{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:38:56Z","timestamp":1792543136821,"version":"4.5.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197864","type":"print"},{"value":"9783031197871","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19787-1_40","type":"book-chapter","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T18:16:11Z","timestamp":1666289771000},"page":"702-719","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Motion Transformer for\u00a0Unsupervised Image Animation"],"prefix":"10.1007","author":[{"given":"Jiale","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiezheng","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuning","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Balakrishnan, G., Zhao, A., Dalca, A.V., Durand, F., Guttag, J.: Synthesizing images of humans in unseen poses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8340\u20138348 (2018)","DOI":"10.1109\/CVPR.2018.00870"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Tiwari, G., Theobalt, C., Pons-Moll, G.: Multi-garment net: learning to dress 3D people from images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5420\u20135430 (2019)","DOI":"10.1109\/ICCV.2019.00552"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Burkov, E., Pasechnik, I., Grigorev, A., Lempitsky, V.: Neural head reenactment with latent pose descriptors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13786\u201313795 (2020)","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"40_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"40_CR5","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":"40_CR6","unstructured":"Chen, X., Song, J., Hilliges, O.: Unpaired pose guided human image generation. In: Conference on Computer Vision and Pattern Recognition (CVPR 2019). Computer Vision Foundation (CVF) (2019)"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Chopra, A., Jain, R., Hemani, M., Krishnamurthy, B.: Zflow: gated appearance flow-based virtual try-on with 3d priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5433\u20135442 (2021)","DOI":"10.1109\/ICCV48922.2021.00538"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"40_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"40_CR10","unstructured":"Gao, Q., Wang, B., Liu, L., Chen, B.: Unsupervised co-part segmentation through assembly. In: International Conference on Machine Learning (2021)"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Geng, Z., Cao, C., Tulyakov, S.: 3D guided fine-grained face manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9821\u20139830 (2019)","DOI":"10.1109\/CVPR.2019.01005"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Ha, S., Kersner, M., Kim, B., Seo, S., Kim, D.: Marionette: few-shot face reenactment preserving identity of unseen targets. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10893\u201310900 (2020)","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Z., Han, X., Xu, J., Zhang, T.: Few-shot human motion transfer by personalized geometry and texture modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2297\u20132306 (2021)","DOI":"10.1109\/CVPR46437.2021.00233"},{"issue":"4","key":"40_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530104","volume":"41","author":"Y Jiang","year":"2022","unstructured":"Jiang, Y., Yang, S., Qiu, H., Wu, W., Loy, C.C., Liu, Z.: Text2human: text-driven controllable human image generation. ACM Trans. Graphics (TOG) 41(4), 1\u201311 (2022). https:\/\/doi.org\/10.1145\/3528223.3530104","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"40_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"issue":"4","key":"40_CR16","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1145\/3197517.3201283","volume":"37","author":"H Kim","year":"2018","unstructured":"Kim, H., et al.: Deep video portraits. ACM Trans. Graphics (TOG) 37(4), 163 (2018)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"40_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Tokenpose: learning keypoint tokens for human pose estimation. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Loy, C.C.: Dense intrinsic appearance flow for human pose transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3693\u20133702 (2019)","DOI":"10.1109\/CVPR.2019.00381"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., He, J., Zhang, T., Liu, X., Zhang, Y., Wu, F.: Diverse part discovery: occluded person re-identification with part-aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2898\u20132907 (2021)","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"40_CR21","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":"40_CR22","doi-asserted-by":"crossref","unstructured":"Lorenz, D., Bereska, L., Milbich, T., Ommer, B.: Unsupervised part-based disentangling of object shape and appearance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10955\u201310964 (2019)","DOI":"10.1109\/CVPR.2019.01121"},{"key":"40_CR23","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Advances in Neural Information Processing Systems, vol. 30, pp. 406\u2013416 (2017)"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q., Georgoulis, S., Van Gool, L., Schiele, B., Fritz, M.: Disentangled person image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 99\u2013108 (2018)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"40_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1007\/978-3-030-01219-9_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Neverova","year":"2018","unstructured":"Neverova, N., Alp G\u00fcler, R., Kokkinos, I.: Dense pose transfer. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 128\u2013143. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_8"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGAN: subject agnostic face swapping and reenactment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7184\u20137193 (2019)","DOI":"10.1109\/ICCV.2019.00728"},{"key":"40_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-030-01249-6_50","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Pumarola","year":"2018","unstructured":"Pumarola, A., Agudo, A., Martinez, A.M., Sanfeliu, A., Moreno-Noguer, F.: GANimation: anatomically-aware facial animation from a single image. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 835\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_50"},{"key":"40_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/978-3-030-67070-2_16","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"J Ren","year":"2020","unstructured":"Ren, J., Chai, M., Tulyakov, S., Fang, C., Shen, X., Yang, J.: Human motion transfer from poses in the wild. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12537, pp. 262\u2013279. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-67070-2_16"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Ren, J., Chai, M., Woodford, O.J., Olszewski, K., Tulyakov, S.: Flow guided transformable bottleneck networks for motion retargeting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10795\u201310805 (2021)","DOI":"10.1109\/CVPR46437.2021.01065"},{"key":"40_CR31","doi-asserted-by":"crossref","unstructured":"Ren, Y., Yu, X., Chen, J., Li, T.H., Li, G.: Deep image spatial transformation for person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7690\u20137699 (2020)","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"40_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"40_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/978-3-030-58621-8_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Sarkar","year":"2020","unstructured":"Sarkar, K., Mehta, D., Xu, W., Golyanik, V., Theobalt, C.: Neural re-rendering of humans from a single image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 596\u2013613. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_35"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2377\u20132386 (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"40_CR35","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. In: Advances in Neural Information Processing Systems (2019)"},{"key":"40_CR36","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"},{"key":"40_CR37","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"40_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Tao, J., et al.: Structure-aware motion transfer with deformable anchor model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3637\u20133646 (2022)","DOI":"10.1109\/CVPR52688.2022.00362"},{"key":"40_CR41","doi-asserted-by":"crossref","unstructured":"Tripathy, S., Kannala, J., Rahtu, E.: Facegan: Facial attribute controllable reenactment gan. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1329\u20131338 (2021)","DOI":"10.1109\/WACV48630.2021.00137"},{"key":"40_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"40_CR43","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, J., Chen, D., Liao, J.: High-fidelity pluralistic image completion with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4692\u20134701, October 2021","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Mallya, A., Liu, M.Y.: 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 (2021)","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"40_CR45","doi-asserted-by":"crossref","unstructured":"Watchareeruetai, U., et al.: Lotr: face landmark localization using localization transformer. arXiv preprint arXiv:2109.10057 (2021)","DOI":"10.1109\/ACCESS.2022.3149380"},{"key":"40_CR46","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, no. 4, 2852\u20132860, May 2021. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16391","DOI":"10.1609\/aaai.v35i4.16391"},{"key":"40_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1007\/978-3-030-58610-2_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Wei","year":"2020","unstructured":"Wei, Y., Liu, M., Wang, H., Zhu, R., Hu, G., Zuo, W.: Learning flow-based feature warping for face frontalization with illumination inconsistent supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 558\u2013574. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_33"},{"key":"40_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01261-8_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"O Wiles","year":"2018","unstructured":"Wiles, O., Koepke, A.S., Zisserman, A.: X2Face: a network for controlling face generation using images, audio, and pose codes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_41"},{"key":"40_CR49","doi-asserted-by":"crossref","unstructured":"Xu, B., et al.: Move as you like: image animation in e-commerce scenario. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2759\u20132761 (2021)","DOI":"10.1145\/3474085.3478550"},{"key":"40_CR50","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: Transpose: keypoint localization via transformer. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"40_CR51","doi-asserted-by":"crossref","unstructured":"Yao, G., et al.: One-shot face reenactment using appearance adaptive normalization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3172\u20133180 (2021)","DOI":"10.1609\/aaai.v35i4.16427"},{"key":"40_CR52","doi-asserted-by":"crossref","unstructured":"Yoon, J.S., Liu, L., Golyanik, V., Sarkar, K., Park, H.S., Theobalt, C.: Pose-guided human animation from a single image in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15039\u201315048, June 2021","DOI":"10.1109\/CVPR46437.2021.01479"},{"key":"40_CR53","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Wang, Z., Liu, Z., Lu, J., Zhou, J.: Pointr: diverse point cloud completion with geometry-aware transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12498\u201312507 (2021)","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"40_CR54","unstructured":"Zablotskaia, P., Siarohin, A., Zhao, B., Sigal, L.: DWNET: dense warp-based network for pose-guided human video generation. In: BMVC, p. 51 (2019)"},{"key":"40_CR55","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Shysheya, A., Burkov, E., Lempitsky, V.: Few-shot adversarial learning of realistic neural talking head models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9459\u20139468 (2019)","DOI":"10.1109\/ICCV.2019.00955"},{"key":"40_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, K., Lai, Y.K., Yang, J.: PISE: person image synthesis and editing with decoupled GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7982\u20137990 (2021)","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"40_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-030-01267-0_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Zhao","year":"2018","unstructured":"Zhao, L., Peng, X., Tian, Yu., Kapadia, M., Metaxas, D.: Learning to forecast and refine residual motion for image-to-video generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 403\u2013419. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_24"},{"key":"40_CR58","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"40_CR59","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable {detr}: Deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)"},{"key":"40_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., Bai, X.: Progressive pose attention transfer for person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2347\u20132356 (2019)","DOI":"10.1109\/CVPR.2019.00245"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19787-1_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:05:25Z","timestamp":1792541125000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-19787-1_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197864","9783031197871"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19787-1_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"21 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}