{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:49:25Z","timestamp":1773856165389,"version":"3.50.1"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002766","name":"Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","award":["CX20242080"],"award-info":[{"award-number":["CX20242080"]}],"id":[{"id":"10.13039\/501100002766","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136001"],"award-info":[{"award-number":["62136001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.neucom.2025.132199","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T17:02:07Z","timestamp":1764003727000},"page":"132199","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["L-C4: Language-based video colorization for creative and consistent color"],"prefix":"10.1016","volume":"665","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0538-9472","authenticated-orcid":false,"given":"Zheng","family":"Chang","sequence":"first","affiliation":[]},{"given":"Shuchen","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Huan","family":"Ouyang","sequence":"additional","affiliation":[]},{"given":"Lihan","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Si","family":"Li","sequence":"additional","affiliation":[]},{"given":"Boxin","family":"Shi","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2025.132199_bib0005","article-title":"Temporally consistent video colorization with deep feature propagation and self-regularization learning","volume":"10","author":"Liu","year":"2024","journal-title":"CVM"},{"key":"10.1016\/j.neucom.2025.132199_bib0010","author":"Wang"},{"key":"10.1016\/j.neucom.2025.132199_bib0015","series-title":"NeurIPS","article-title":"L-CAD: language-based colorization with any-level descriptions using diffusion priors","author":"Chang","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0020","article-title":"Hierarchical Color Fusion Network (HCFN): enhancing exemplar-based video colorization","volume":"589","author":"Yin","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2025.132199_bib0025","series-title":"CRV","article-title":"Automatic temporally coherent video colorization","author":"Thasarathan","year":"2019"},{"key":"10.1016\/j.neucom.2025.132199_bib0030","series-title":"CVPR","article-title":"Fully automatic video colorization with self-regularization and diversity","author":"Lei","year":"2019"},{"key":"10.1016\/j.neucom.2025.132199_bib0035","series-title":"CVPR","article-title":"Vidtome: video token merging for zero-shot video editing","author":"Li","year":"2024"},{"key":"10.1016\/j.neucom.2025.132199_bib0040","series-title":"ICCV","article-title":"Fatezero: fusing attentions for zero-shot text-based video editing","author":"Qi","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0045","series-title":"CVPR","article-title":"L-coins: language-based colorization with instance awareness","author":"Chang","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0050","series-title":"SIGGRAPH Asia","article-title":"Unicolor: a unified framework for multi-modal colorization with transformer","author":"Huang","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0055","series-title":"ECCV","article-title":"Learning blind video temporal consistency","author":"Lai","year":"2018"},{"key":"10.1016\/j.neucom.2025.132199_bib0060","series-title":"NeurIPS","article-title":"Blind video temporal consistency via deep video prior","author":"Lei","year":"2020"},{"key":"10.1016\/j.neucom.2025.132199_bib0065","series-title":"CVPR","article-title":"Blind video deflickering by neural filtering with a flawed atlas","author":"Lei","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0070","series-title":"CVPR","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0075","series-title":"ECCV","article-title":"Colorful image colorization","author":"Zhang","year":"2016"},{"key":"10.1016\/j.neucom.2025.132199_bib0080","doi-asserted-by":"crossref","first-page":"130713","DOI":"10.1016\/j.neucom.2025.130713","article-title":"Adversarial network for unsupervised infrared image colorization based on full-scale feature fusion and cosine contrastive learning","volume":"649","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2025.132199_bib0085","series-title":"ICCV","article-title":"Deep colorization","author":"Cheng","year":"2015"},{"key":"10.1016\/j.neucom.2025.132199_bib0090","series-title":"ECCV","article-title":"CT2: colorization transformer via color tokens","author":"Weng","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0095","series-title":"CVPR","article-title":"Instance-aware image colorization","author":"Su","year":"2020"},{"key":"10.1016\/j.neucom.2025.132199_bib0100","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2022.3154600","article-title":"VCGAN: video colorization with hybrid generative adversarial network","volume":"25","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2025.132199_bib0105","series-title":"IJCAI","article-title":"Gl-rg: global-local representation granularity for video captioning","author":"Yan","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0110","series-title":"ICLR","article-title":"Re-imagining multimodal instruction tuning: a representation view","author":"Liu","year":"2025"},{"key":"10.1016\/j.neucom.2025.132199_bib0115","series-title":"ICLR","article-title":"Visual agents as fast and slow thinkers","author":"Sun","year":"2025"},{"key":"10.1016\/j.neucom.2025.132199_bib0120","series-title":"NAACL","article-title":"Learning to color from language","author":"Manjunatha","year":"2018"},{"key":"10.1016\/j.neucom.2025.132199_bib0125","series-title":"AAAI","article-title":"Film: visual reasoning with a general conditioning layer","author":"Perez","year":"2018"},{"key":"10.1016\/j.neucom.2025.132199_bib0130","series-title":"CVPR","article-title":"Language-based image editing with recurrent attentive models","author":"Chen","year":"2018"},{"key":"10.1016\/j.neucom.2025.132199_bib0135","series-title":"AAAI","article-title":"L-code: language-based colorization using color-object decoupled conditions","author":"Weng","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0140","series-title":"ECCV","article-title":"L-coder: language-based colorization with color-object decoupling transformer","author":"Chang","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0145","author":"Liang"},{"key":"10.1016\/j.neucom.2025.132199_bib0150","series-title":"ICCV","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0155","series-title":"NeurIPS","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0160","series-title":"ICLR","article-title":"Controlvideo: training-free controllable text-to-video generation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2025.132199_bib0165","series-title":"CVPR","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"10.1016\/j.neucom.2025.132199_bib0170","series-title":"ICML","article-title":"Is space-time attention all you need for video understanding?","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.neucom.2025.132199_bib0175","series-title":"ICCV","article-title":"Structure and content-guided video synthesis with diffusion models","author":"Esser","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0180","author":"He"},{"key":"10.1016\/j.neucom.2025.132199_bib0185","series-title":"Imagen video: high definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"10.1016\/j.neucom.2025.132199_bib0190","series-title":"ACM SIGGRAPH","article-title":"Versatile vision Foundation model for image and video colorization","author":"Bozic","year":"2024"},{"key":"10.1016\/j.neucom.2025.132199_bib0195","series-title":"ACM MM","article-title":"Towards photorealistic video colorization via gated color-guided image diffusion models","author":"Li","year":"2024"},{"key":"10.1016\/j.neucom.2025.132199_bib0200","author":"Jiang"},{"key":"10.1016\/j.neucom.2025.132199_bib0205","series-title":"CVPR","article-title":"Align your latents: high-resolution video synthesis with latent diffusion models","author":"Blattmann","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0210","series-title":"ICML","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2025.132199_bib0215","series-title":"ICLR","article-title":"Internvid: a large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0220","series-title":"CVPR","article-title":"A benchmark dataset and evaluation methodology for video object segmentation","author":"Perazzi","year":"2016"},{"key":"10.1016\/j.neucom.2025.132199_bib0225","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3370920","article-title":"Bistnet: semantic image prior guided bidirectional temporal feature fusion for deep exemplar-based video colorization","volume":"46","author":"Yang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2025.132199_bib0230","series-title":"NIPS","article-title":"Instructblip: towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0235","author":"Achiam"},{"key":"10.1016\/j.neucom.2025.132199_bib0240","series-title":"Human Vision and Electronic Imaging VIII","article-title":"Measuring colorfulness in natural images","author":"Hasler","year":"2003"},{"key":"10.1016\/j.neucom.2025.132199_bib0245","doi-asserted-by":"crossref","DOI":"10.1049\/el:20080522","article-title":"Scope of validity of PSNR in image\/video quality assessment","volume":"44","author":"Huynh-Thu","year":"2008","journal-title":"Electron. Lett."},{"key":"10.1016\/j.neucom.2025.132199_bib0250","first-page":"600","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"TIP"},{"key":"10.1016\/j.neucom.2025.132199_bib0255","series-title":"CVPR","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2025.132199_bib0260","series-title":"ICLR","article-title":"FVD: a new metric for video generation","author":"Unterthiner","year":"2019"},{"key":"10.1016\/j.neucom.2025.132199_bib0265","author":"Song"},{"key":"10.1016\/j.neucom.2025.132199_bib0270","series-title":"ICCV","article-title":"Ddcolor: towards photo-realistic image colorization via dual decoders","author":"Kang","year":"2023"},{"key":"10.1016\/j.neucom.2025.132199_bib0275","series-title":"CVPR","article-title":"Deep exemplar-based video colorization","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neucom.2025.132199_bib0280","doi-asserted-by":"crossref","DOI":"10.1145\/3355089.3356570","article-title":"Deepremaster: temporal source-reference attention networks for comprehensive video enhancement","volume":"38","author":"Iizuka","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2025.132199_bib0285","series-title":"ECCV","article-title":"Colormnet: a memory-based deep spatial-temporal feature propagation network for video colorization","author":"Yang","year":"2024"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231225028711?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231225028711?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T11:08:01Z","timestamp":1773832081000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231225028711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":57,"alternative-id":["S0925231225028711"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2025.132199","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"L-C4: Language-based video colorization for creative and consistent color","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2025.132199","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132199"}}