{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T16:06:39Z","timestamp":1779811599157,"version":"3.53.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":85,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s44443-026-00591-z","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T06:34:18Z","timestamp":1772433258000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RIA-Net:Realistic Image Animation through Semantic-aware Feature Learning Network"],"prefix":"10.1007","volume":"38","author":[{"given":"Asebe Teka","family":"Nega","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gedamu Alemu","family":"Kumie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albert","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5987-148X","authenticated-orcid":false,"given":"Jianwen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"591_CR1","unstructured":"Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International conference on machine learning.\u00a0Pmlr pp 214\u2013223. Accessed 17 Jul 2017\u00a0"},{"key":"591_CR2","doi-asserted-by":"publisher","first-page":"92712","DOI":"10.1109\/ACCESS.2025.3571760","volume":"13","author":"N Asebe Teka","year":"2025","unstructured":"Asebe Teka N, Gedamu Alemu K, Assefa M, Akmel F, Zhou Z, Wu W, Chen J (2025) Amt-net: adversarial motion transfer network with disentangled shape and pose for realistic image animation. IEEE Access 13:92712\u201392729. https:\/\/doi.org\/10.1109\/ACCESS.2025.3571760","journal-title":"IEEE Access"},{"key":"591_CR3","unstructured":"Balaji Y, Nah S, Huang X, Vahdat A, Song J, Zhang Q, Kreis K, Aittala M, Aila T, Laine S, Catanzaro B (2022) ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324"},{"key":"591_CR4","doi-asserted-by":"crossref","unstructured":"Bao W, Lai WS, Ma C, Zhang X, Gao Z, Yang MH (2019) Depth-aware video frame interpolation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 3703\u20133712","DOI":"10.1109\/CVPR.2019.00382"},{"key":"591_CR5","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision. Springer International Publishing.\u00a0Cham pp 213\u2013229. Accessed 23 Aug 2020","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"591_CR6","doi-asserted-by":"crossref","unstructured":"Chan C, Ginosar S, Zhou T, Efros AA (2019) Everybody dance now. In Proceedings of the IEEE\/CVF international conference on computer vision. pp 5933\u20135942","DOI":"10.1109\/ICCV.2019.00603"},{"issue":"6","key":"591_CR7","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/s00530-024-01499-2","volume":"30","author":"X Chen","year":"2024","unstructured":"Chen X, Lei W, Zhang W, Meng H, Guo H (2024) Model-based portrait video compression with spatial constraint and adaptive pose processing. Multimedia Syst 30(6):311","journal-title":"Multimedia Syst"},{"key":"591_CR8","unstructured":"Devlin J (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint.\u00a0arXiv:1810.04805"},{"key":"591_CR9","unstructured":"Di Chang YS, Gao Q, Fu J, Xu H, Song G, Yan Q, Yang X, Soleymani M (2023) Magicdance: Realistic human dance video generation with motions & facial expressions transfer. arXiv preprint arXiv:2311.12052. 2(3):4"},{"key":"591_CR10","unstructured":"Dosovitskiy A (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint.\u00a0arXiv:2010.11929"},{"key":"591_CR11","unstructured":"Gao Q, Wang B, Liu L, Chen B (2021) Unsupervised co-part segmentation through assembly. In: International Conference on Machine Learning. PMLR\u00a0pp 3576\u20133586. Accessed 1 Jul 2021"},{"key":"591_CR12","unstructured":"Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S (2014) Courville A, Bengio Y. Generative adversarial nets. Advances in neural information processing systems. p 27"},{"key":"591_CR13","unstructured":"Guo Y, Yang C, Rao A, Liang Z, Wang Y, Qiao Y, Agrawala M, Lin D, Dai B (2023) Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725"},{"key":"591_CR14","doi-asserted-by":"crossref","unstructured":"Hu L (2024) Animate anyone: Consistent and controllable image-to-video synthesis for character animation. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 8153\u20138163","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"591_CR15","unstructured":"Huang L, Chen D, Liu Y, Shen Y, Zhao D, Zhou J (2023) Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778"},{"key":"591_CR16","unstructured":"Jang Y, Kim G, Song Y (2018) Video prediction with appearance and motion conditions. In: International conference on machine learning PMLR. pp 2225\u20132234. Accessed\u00a02018 3 Jul 2018"},{"key":"591_CR17","doi-asserted-by":"crossref","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision.\u00a0Springer International Publishing. Springer. Cham pp 694\u2013711. Accessed 17 Sep 2016","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"591_CR18","doi-asserted-by":"crossref","unstructured":"Karras J, Holynski A, Wang TC (2023) Kemelmacher-Shlizerman I. Dreampose: Fashion video synthesis with stable diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision 2023. pp 22680\u201322690","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"591_CR19","doi-asserted-by":"crossref","unstructured":"Li Y, Huang C, Loy CC (2019) Dense intrinsic appearance flow for human pose transfer. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 3693\u20133702","DOI":"10.1109\/CVPR.2019.00381"},{"key":"591_CR20","doi-asserted-by":"crossref","unstructured":"Li R, Yang S, Ross DA, Kanazawa A (2021) Ai choreographer: Music conditioned 3d dance generation with aist++. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 13401\u201313412","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"591_CR21","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang S, Wang Z, Yang S, Yang W, Xia ST, Zhou E (2021) Tokenpose: Learning keypoint tokens for human pose estimation. In: Proceedings of the IEEE\/CVF International conference on computer vision. pp 11313\u201311322","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"591_CR22","doi-asserted-by":"crossref","unstructured":"Liu W, Piao Z, Min J, Luo W, Ma L, Gao S (2019) Liquid warping gan: A unified framework for human motion imitation, appearance transfer and novel view synthesis. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 5904\u20135913","DOI":"10.1109\/ICCV.2019.00600"},{"key":"591_CR23","unstructured":"Ma Y, Zhang S, Wang J, Wang X, Zhang Y, Deng Z (2023) Dreamtalk: When emotional talking head generation meets diffusion probabilistic models. arXiv preprint arXiv:2312.09767"},{"key":"591_CR24","doi-asserted-by":"crossref","unstructured":"Ma Y, He Y, Cun X, Wang X, Chen S, Li X, Chen Q (2024) Follow your pose: Pose-guided text-to-video generation using pose-free videos. In: Proceedings of the AAAI Conference on Artificial Intelligence. 38(5):4117\u20134125. Accessed 24 Mar 2024","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"591_CR25","doi-asserted-by":"crossref","unstructured":"Ma H, Zhang T, Sun S, Yan X, Han K, Xie X (2024) Cvthead: One-shot controllable head avatar with vertex-feature transformer. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp 6131\u20136141","DOI":"10.1109\/WACV57701.2024.00602"},{"key":"591_CR26","unstructured":"Mathieu M, Couprie C, LeCun Y (2015) Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440. arXiv preprint arXiv:1511.05440"},{"issue":"6","key":"591_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024","volume":"36","author":"AH Meftah","year":"2024","unstructured":"Meftah AH, Alotaibi YA, Ahmed Selouani S (2024) Scalability and diversity of starganv2-vc in arabic emotional voice conversion: overcoming data limitations and enhancing performance. J King Saud Univ Comput Inf Sci 36(6):102091. https:\/\/doi.org\/10.1016\/j.jksuci.2024","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"591_CR28","doi-asserted-by":"crossref","unstructured":"Nagrani A, Chung JS, Zisserman A (2017) Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612","DOI":"10.21437\/Interspeech.2017-950"},{"key":"591_CR29","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision.\u00a0Springer International Publishing.\u00a0Cham pp 483\u2013499. Accessed 17 Sept 2016","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"591_CR30","unstructured":"Radford A. (2018) Improving language understanding by generative pre-training (2018)"},{"key":"591_CR31","unstructured":"Ramesh A, Dhariwal P, Nichol A, Chu C, Chen M (2022) Hierarchical textconditional image generation with clip latents.\u00a01(2):3 arXiv preprint arXiv:2204.06125"},{"key":"591_CR32","doi-asserted-by":"crossref","unstructured":"Reda F, Kontkanen J, Tabellion E, Sun D, Pantofaru C, Curless B (2022) Film: Frame interpolation for large motion. In: European Conference on Computer Vision.\u00a0Springer Nature Switzerland. Cham pp 250\u2013266. Accessed 23 Oct 2022","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"591_CR33","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"591_CR34","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia C, Chan W, Saxena S, Li L, Whang J, Denton EL, Ghasemipour K, Gontijo Lopes R, Karagol Ayan B, Salimans T et al (2022) Photorealistic textto-image diffusion models with deep language understanding. Adv Neural Inf Process Syst 35:36479\u201336494","journal-title":"Adv Neural Inf Process Syst"},{"key":"591_CR35","unstructured":"Siarohin A, Lathuili`ere S, Tulyakov S, Ricci E, Sebe N (2019) First order motion model for image animation. Advances in neural information processing systems 32"},{"key":"591_CR36","doi-asserted-by":"crossref","unstructured":"Siarohin A, Lathuili\u00e8re S, Tulyakov S, Ricci E, Sebe N (2019) Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 2377\u20132386","DOI":"10.1109\/CVPR.2019.00248"},{"key":"591_CR37","doi-asserted-by":"crossref","unstructured":"Siarohin A, Woodford OJ, Ren J, Chai M, Tulyakov S (2021) Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 13653\u201313662","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"591_CR38","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"591_CR39","doi-asserted-by":"publisher","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 5693\u20135703. https:\/\/doi.org\/10.1109\/CVPR.2019.00584","DOI":"10.1109\/CVPR.2019.00584"},{"key":"591_CR40","unstructured":"Vaswani A (2017) Attention is all you need. Advances in Neural Information Processing Systems"},{"key":"591_CR41","doi-asserted-by":"crossref","unstructured":"Wan Z, Zhang J, Chen D, Liao J (2021) High-fidelity pluralistic image completion with transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 4692\u20134701","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"591_CR42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449075","author":"Y Wang","year":"2024","unstructured":"Wang Y, Yang D, Bremond F, Dantcheva A (2024d) Lia: latent image animator. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3449075","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"591_CR43","unstructured":"Wang TC, Liu MY, Zhu JY, Liu G, Tao A, Kautz J, Catanzaro B (2018) Video-to-video synthesis. arXiv preprint arXiv:1808.06601"},{"key":"591_CR44","doi-asserted-by":"crossref","unstructured":"Wang TC, Mallya A, Liu MY. (2021) One-shot free-view neural talking-head synthesis for video conferencing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 10039\u201310049","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"591_CR45","doi-asserted-by":"crossref","unstructured":"Wang R, Mao Q, Jia C, Wang R, Ma S (2023) Extreme generative human-oriented video coding via motion representation compression. In2023 IEEE International Symposium on Circuits and Systems (ISCAS) IEEE. pp 1\u20135. Accessed 21 May 2023","DOI":"10.1109\/ISCAS46773.2023.10181664"},{"key":"591_CR46","doi-asserted-by":"crossref","unstructured":"Wang T, Li L, Lin K, Zhai Y, Lin CC, Yang Z, Zhang H, Liu Z, Wang L (2024) Disco: Disentangled control for realistic human dance generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 9326\u20139336","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"591_CR47","first-page":"7594","volume":"36","author":"X Wang","year":"2023","unstructured":"Wang X, Yuan H, Zhang S, Chen D, Wang J, Zhang Y, Shen Y, Zhao D, Zhou J (2023) Videocomposer: compositional video synthesis with motion controllability. Adv Neural Inf Process Syst 36:7594\u2013611","journal-title":"Adv Neural Inf Process Syst"},{"key":"591_CR48","doi-asserted-by":"crossref","unstructured":"Wang X, Zhang S, Yuan H, Qing Z, Gong B, Zhang Y, Shen Y, Gao C, Sang N (2024) A recipe for scaling up text-to-video generation with text-free videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 6572\u20136582","DOI":"10.1109\/CVPR52733.2024.00628"},{"key":"591_CR49","doi-asserted-by":"crossref","unstructured":"Wang T, Li L, Lin K, Zhai Y, Lin CC, Yang Z, Zhang H, Liu Z, Wang L (2024) Disco: Disentangled control for realistic human dance generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 9326\u20139336","DOI":"10.1109\/CVPR52733.2024.00891"},{"issue":"3","key":"591_CR50","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1007\/s11263-024-02231-3","volume":"133","author":"Y Wang","year":"2025","unstructured":"Wang Y, Ma X, Chen X, Chen C, Dantcheva A, Dai B, Qiao Y (2025) Leo: generative latent image animator for human video synthesis. Int J Comput Vis 133(3):1277\u201389","journal-title":"Int J Comput Vis"},{"key":"591_CR51","doi-asserted-by":"publisher","first-page":"16530","DOI":"10.1109\/ACCESS.2022.3149380","volume":"10","author":"U Watchareeruetai","year":"2022","unstructured":"Watchareeruetai U, Sommana B, Jain S, Noinongyao P, Ganguly A, Samacoits A, Earp SW, Sritrakool N (2022) Lotr: face landmark localization using localization transformer. IEEE Access 10:16530\u201316543","journal-title":"IEEE Access"},{"key":"591_CR52","doi-asserted-by":"crossref","unstructured":"Weng CY, Curless B, Kemelmacher-Shlizerman I (2019) Photo wake-up: 3d character animation from a single photo. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 5908\u20135917","DOI":"10.1109\/CVPR.2019.00606"},{"key":"591_CR53","doi-asserted-by":"crossref","unstructured":"Xing J, Xia M, Zhang Y, Chen H, Yu W, Liu H, Liu G, Wang X, Shan Y, Wong TT (2025) Dynamicrafter: Animating open-domain images with video diffusion priors. In: European Conference on Computer Vision, pp. 399\u2013417 (2025). Springer","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"591_CR54","doi-asserted-by":"crossref","unstructured":"Xu Z, Zhang J, Liew JH, Yan H, Liu JW, Zhang C, Feng J, Shou MZ (2024) Magicanimate: Temporally consistent human image animation using diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 1481\u20131490","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"591_CR55","unstructured":"Xu Z, Wei K, Yang X, Deng C (2024) Do you guys want to dance: zero-shot compositional human dance generation with multiple persons. arXiv preprint arXiv:2401.13363"},{"key":"591_CR56","unstructured":"Yan W, Zhang Y, Abbeel P, Srinivas A (2021) Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157"},{"key":"591_CR57","doi-asserted-by":"crossref","unstructured":"Yang C, Wang Z, Zhu X, Huang C, Shi J, Lin,D (2018) Pose guided human video generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 201\u2013216","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"591_CR58","doi-asserted-by":"crossref","unstructured":"Yang S, Quan Z, Nie M, Yang W (2021) Transpose: Keypoint localization via transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 11802\u201311812","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"591_CR59","doi-asserted-by":"crossref","unstructured":"Yu WY, Po LM, Cheung RC, Zhao Y, Xue Y, Li K (2023) Bidirectionally deformable motion modulation for video-based human pose transfer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 7502\u20137512","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"591_CR60","unstructured":"Zablotskaia P, Siarohin A, Zhao B, Sigal L (2019) Dwnet: Dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139. Accessed 21 Oct 2019"},{"key":"591_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128168","volume":"598","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Su R, Yu J, Li R (2024) 3d facial modeling, animation, and rendering for digital humans: a survey. Neurocomputing 598:128168","journal-title":"Neurocomputing"},{"key":"591_CR62","doi-asserted-by":"crossref","unstructured":"Zhang P, Yang L, Lai JH, Xie X (2022) Exploring dual-task correlation for pose guided person image generation. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition. pp 7713\u20137722","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"591_CR63","doi-asserted-by":"crossref","unstructured":"Zhang L, Rao A, Agrawala M (2023) Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp 3836\u20133847","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"591_CR64","doi-asserted-by":"crossref","unstructured":"Zhao J, Zhang H (2022) Thin-plate spline motion model for image animation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 3657\u20133666","DOI":"10.1109\/CVPR52688.2022.00364"},{"issue":"1","key":"591_CR65","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/JBHI.2021.3074852","volume":"26","author":"Y Zhou","year":"2021","unstructured":"Zhou Y, Yu K, Wang M, Ma Y, Peng Y, Chen Z, Zhu W, Shi F, Chen X (2021) Speckle noise reduction for oct images based on image style transfer and conditional gan. IEEE J Biomed Health Inform 26(1):139\u2013150","journal-title":"IEEE J Biomed Health Inform"},{"key":"591_CR66","doi-asserted-by":"crossref","unstructured":"Zhou Y, Wang Z, Fang C, Bui T, Berg T (2019) Dance dance generation: Motion transfer for internet videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops. pp 0-0","DOI":"10.1109\/ICCVW.2019.00153"},{"key":"591_CR67","doi-asserted-by":"crossref","unstructured":"Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision. pp 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"},{"key":"591_CR68","unstructured":"Zhu B, Wang F, Lu T, Liu P, Su J, Liu J, Zhang Y, Wu Z, Qi GJ, Jiang YG (2024) Zero-shot high-fidelity and pose-controllable character animation. arXiv preprint arXiv:2404.13680"},{"key":"591_CR69","doi-asserted-by":"crossref","unstructured":"Zhu S, Chen JL, Dai Z, Dong Z, Xu Y, Cao X, Yao Y, Zhu H, Zhu S (2024) Champ: Controllable and consistent human image animation with 3d parametric guidance. In: European Conference on Computer Vision. Springer Nature Switzerland. Cham pp. 145\u2013162. Accessed 29 Sept 2024","DOI":"10.1007\/978-3-031-73001-6_9"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00591-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00591-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00591-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:45:38Z","timestamp":1779810338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00591-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":69,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["591"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00591-z","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"assertion":[{"value":"7 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"185"}}