{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:18:16Z","timestamp":1783315096214,"version":"3.54.6"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02266-1","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:03:10Z","timestamp":1773151390000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Disentangle to edit: instruction-guided latent manipulation for 3D facial video consistency"],"prefix":"10.1007","volume":"32","author":[{"given":"Peixu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxi","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shulei","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"2266_CR1","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). 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)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2266_CR2","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., & Lischinski, D. (2021). StyleCLIP: Text-driven manipulation of StyleGAN imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 2085\u20132094)","DOI":"10.1109\/ICCV48922.2021.00209"},{"issue":"4","key":"2266_CR3","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TPAMI.2020.3034267","volume":"44","author":"Y Shen","year":"2022","unstructured":"Shen, Y., Yang, C., Tang, X., Zhou, B.: InterFaceGAN: Interpreting the disentangled face representation learned by GANs. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 2004\u20132018 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2266_CR4","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125"},{"key":"2266_CR5","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, S. K. S., Lopes, R. G., Ayan, B. K., Salimans, T., Ho, J., Fleet, D. J., & Norouzi, M. (2022). Photorealistic text-to-image diffusion models with deep language understanding. In: Proceedings of the Conference on Neural Information Processing Systems","DOI":"10.52202\/068431-2643"},{"key":"2266_CR6","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021). Zero-shot text-to-image generation. In: International Conference on Machine Learning, (pp. 8821\u20138831)"},{"issue":"5","key":"2266_CR7","doi-asserted-by":"publisher","first-page":"3692","DOI":"10.1109\/TPAMI.2023.3347299","volume":"46","author":"Y Jiang","year":"2024","unstructured":"Jiang, Y., Huang, Z., Wu, T., Pan, X., Loy, C.C., Liu, Z.: Talk-to-edit: Fine-grained 2D and 3D facial editing via dialog. IEEE Trans. Pattern Anal. Mach. Intell. 46(5), 3692\u20133706 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2266_CR8","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., & Efros, A. A. (2023). InstructPix2Pix: Learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 18392\u201318402)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"2266_CR9","doi-asserted-by":"crossref","unstructured":"Chan, E. R., Lin, C. Z., Chan, M. A., Nagano, K., Pan, B., De Mello, S., Gallo, O., Guibas, L. J., Tremblay, J., Khamis, S., Karras, T., & Wetzstein, G. (2022). Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 16102\u201316112)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2266_CR10","doi-asserted-by":"crossref","unstructured":"An, S., Xu, H., Shi, Y., Song, G., Ogras, \u00dc. Y., & Luo, L. (2023). PanoHead: Geometry-aware 3D full-head synthesis in 360\u00b0. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 20950\u201320959)","DOI":"10.1109\/CVPR52729.2023.02007"},{"key":"2266_CR11","doi-asserted-by":"crossref","unstructured":"Bhattarai, A. R., Niessner, M., & Sevastopolsky, A. (2024). TriPlaneNet: An encoder for EG3D inversion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, (pp. 3043\u20133053)","DOI":"10.1109\/WACV57701.2024.00303"},{"key":"2266_CR12","doi-asserted-by":"crossref","unstructured":"Tzaban, R., Mokady, R., Gal, R., Bermano, A., & Cohen-Or, D. (2022). Stitch it in time: GAN-based facial editing of real videos. In: Proceedings of SIGGRAPH Asia, (pp. 29:1\u201329:9)","DOI":"10.1145\/3550469.3555382"},{"key":"2266_CR13","doi-asserted-by":"crossref","unstructured":"Fr \u00fcst \u00fcck, A., Sarafianos, N., Xu, Y., Wonka, P., & Tung, T. (2023). VIVE3D: Viewpoint-independent video editing using 3D-aware GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 4446\u20134455)","DOI":"10.1109\/CVPR52729.2023.00432"},{"key":"2266_CR14","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020). NeRF: Representing scenes as neural radiance fields for view synthesis. In: Proceedings of the European Conference on Computer Vision, (pp. 405\u2013421)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2266_CR15","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollh \u00f6fer, M., & Niessner, M. (2021). Dynamic neural radiance fields for monocular 4D facial avatar reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 8649\u20138658)","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"2266_CR16","doi-asserted-by":"crossref","unstructured":"Athar, S., Xu, Z., Sunkavalli, K., Shechtman, E., & Shu, Z. (2022). RigNeRF: Fully controllable neural 3D portraits. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 20332\u201320341)","DOI":"10.1109\/CVPR52688.2022.01972"},{"key":"2266_CR17","doi-asserted-by":"crossref","unstructured":"Wu, Y., Xu, S., Xiang, J., Wei, F., Chen, Q., Yang, J., & Tong, X. (2023). AniPortraitGAN: Animatable 3D portrait generation from 2D image collections. SIGGRAPH Asia, (pp. 51:1\u201351:9)","DOI":"10.1145\/3610548.3618164"},{"key":"2266_CR18","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yang, X., Wan, Y., & Shen, X. (2022). SemanticStyleGAN: Learning compositional generative priors for controllable image synthesis and editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 11244\u201311254)","DOI":"10.1109\/CVPR52688.2022.01097"},{"key":"2266_CR19","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., Xue, J.-H., & Wu, B. (2021). TediGAN: Text-guided diverse face image generation and manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 2256\u20132265)","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"2266_CR20","doi-asserted-by":"crossref","unstructured":"Xu, Y., Yin, Y., Jiang, L., Wu, Q., Zheng, C., Loy, C. C., Dai, B., & Wu, W. (2022). TransEditor: Transformer-based dual-space GAN for highly controllable facial editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 7673\u20137682)","DOI":"10.1109\/CVPR52688.2022.00753"},{"key":"2266_CR21","doi-asserted-by":"crossref","unstructured":"Sarridis, I., Koutlis, C., Papadopoulos, S., & Diou, C. (2024). FaceX: Understanding face attribute classifiers through summary model explanations. In: Proceedings of the International Conference on Multimedia Retrieval, (pp. 758\u2013766)","DOI":"10.1145\/3652583.3658007"},{"key":"2266_CR22","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2023). Prompt-to-prompt image editing with cross-attention control. In: Proceedings of the International Conference on Learning Representations"},{"key":"2266_CR23","unstructured":"Fu, T.-J., Hu, W., Du, X., Wang, W. Y., Yang, Y., & Gan, Z. (2024). Guiding instruction-based image editing via multimodal large language models. In: Proceedings of the International Conference on Learning Representations"},{"key":"2266_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yu, Y., Ouyang, H., Wang, Q., Cheng, K. L., Wang, W., Liu, Z., Chen, Q., & Shen, Y. (2024). MagicQuill: An intelligent interactive image editing system. arXiv preprint arXiv:2411.09703","DOI":"10.1109\/CVPR52734.2025.01220"},{"key":"2266_CR25","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., & Ye, J. C. (2022). DiffusionCLIP: Text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 2416\u20132425)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"2266_CR26","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Chen, Z., Ren, X., Zhu, W., Xu, Z., Xu, D., Yang, C., & Yan, Y. (2024). 3D-aware face editing via warping-guided latent direction learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 916\u2013926)","DOI":"10.1109\/CVPR52733.2024.00093"},{"key":"2266_CR27","doi-asserted-by":"crossref","unstructured":"Roich, D., Mokady, R., Bermano, A. H., & Cohen-Or, D. (2023). Pivotal tuning for latent-based editing of real images. ACM Transactions on Graphics, 42(1), (pp. 6:1\u20136:13","DOI":"10.1145\/3544777"},{"key":"2266_CR28","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Chan, M. A., Takikawa, T., Iqbal, U., De Mello, S., Chandraker, M., Ramamoorthi, R., & Nagano, K. (2024). What you see is what you GAN: Rendering every pixel for high-fidelity geometry in 3D GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 22765\u201322775","DOI":"10.1109\/CVPR52733.2024.02148"},{"key":"2266_CR29","doi-asserted-by":"crossref","unstructured":"Xu, Y., AlBahar, B., & Huang, J.-B. (2022). Temporally consistent semantic video editing. In: Proceedings of the European Conference on Computer Vision, 13675, (pp. 357\u2013374)","DOI":"10.1007\/978-3-031-19784-0_21"},{"key":"2266_CR30","unstructured":"Wang, G., Chen, T., Ghasedi, K., Wu, H., Ding, T., Nuesmeyer, C., Zharkov, I., Kankanhalli, M. S., & Liang, L. (2024). S3Editor: A sparse semantic-disentangled self-training framework for face video editing. arXiv preprint arXiv:2404.08111"},{"key":"2266_CR31","doi-asserted-by":"crossref","unstructured":"Xu, Y., He, S., Wong, K.-Y. K., & Luo, P. (2023). RIGID: Recurrent GAN inversion and editing of real face videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 13645\u201313655)","DOI":"10.1109\/ICCV51070.2023.01259"},{"key":"2266_CR32","doi-asserted-by":"crossref","unstructured":"Kim, G., Shim, H., Kim, H., Choi, Y., Kim, J., & Yang, E. (2023). Diffusion video autoencoders: Toward temporally consistent face video editing via disentangled video encoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 6091\u20136100)","DOI":"10.1109\/CVPR52729.2023.00590"},{"key":"2266_CR33","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations"},{"issue":"10","key":"2266_CR34","doi-asserted-by":"publisher","first-page":"5962","DOI":"10.1109\/TPAMI.2021.3087709","volume":"44","author":"J Deng","year":"2022","unstructured":"Deng, J., Guo, J., Yang, J., Xue, N., Kotsia, I., Zafeiriou, S.: ArcFace: Additive angular margin loss for deep face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 5962\u20135979 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2266_CR35","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, 139, (pp. 8748\u20138763)"},{"key":"2266_CR36","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. In: Proceedings of the Conference on Neural Information Processing Systems"},{"key":"2266_CR37","unstructured":"Song, J., Meng, C., & Ermon, S. (2021). Denoising diffusion implicit models. In: International Conference on Learning Representations"},{"key":"2266_CR38","doi-asserted-by":"crossref","unstructured":"Du, C., Li, Y., Qiu, Z., & Xu, C. (2023). Stable diffusion is unstable. In: Proceedings of the Conference on Neural Information Processing Systems","DOI":"10.52202\/075280-2556"},{"key":"2266_CR39","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xu, S., Chen, D., Jia, Y., & Tong, X. (2019). Accurate 3D face reconstruction with weakly-supervised learning: From single image to image set. CVPR Workshops, (pp. 285\u2013295)","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"2266_CR40","doi-asserted-by":"crossref","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., & Cohen-Or, D. (2021). Designing an encoder for StyleGAN image manipulation. ACM Transactions on Graphics, 40(4), 133:1\u2013133:14","DOI":"10.1145\/3450626.3459838"},{"key":"2266_CR41","unstructured":"Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., & Amodei, D. (2020). Language models are few-shot learners. In: Proceedings of the Conference on Neural Information Processing Systems"},{"key":"2266_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., & Fan, C. (2021). Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 3661\u20133670)","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"2266_CR43","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., Liang, S., Liu, Y.-J., Bao, H., & Zhang, J. (2021). AD-NeRF: Audio driven neural radiance fields for talking head synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 5764\u20135774)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"2266_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, H., Wu, W., Zhu, W., Jiang, L., Tang, S., Zhang, L., Liu, Z., & Loy, C. C. (2022). CelebV-HQ: A large-scale video facial attributes dataset. In: Proceedings of the European Conference on Computer Vision, 13667, (pp. 650\u2013667)","DOI":"10.1007\/978-3-031-20071-7_38"},{"key":"2266_CR45","doi-asserted-by":"crossref","unstructured":"Suwajanakorn, S., Seitz, S. M., & Kemelmacher-Shlizerman, I. (2017). Synthesizing Obama: Learning lip sync from audio. ACM Transactions on Graphics, 36(4), 95:1\u201395:13","DOI":"10.1145\/3072959.3073640"},{"key":"2266_CR46","doi-asserted-by":"crossref","unstructured":"Guo, J., Zhu, X., Yang, Y., Yang, F., Lei, Z., & Li, S. Z. (2020). Towards fast, accurate and stable 3D dense face alignment. In: Proceedings of the European Conference on Computer Vision, 12364, (pp. 152\u2013168)","DOI":"10.1007\/978-3-030-58529-7_10"},{"key":"2266_CR47","doi-asserted-by":"crossref","unstructured":"Yin, F., Zhang, Y., Cun, X., Cao, M., Fan, Y., Wang, X., Bai, Q., Wu, B., Wang, J., & Yang, Y. (2022). StyleHEAT: One-shot high-resolution editable talking face generation via pre-trained StyleGAN. In: Proceedings of the European Conference on Computer Vision, 13677, (pp. 85-101)","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"2266_CR48","doi-asserted-by":"crossref","unstructured":"Gal, R., Patashnik, O., Maron, H., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2022). StyleGAN-NADA: CLIP-guided domain adaptation of image generators. ACM Transactions on Graphics, 41(4), 141:1\u2013141:13","DOI":"10.1145\/3528223.3530164"},{"key":"2266_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120130","volume":"660","author":"X Ning","year":"2024","unstructured":"Ning, X., He, F., Dong, X., Li, W., Alenezi, F., Tiwari, P.: ICGNet: an intensity-controllable generation network based on covering learning for face attribute synthesis. Inf. Sci. 660, 120130 (2024)","journal-title":"Inf. Sci."},{"key":"2266_CR50","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.ins.2021.09.024","volume":"581","author":"X Cai","year":"2021","unstructured":"Cai, X., Cao, Y., Ren, Y., Cui, Z., Zhang, W.: Multi-objective evolutionary 3D face reconstruction based on improved encoder\u2013decoder network. Inf. Sci. 581, 233\u2013248 (2021)","journal-title":"Inf. Sci."},{"key":"2266_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119831","volume":"654","author":"W Kong","year":"2024","unstructured":"Kong, W., You, Z., Lyu, S.,& Lv, X.: Multi-dimensional stereo face reconstruction for psychological assistant diagnosis in medical meta-universe. Inf. Sci. 654, 119831 (2024)","journal-title":"Inf. Sci."},{"key":"2266_CR52","doi-asserted-by":"crossref","unstructured":"Gerogiannis, D., Papantoniou, F. P., Potamias, R. A., Lattas, A., & Zafeiriou, S. (2025). Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance. arXiv preprint arXiv:2501.05379","DOI":"10.1109\/CVPR52734.2025.01006"},{"key":"2266_CR53","doi-asserted-by":"crossref","unstructured":"Xu, Y., Shu, Z., Smith, C., Oh, S. W., & Huang, J. B. (2024). In-n-out: Faithful 3d gan inversion with volumetric decomposition for face editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 7225-7235)","DOI":"10.1109\/CVPR52733.2024.00690"},{"key":"2266_CR54","doi-asserted-by":"crossref","unstructured":"Qi, C., Cun, X., Zhang, Y., Lei, C., Wang, X., Shan, Y., & Chen, Q. (2023). Fatezero: Fusing attentions for zero-shot text-based video editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 15932-15942)","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"2266_CR55","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., & Dekel, T. (2024). TokenFlow: Consistent Diffusion Features for Consistent Video Editing. In: International Conference on Learning Representations (ICLR)"},{"key":"2266_CR56","doi-asserted-by":"crossref","unstructured":"Ouyang, H., Wang, Q., Xiao, Y., Bai, Q., Zhang, J., Zheng, K., ... & Shen, Y. (2024). Codef: Content deformation fields for temporally consistent video processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 8089-8099)","DOI":"10.1109\/CVPR52733.2024.00773"},{"key":"2266_CR57","unstructured":"Yang, X., Zhu, L., Fan, H., & Yang, Y. (2025). Videograin: Modulating space-time attention for multi-grained video editing. In: International Conference on Learning Representations (ICLR)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02266-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02266-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02266-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:07:37Z","timestamp":1783314457000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02266-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2266"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02266-1","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"9 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"221"}}