. T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models. arXiv:2302.08453 [cs.CV]","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_47_1","volume-title":"Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation. In European Conference on Computer Vision (ECCV).","author":"Pan X","year":"2020","unstructured":"X Pan, X Zhan, B Dai, D Lin, CC Loy, and P Luo. 2020. Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"F. Perazzi J. Pont-Tuset B. McWilliams L. Van Gool M. Gross and A. Sorkine-Hornung. 2016. A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation. In Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_1_49_1","unstructured":"Zhaofan Qiu Ting Yao and Tao Mei. 2017. Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks. In ICCV."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142017"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13132511"},{"key":"e_1_3_2_1_55_1","unstructured":"Uriel Singer Adam Polyak Thomas Hayes Xi Yin Jie An Songyang Zhang Qiyuan Hu Harry Yang Oron Ashual Oran Gafni Devi Parikh Sonal Gupta and Yaniv Taigman. 2022. Make-A-Video: Text-to-Video Generation without Text-Video Data. arXiv:2209.14792 [cs.CV]"},{"key":"e_1_3_2_1_56_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_57_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020a. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_58_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency Models. arXiv:2303.01469 [cs.LG]"},{"key":"e_1_3_2_1_59_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020b. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00799"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1109\/CVPR.2005.215","volume-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)","volume":"1","author":"Tai Yu-Wing","year":"2005","unstructured":"Yu-Wing Tai, Jiaya Jia, and Chi-Keung Tang. 2005. Local color transfer via probabilistic segmentation by expectation-maximization. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), , Vol. 1. IEEE, 747-754."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. doi:10.48550\/ARXIV.1706.03762","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093389"},{"key":"e_1_3_2_1_64_1","volume-title":"Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers.","author":"von Platen Patrick","year":"2022","unstructured":"Patrick von Platen, Suraj Patil, Anton Lozhkov, Pedro Cuenca, Nathan Lambert, Kashif Rasul, Mishig Davaadorj, and Thomas Wolf. 2022. Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"e_1_3_2_1_66_1","volume-title":"PalGAN: Image Colorization with Palette Generative Adversarial Networks. In European Conference on Computer Vision (ECCV).","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 (ECCV)."},{"key":"e_1_3_2_1_67_1","volume-title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model. The Eleventh International Conference on Learning Representations","author":"Wang Yinhuai","year":"2023","unstructured":"Yinhuai Wang, Jiwen Yu, and Jian Zhang. 2023. Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model. The Eleventh International Conference on Learning Representations (2023)."},{"key":"e_1_3_2_1_68_1","volume-title":"European Conference on Computer Vision (ECCV).","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 (ECCV)."},{"key":"e_1_3_2_1_69_1","volume-title":"Yuchao Gu, Wynne Hsu, Ying Shan, Xiaohu Qie, and Mike Zheng Shou.","author":"Wu Jay Zhangjie","year":"2022","unstructured":"Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei, Yuchao Gu, Wynne Hsu, Ying Shan, Xiaohu Qie, and Mike Zheng Shou. 2022. Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation. arXiv preprint arXiv:2212.11565 (2022)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01411"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70095"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"e_1_3_2_1_73_1","volume-title":"European Conference on Computer Vision. Springer, 399-417","author":"Xing Jinbo","year":"2024","unstructured":"Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, and Tien-Tsin Wong. 2024. Dynamicrafter: Animating open-domain images with video diffusion priors. In European Conference on Computer Vision. Springer, 399-417."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00938"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"Shuai Yang Yifan Zhou Ziwei Liu and Chen Change Loy. 2023. Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation. arXiv:2306.07954 [cs.CV]","DOI":"10.1145\/3610548.3618160"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","unstructured":"Yixin Yang Jiangxin Dong Jinhui Tang and Jinshan Pan. 2024. ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization. arXiv:2404.06251 [cs.CV] https:\/\/arxiv.org\/abs\/2404.06251","DOI":"10.1007\/978-3-031-73235-5_19"},{"key":"e_1_3_2_1_77_1","unstructured":"Yixin Yang Zhongzheng Peng Xiaoyu Du Zhulin Tao Jinhui Tang and Jinshan Pan. 2022. BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization. arXiv:2212.02268 [cs.CV]"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.864231"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00824"},{"key":"e_1_3_2_1_80_1","volume-title":"Adding Conditional Control to Text-to-Image Diffusion Models. arXiv preprint arXiv:2302.05543","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arXiv preprint arXiv:2302.05543 (2023)."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073710"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3298537"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154600"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222579"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:14Z","timestamp":1765309514000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":86,"alternative-id":["10.1145\/3746027.3755761","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755761","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"}}]}}