{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T01:04:22Z","timestamp":1789607062711,"version":"build-2803163510"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014736","name":"Lingnan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014736","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134533","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:25:04Z","timestamp":1784388304000},"page":"134533","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CartoonCodec: Generative talking face video coding with cartoon-style customization"],"prefix":"10.1016","volume":"701","author":[{"given":"Xiaona","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihua","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-7261","authenticated-orcid":false,"given":"Sam","family":"Kwong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134533_bib0005","doi-asserted-by":"crossref","first-page":"6341","DOI":"10.1109\/TMM.2022.3207580","article-title":"A super-resolution flexible video coding solution for improving live streaming quality","volume":"25","author":"Li","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0010","doi-asserted-by":"crossref","first-page":"2300","DOI":"10.1109\/TMM.2021.3079288","article-title":"Catching the moment with LoL+ in twitch-like low-latency live streaming platforms","volume":"24","author":"Bentaleb","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0015","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/JSAC.2022.3221968","article-title":"Wireless semantic communications for video conferencing","volume":"41","author":"Jiang","year":"2022","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.neucom.2026.134533_bib0020","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134533_bib0025","series-title":"2022 Data Compression Conference (DCC)","first-page":"13","article-title":"Beyond keypoint coding: temporal evolution inference with compact feature representation for talking face video compression","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134533_bib0030","doi-asserted-by":"crossref","first-page":"7009","DOI":"10.1109\/TCSVT.2023.3271130","article-title":"Compact temporal trajectory representation for talking face video compression","volume":"33","author":"Chen","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134533_bib0035","series-title":"Encoding and decoding for face videos","author":"KWONG","year":"2024"},{"key":"10.1016\/j.neucom.2026.134533_bib0040","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/TIP.2025.3648562","article-title":"CoFaCo: controllable generative talking face video coding","volume":"35","author":"Li","year":"2026","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134533_bib0045","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"1202","article-title":"A virtual character generation and animation system for e-commerce live streaming","author":"Hu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0050","series-title":"Proceeding of the 2024 5th International Conference on Computer Science and Management Technology","first-page":"741","article-title":"Cartoonish vs. realistic: the marketing effect of form realism of AI avatar in live streaming e-commerce","author":"Yu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134533_bib0055","doi-asserted-by":"crossref","first-page":"2910","DOI":"10.1109\/TIP.2025.3563762","article-title":"Interactive face video coding: a generative compression framework","volume":"34","author":"Chen","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.134533_bib0060","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1109\/TCSS.2022.3231987","article-title":"Zooming into video conferencing privacy","volume":"11","author":"Kagan","year":"2023","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.neucom.2026.134533_bib0065","series-title":"International Conference on Human-Computer Interaction","first-page":"44","article-title":"Effectiveness of digital avatars in student engagement and learning","author":"Hoang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134533_bib0070","doi-asserted-by":"crossref","first-page":"3313","DOI":"10.1080\/10447318.2023.2189818","article-title":"Being there, and being together: avatar appearance and peer interaction in VR classrooms for video-based learning","volume":"40","author":"Yuan","year":"2024","journal-title":"Int. J. Hum.\u2013comput. Interact."},{"key":"10.1016\/j.neucom.2026.134533_bib0075","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","article-title":"Overview of the high efficiency video coding (HEVC) standard","volume":"22","author":"Sullivan","year":"2012","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134533_bib0080","doi-asserted-by":"crossref","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","article-title":"Overview of the versatile video coding (VVC) standard and its applications","volume":"31","author":"Bross","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134533_bib0085","series-title":"Proceedings of the IRE","first-page":"1098","article-title":"A method for the construction of minimum-redundancy codes","volume":"vol. 40","author":"Huffman","year":"1952"},{"key":"10.1016\/j.neucom.2026.134533_bib0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2426","article-title":"Diffusionclip: text-guided diffusion models for robust image manipulation","author":"Kim","year":"2022"},{"key":"10.1016\/j.neucom.2026.134533_bib0095","author":"Lyu"},{"key":"10.1016\/j.neucom.2026.134533_bib0100","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21492","article-title":"Swiftedit: lightning fast text-guided image editing via one-step diffusion","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.neucom.2026.134533_bib0105","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3528223.3530164","article-title":"Stylegan-Nada: clip-guided domain adaptation of image generators","volume":"41","author":"Gal","year":"2022","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10.1016\/j.neucom.2026.134533_bib0110","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196391","article-title":"The ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American english","volume":"13","author":"Livingstone","year":"2018","journal-title":"PLoS One"},{"key":"10.1016\/j.neucom.2026.134533_bib0115","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4210","article-title":"Ultra-low bitrate video conferencing using deep image animation","author":"Konuko","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0120","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10039","article-title":"One-shot free-view neural talking-head synthesis for video conferencing","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0125","author":"Li"},{"key":"10.1016\/j.neucom.2026.134533_bib0130","series-title":"Lucy edit: open-weight text-guided video editing","author":"Team","year":"2025"},{"key":"10.1016\/j.neucom.2026.134533_bib0135","doi-asserted-by":"crossref","first-page":"9936","DOI":"10.1109\/TMM.2024.3417694","article-title":"Align and retrieve: composition and decomposition learning in image retrieval with text feedback","volume":"26","author":"Xu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0140","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1109\/LSP.2024.3516699","article-title":"Multi-modal prior-guided diffusion model for blind image super-resolution","volume":"32","author":"Huang","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.neucom.2026.134533_bib0145","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"23141","article-title":"The power of context: how multimodality improves image super-resolution","author":"Mei","year":"2025"},{"key":"10.1016\/j.neucom.2026.134533_bib0150","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"4015","article-title":"Lamra: large multimodal model as your advanced retrieval assistant","author":"Liu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134533_bib0155","doi-asserted-by":"crossref","first-page":"5831","DOI":"10.1109\/TMM.2025.3543098","article-title":"Learning the scale in reference picture resampling for versatile video coding","volume":"27","author":"Lu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0160","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TBC.2016.2623241","article-title":"Fast intra prediction based on content property analysis for low complexity HEVC-based screen content coding","volume":"63","author":"Lei","year":"2016","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.neucom.2026.134533_bib0165","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1109\/TBC.2017.2711142","article-title":"Binary and multi-class learning based low complexity optimization for HEVC encoding","volume":"63","author":"Zhu","year":"2017","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.neucom.2026.134533_bib0170","doi-asserted-by":"crossref","first-page":"5632","DOI":"10.1109\/TMM.2025.3543061","article-title":"Bi-directional deep contextual video compression","volume":"27","author":"Sheng","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0175","doi-asserted-by":"crossref","first-page":"4579","DOI":"10.1109\/TPAMI.2024.3356548","article-title":"Vnvc: a versatile neural video coding framework for efficient human-machine vision","volume":"46","author":"Sheng","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134533_bib0180","doi-asserted-by":"crossref","first-page":"6460","DOI":"10.1109\/TCSVT.2024.3360248","article-title":"Spatial decomposition and temporal fusion based inter prediction for learned video compression","volume":"34","author":"Sheng","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134533_bib0185","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/TMM.2024.3521715","article-title":"HNR-ISC: hybrid neural representation for image set compression","volume":"27","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0190","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1109\/76.285624","article-title":"Optimization and efficiency of an object-oriented analysis-synthesis coder","volume":"4","author":"Hotter","year":"1994","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134533_bib0195","series-title":"2022 Data Compression Conference (DCC)","first-page":"461","article-title":"Towards ultra low bit-rate digital human character communication via compact 3D face descriptors","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134533_bib0200","first-page":"157","article-title":"A morphable model for the synthesis of 3D faces","volume":"2","author":"Blanz","year":"2023","journal-title":"Semin. Graph. Pap.: Push. Boundaries"},{"key":"10.1016\/j.neucom.2026.134533_bib0205","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134533_bib0210","author":"Kingma"},{"key":"10.1016\/j.neucom.2026.134533_bib0215","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134533_bib0220","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TETCI.2020.2991774","article-title":"Loss functions of generative adversarial networks (GANs): opportunities and challenges","volume":"4","author":"Pan","year":"2020","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.neucom.2026.134533_bib0225","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/TMM.2019.2924591","article-title":"Generative adversarial network-based intra prediction for video coding","volume":"22","author":"Zhu","year":"2019","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0230","author":"Back"},{"key":"10.1016\/j.neucom.2026.134533_bib0235","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2085","article-title":"Styleclip: text-driven manipulation of stylegan imagery","author":"Patashnik","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0240","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12863","article-title":"Stylespace analysis: disentangled controls for stylegan image generation","author":"Wu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0245","series-title":"International Conference on Learning Representations","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0250","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/0020-0190(78)90024-8","article-title":"A compression method for clustered bit-vectors","volume":"7","author":"Teuhola","year":"1978","journal-title":"Inf. Process. Lett."},{"key":"10.1016\/j.neucom.2026.134533_bib0255","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TCOM.1984.1096090","article-title":"Data compression using adaptive coding and partial string matching","volume":"32","author":"Cleary","year":"1984","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.neucom.2026.134533_bib0260","first-page":"1","article-title":"Learning an animatable detailed 3D face model from in-the-wild images","volume":"40","author":"Feng","year":"2021","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10.1016\/j.neucom.2026.134533_bib0265","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","volume":"vol. 14","author":"Johnson","year":"2016"},{"key":"10.1016\/j.neucom.2026.134533_bib0270","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8110","article-title":"Analyzing and improving the image quality of stylegan","author":"Karras","year":"2020"},{"key":"10.1016\/j.neucom.2026.134533_bib0275","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"427","article-title":"Dpe: disentanglement of pose and expression for general video portrait editing","author":"Pang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134533_bib0280","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134533_bib0285","first-page":"2567","article-title":"Image quality assessment: unifying structure and texture similarity","volume":"44","author":"Ding","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134533_bib0290","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134533_bib0295","doi-asserted-by":"crossref","first-page":"4375","DOI":"10.1109\/TMM.2023.3322326","article-title":"Text-guided eyeglasses manipulation with spatial constraints","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134533_bib0300","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"484","article-title":"A lip sync expert is all you need for speech to lip generation in the wild","author":"Prajwal","year":"2020"},{"key":"10.1016\/j.neucom.2026.134533_bib0305","series-title":"Proc. IEEE International Conference on Multimedia Expo Workshops (ICMEW)","first-page":"1","article-title":"VVenc: an open and optimized VVC encoder implementation","author":"Wieckowski","year":"2021"},{"key":"10.1016\/j.neucom.2026.134533_bib0310","series-title":"Proc. IEEE International Conference on Image Processing (ICIP)","first-page":"3124","article-title":"Towards a live software decoder implementation for the upcoming versatile video coding (VVC) codec","author":"Wieckowski","year":"2020"},{"key":"10.1016\/j.neucom.2026.134533_bib0315","author":"Nagrani"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019314?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019314?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:23:43Z","timestamp":1789604623000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226019314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":63,"alternative-id":["S0925231226019314"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134533","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CartoonCodec: Generative talking face video coding with cartoon-style customization","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134533","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134533"}}