{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T20:55:27Z","timestamp":1758056127360,"version":"3.44.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"242 project","award":["2023A078","2023A078","2023A078","2023A078","2023A078"],"award-info":[{"award-number":["2023A078","2023A078","2023A078","2023A078","2023A078"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03956-z","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T03:49:15Z","timestamp":1747885755000},"page":"9427-9440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Latent inversion for consistent identity preservation in character animation"],"prefix":"10.1007","volume":"41","author":[{"given":"Haochen","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"issue":"4","key":"3956_CR1","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.vrih.2023.06.010","volume":"6","author":"P Chuanyu","year":"2024","unstructured":"Chuanyu, P., Guowei, Y., Taijiang, M., Yu-Kun, L.: Generating animatable 3d cartoon faces from single portraits. Virt. Reality Intell. Hardw. 6(4), 292\u2013307 (2024)","journal-title":"Virt. Reality Intell. Hardw."},{"issue":"1","key":"3956_CR2","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.vrih.2023.08.006","volume":"6","author":"L Niu","year":"2024","unstructured":"Niu, L., Xie, W., Wang, D., Cao, Z., Liu, X.: Audio2ab: audio-driven collaborative generation of virtual character animation. Virt. Reality Intell. Hardw. 6(1), 56\u201370 (2024)","journal-title":"Virt. Reality Intell. Hardw."},{"issue":"3","key":"3956_CR3","doi-asserted-by":"publisher","first-page":"2248","DOI":"10.1002\/cav.2248","volume":"35","author":"W Zhao","year":"2024","unstructured":"Zhao, W., Zhu, J., Huang, J., Li, P., Sheng, B.: Gan-based multi-decomposition photo cartoonization. Comput. Animat. Virt. Worlds 35(3), 2248 (2024)","journal-title":"Comput. Animat. Virt. Worlds"},{"key":"3956_CR4","doi-asserted-by":"crossref","unstructured":"Choi, S., Park, S., Lee, M., Choo, J.: Viton-hd: high-resolution virtual try-on via misalignment-aware normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14131\u201314140 (2021)","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"3956_CR5","doi-asserted-by":"crossref","unstructured":"Cui, A., McKee, D., Lazebnik, S.: Dressing in order: recurrent person image generation for pose transfer, virtual try-on and outfit editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14638\u201314647 (2021)","DOI":"10.1109\/ICCV48922.2021.01437"},{"issue":"3","key":"3956_CR6","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1002\/cav.2278","volume":"35","author":"L Wang","year":"2024","unstructured":"Wang, L., Wu, Y., Yang, Y.-L., Liu, C., Jin, X.: Identity-consistent transfer learning of portraits for digital apparel sample display. Comput. Animat. Virt. Worlds 35(3), 2278 (2024)","journal-title":"Comput. Animat. Virt. Worlds"},{"key":"3956_CR7","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3497\u20133506 (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"3956_CR8","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214\u2013223 (2017). PMLR"},{"key":"3956_CR9","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Adv. Neural Inform. Process. Syst. 27 (2014)"},{"key":"3956_CR10","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"3956_CR11","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuiliere, S., Sebe, N.: Deformable gans for pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3408\u20133416 (2018)","DOI":"10.1109\/CVPR.2018.00359"},{"issue":"4","key":"3956_CR12","doi-asserted-by":"publisher","first-page":"1156","DOI":"10.1109\/TPAMI.2019.2947427","volume":"43","author":"A Siarohin","year":"2019","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Sangineto, E., Sebe, N.: Appearance and pose-conditioned human image generation using deformable GANs. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1156\u20131171 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3956_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Piao, Z., Min, J., Luo, W., Ma, L., Gao, S.: 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 (2019)","DOI":"10.1109\/ICCV.2019.00600"},{"key":"3956_CR14","doi-asserted-by":"publisher","first-page":"2457","DOI":"10.1109\/TMM.2020.3011290","volume":"23","author":"D Wei","year":"2020","unstructured":"Wei, D., Xu, X., Shen, H., Huang, K.: GAC-GAN: a general method for appearance-controllable human video motion transfer. IEEE Trans. Multimedia 23, 2457\u20132470 (2020)","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"3956_CR15","doi-asserted-by":"publisher","first-page":"4682","DOI":"10.1109\/TPAMI.2022.3201904","volume":"45","author":"Y-T Sun","year":"2022","unstructured":"Sun, Y.-T., Fu, Q.-C., Jiang, Y.-R., Liu, Z., Lai, Y.-K., Fu, H., Gao, L.: Human motion transfer with 3d constraints and detail enhancement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4682\u20134693 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3956_CR16","unstructured":"Liu, H., Han, X., Jin, C., Qian, L., Wei, H., Lin, Z., Wang, F., Dong, H., Song, Y., Xu, J., Chen, Q.: Human MotionFormer: Transferring Human Motions with Vision Transformers (2023)"},{"key":"3956_CR17","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3956_CR18","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3956_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"3956_CR20","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.-C., Kemelmacher-Shlizerman, I.: Dreampose: Fashion image-to-video synthesis via stable diffusion. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22623\u201322633 (2023). IEEE","DOI":"10.1109\/ICCV51070.2023.02073"},{"issue":"3","key":"3956_CR21","doi-asserted-by":"publisher","first-page":"2252","DOI":"10.1002\/cav.2252","volume":"35","author":"M Zhang","year":"2024","unstructured":"Zhang, M., Yang, J., Xian, Y., Li, W., Gu, J., Meng, W., Zhang, J., Zhang, X.: AG-SDM: aquascape generation based on stable diffusion model with low-rank adaptation. Comput. Animat. Virt. Worlds 35(3), 2252 (2024)","journal-title":"Comput. Animat. Virt. Worlds"},{"key":"3956_CR22","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, L., Lin, K., Zhai, Y., Lin, C.-C., Yang, Z., Zhang, H., Liu, Z., Wang, L.: Disco: Disentangled control for realistic human dance generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9326\u20139336 (2024)","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"3956_CR23","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, J., Liew, J.H., Yan, H., Liu, J.-W., Zhang, C., Feng, J., Shou, M.Z.: 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 (2024)","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"3956_CR24","doi-asserted-by":"crossref","unstructured":"Hu, L.: Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8153\u20138163 (2024)","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"3956_CR25","doi-asserted-by":"crossref","unstructured":"Luo, Z., Chen, D., Zhang, Y., Huang, Y., Wang, L., Shen, Y., Zhao, D., Zhou, J., Tan, T.: Videofusion: Decomposed diffusion models for high-quality video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10209\u201310218 (2023)","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"3956_CR26","doi-asserted-by":"publisher","first-page":"6821","DOI":"10.1109\/TMM.2022.3214776","volume":"25","author":"J Zhu","year":"2022","unstructured":"Zhu, J., Zhang, Q., Fei, L., Cai, R., Xie, Y., Sheng, B., Yang, X.: FFFN: frame-by-frame feedback fusion network for video super-resolution. IEEE Trans. Multimedia 25, 6821\u20136835 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"3956_CR27","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"3956_CR28","doi-asserted-by":"crossref","unstructured":"Dong, W., Xue, S., Duan, X., Han, S.: Prompt tuning inversion for text-driven image editing using diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7430\u20137440 (2023)","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"3956_CR29","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/TMM.2020.2999181","volume":"23","author":"A Kamel","year":"2020","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Hybrid refinement-correction heatmaps for human pose estimation. IEEE Trans. Multimedia 23, 1330\u20131342 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"3956_CR30","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"3956_CR31","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"3956_CR32","doi-asserted-by":"crossref","unstructured":"Efros, Berg, Mori, Malik: Recognizing action at a distance. In: Proceedings Ninth IEEE International Conference on Computer Vision, pp. 726\u2013733 (2003). IEEE","DOI":"10.1109\/ICCV.2003.1238420"},{"key":"3956_CR33","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5933\u20135942 (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"3956_CR34","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"3956_CR35","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.-Y., Yang, X., Kautz, J.: Mocogan: Decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"3956_CR36","doi-asserted-by":"crossref","unstructured":"Wei, D., Xu, X., Shen, H., Huang, K.: C2F-FWN: coarse-to-fine flow warping network for spatial-temporal consistent motion transfer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, 2852\u20132860 (2021)","DOI":"10.1609\/aaai.v35i4.16391"},{"issue":"9","key":"3956_CR37","first-page":"5114","volume":"44","author":"W Liu","year":"2021","unstructured":"Liu, W., Piao, Z., Tu, Z., Luo, W., Ma, L., Gao, S.: Liquid warping GAN with attention: a unified framework for human image synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5114\u20135132 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3956_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, J., Zhao, H., Zhang, Y.: Filter-deform attention GAN: constructing human motion videos from few images. The Visual Comput., 1\u201316 (2024)","DOI":"10.1007\/s00371-024-03595-w"},{"key":"3956_CR39","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"3956_CR40","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13653\u201313662 (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"3956_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhang, H.: Thin-plate spline motion model for image animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3657\u20133666 (2022)","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"3956_CR42","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3956_CR43","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et al.: Neural discrete representation learning. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"3956_CR44","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: Densepose: Dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"3956_CR45","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"3956_CR46","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"3956_CR47","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., Ge, Y., Wang, X., Lei, S.W., Gu, Y., Shi, Y., Hsu, W., Shan, Y., Qie, X., Shou, M.Z.: Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7623\u20137633 (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"3956_CR48","doi-asserted-by":"crossref","unstructured":"Jafarian, Y., Park, H.S.: Learning high fidelity depths of dressed humans by watching social media dance videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12753\u201312762 (2021)","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"3956_CR49","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"3956_CR50","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3956_CR51","doi-asserted-by":"crossref","unstructured":"Fu, J., Li, S., Jiang, Y., Lin, K.-Y., Qian, C., Loy, C.C., Wu, W., Liu, Z.: Stylegan-human: A data-centric odyssey of human generation. In: European Conference on Computer Vision, pp. 1\u201319 (2022). Springer","DOI":"10.1007\/978-3-031-19787-1_1"},{"key":"3956_CR52","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: Deepfashion2: A versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5337\u20135345 (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"3956_CR53","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., Komatsuzaki, A.: Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"3956_CR54","unstructured":"Pinkney, J., Lambda: Stable Diffusion Image Variations (2022). https:\/\/huggingface.co\/lambdalabs\/sd-image-variations-diffusers"},{"key":"3956_CR55","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local Nash equilibrium. Adv. Neural Inform. Process. Syst. ms 30 (2017)"},{"issue":"4","key":"3956_CR56","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"3956_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3956_CR58","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: Psnr vs. ssim. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369 (2010). IEEE","DOI":"10.1109\/ICPR.2010.579"},{"key":"3956_CR59","doi-asserted-by":"crossref","unstructured":"Balaji, Y., Min, M.R., Bai, B., Chellappa, R., Graf, H.P.: Conditional GAN with discriminative filter generation for text-to-video synthesis. In: IJCAI, vol. 1, 2 (2019)","DOI":"10.24963\/ijcai.2019\/276"},{"key":"3956_CR60","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03956-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03956-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03956-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:36:46Z","timestamp":1757929006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03956-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":60,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3956"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03956-z","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"assertion":[{"value":"22 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}