{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:47:04Z","timestamp":1782841624106,"version":"3.54.5"},"reference-count":118,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11263-023-01832-8","type":"journal-article","created":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T09:01:56Z","timestamp":1687078916000},"page":"2699-2722","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Conditional Temporal Variational AutoEncoder for Action Video Prediction"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-8001","authenticated-orcid":false,"given":"Xiaogang","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,18]]},"reference":[{"key":"1832_CR1","doi-asserted-by":"crossref","unstructured":"Aberman, K., Wu, R., Lischinski, D., Chen, B., & Cohen-Or, D. (2019). Learning character-agnostic motion for motion retargeting in 2d. arXiv:1905.01680.","DOI":"10.1145\/3306346.3322999"},{"key":"1832_CR2","doi-asserted-by":"crossref","unstructured":"Adeli, V., Ehsanpour, M., Reid, I., Niebles, J. C., Savarese, S., Adeli, E., & Rezatofighi, H. (2021). Tripod: Human trajectory and pose dynamics forecasting in the wild. In International conference on computer vision.","DOI":"10.1109\/ICCV48922.2021.01314"},{"key":"1832_CR3","doi-asserted-by":"crossref","unstructured":"Ahuja, C., & Morency, L. P. (2019). Language2pose: Natural language grounded pose forecasting. In 2019 International conference on 3D vision (3DV).","DOI":"10.1109\/3DV.2019.00084"},{"key":"1832_CR4","doi-asserted-by":"crossref","unstructured":"Aliakbarian, S., Saleh, F. S., Salzmann, M., Petersson, L., & Gould, S. (2020). A stochastic conditioning scheme for diverse human motion prediction. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"1832_CR5","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R. H., & Levine, S. (2017). Stochastic variational video prediction. arXiv:1710.11252."},{"key":"1832_CR6","doi-asserted-by":"crossref","unstructured":"Balaji, Y., Min, M. R., Bai, B., Chellappa, R., & Graf, H. P. (2019). Conditional gan with discriminative filter generation for text-to-video synthesis. In IJCAI.","DOI":"10.24963\/ijcai.2019\/276"},{"key":"1832_CR7","doi-asserted-by":"crossref","unstructured":"Cai, H., Bai, C., Tai, Y. W., & Tang, C. K. (2018). Deep video generation, prediction and completion of human action sequences. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01216-8_23"},{"key":"1832_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Y., Huang, L., Wang, Y., Cham, T. J., Cai, J., Yuan, J., Liu, J., Yang, X., Zhu, Y., Shen, X., et\u00a0al. (2020). Learning progressive joint propagation for human motion prediction. In The european conference on computer vision.","DOI":"10.1007\/978-3-030-58571-6_14"},{"key":"1832_CR9","unstructured":"Cao, Z., Hidalgo Martinez, G., Simon, T., Wei, S., & Sheikh, Y. A. (2019). Openpose: Realtime multi-person 2d pose estimation using part affinity fields. In IEEE Transactions on Pattern Analysis and Machine Intelligence. Intell."},{"key":"1832_CR10","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? A new model and the kinetics dataset. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.502"},{"key":"1832_CR11","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Ballas, N., & Courville, A. (2019). Improved conditional vrnns for video prediction. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2019.00770"},{"key":"1832_CR12","doi-asserted-by":"crossref","unstructured":"Chen, G., Li, J., Lu, J., & Zhou, J. (2021). Human trajectory prediction via counterfactual analysis. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV48922.2021.00968"},{"key":"1832_CR13","doi-asserted-by":"crossref","unstructured":"Chen, W., & Hays, J. (2018). Sketchygan: Towards diverse and realistic sketch to image synthesis. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00981"},{"key":"1832_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., Yan, W., & Tan, R. T. (2019). Occlusion-aware networks for 3d human pose estimation in video. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00081"},{"key":"1832_CR15","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Chang, J. Y., & Lee, K. M. (2021). Beyond static features for temporally consistent 3d human pose and shape from a video. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"1832_CR16","unstructured":"Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A.C., & Bengio, Y. (2015). A recurrent latent variable model for sequential data. In Advances in Neural Information Processing Systems."},{"key":"1832_CR17","unstructured":"Clark, A., Donahue, J., & Simonyan, K. (2019). Adversarial video generation on complex datasets. arXiv:1907.06571."},{"key":"1832_CR18","doi-asserted-by":"crossref","unstructured":"Cui, A., McKee, D., & Lazebnik, S. (2021). Dressing in order: Recurrent person image generation for pose transfer, virtual try-on and outfit editing. In International Conference on Computer Vision","DOI":"10.1109\/ICCV48922.2021.01437"},{"key":"1832_CR19","unstructured":"Denton, E., & Fergus, R. (2018). Stochastic video generation with a learned prior. arXiv:1802.07687."},{"key":"1832_CR20","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., & Dai, B. (2022). Revisiting skeleton-based action recognition. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"1832_CR21","doi-asserted-by":"crossref","unstructured":"Duan, J., Wang, L., Long, C., Zhou, S., Zheng, F., Shi, L., & Hua, G. (2022). Complementary attention gated network for pedestrian trajectory prediction. In AAAI.","DOI":"10.1609\/aaai.v36i1.19933"},{"key":"1832_CR22","unstructured":"Finn, C., Goodfellow, I., & Levine, S. (2016). Unsupervised learning for physical interaction through video prediction. In Advances in Neural Information Processing Systems."},{"key":"1832_CR23","doi-asserted-by":"crossref","unstructured":"Fr\u00fchst\u00fcck, A., Singh, K. K., Shechtman, E., Mitra, N. J., Wonka, P., & Lu, J. (2022). Insetgan for full-body image generation. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00757"},{"key":"1832_CR24","doi-asserted-by":"crossref","unstructured":"Fu, J., Li, S., Jiang, Y., Lin, K. Y., Qian, C., Loy, C. C., Wu, W., & Liu, Z. (2022). Stylegan-human: A data-centric odyssey of human generation. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-031-19787-1_1"},{"key":"1832_CR25","doi-asserted-by":"crossref","unstructured":"Gafni, O., Ashual, O., & Wolf, L. (2021). Single-shot freestyle dance reenactment. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.00094"},{"key":"1832_CR26","doi-asserted-by":"crossref","unstructured":"Ge, C., Song, Y., Ge, Y., Yang, H., Liu, W., & Luo, P. (2021). Disentangled cycle consistency for highly-realistic virtual try-on. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01665"},{"key":"1832_CR27","doi-asserted-by":"crossref","unstructured":"Ge, Y., Song, Y., Zhang, R., Ge, C., Liu, W., & Luo, P. (2021). Parser-free virtual try-on via distilling appearance flows. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"1832_CR28","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., & Wang, J. (2021). Bottom-up human pose estimation via disentangled keypoint regression. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"1832_CR29","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Zhang, R., Dokania, P.K., Wang, O., Efros, A.A., Torr, P.H., & Shechtman, E. (2019). Interactive sketch & fill: Multiclass sketch-to-image translation. In International conference on computer vision.","DOI":"10.1109\/ICCV.2019.00126"},{"key":"1832_CR30","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In Advances in Neural Information Processing Systems."},{"key":"1832_CR31","doi-asserted-by":"crossref","unstructured":"Gopalakrishnan, A., Mali, A., Kifer, D., Giles, L., & Ororbia, A.G. (2019). A neural temporal model for human motion prediction. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.01239"},{"key":"1832_CR32","doi-asserted-by":"crossref","unstructured":"Greff, K., Srivastava, R. K., Koutn\u00edk, J., Steunebrink, B. R., & Schmidhuber, J. (2016). Lstm: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems.","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"1832_CR33","unstructured":"Guen, V. L., & Thome, N. (2020). Disentangling physical dynamics from unknown factors for unsupervised video prediction. In IEEE conference on computer vision and pattern recognition."},{"key":"1832_CR34","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., & Cheng, L. (2022). Generating diverse and natural 3d human motions from text. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"1832_CR35","doi-asserted-by":"crossref","unstructured":"Guo, X., & Choi, J. (2019). Human motion prediction via learning local structure representations and temporal dependencies. In AAAI.","DOI":"10.1609\/aaai.v33i01.33012580"},{"key":"1832_CR36","doi-asserted-by":"crossref","unstructured":"Guo, X., Zhao, Y., & Li, J. (2021). Danceit: Music-inspired dancing video synthesis. IEEE Transactions on Image Process.","DOI":"10.1109\/TIP.2021.3086082"},{"key":"1832_CR37","doi-asserted-by":"crossref","unstructured":"Han, L., Ren, J., Lee, H.Y., Barbieri, F., Olszewski, K., Minaee, S., Metaxas, D., & Tulyakov, S. (2022). Show me what and tell me how: Video synthesis via multimodal conditioning. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00360"},{"key":"1832_CR38","doi-asserted-by":"crossref","unstructured":"Ho, T.T., Virtusio, J.J., Chen, Y.Y., Hsu, C.M., & Hua, K.L. (2020). Sketch-guided deep portrait generation. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM).","DOI":"10.1145\/3396237"},{"key":"1832_CR39","doi-asserted-by":"crossref","unstructured":"Huang, Y., Bi, H., Li, Z., Mao, T., & Wang, Z. (2019). Stgat: Modeling spatial-temporal interactions for human trajectory prediction. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2019.00637"},{"key":"1832_CR40","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2013). Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2013.248"},{"key":"1832_CR41","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Molchanov, P., & Kautz, J. (2020). Weakly-supervised 3d human pose learning via multi-view images in the wild. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00529"},{"key":"1832_CR42","unstructured":"Jia, X., De\u00a0Brabandere, B., Tuytelaars, T., & Gool, L. V. (2016). Dynamic filter networks. In Advances in Neural Information Processing Systems."},{"key":"1832_CR43","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Yang, S., Qju, H., Wu, W., Loy, C. C., & Liu, Z. (2022). Text2human: Text-driven controllable human image generation. ACM Transactions on Graph.","DOI":"10.1145\/3528223.3530104"},{"key":"1832_CR44","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"1832_CR45","unstructured":"Kalchbrenner, N., van\u00a0den Oord, A., Simonyan, K., Danihelka, I., Vinyals, O., Graves, A., & Kavukcuoglu, K. (2017). Video pixel networks. In ICML."},{"key":"1832_CR46","doi-asserted-by":"crossref","unstructured":"Kappel, M., Golyanik, V., Elgharib, M., Henningson, J. O., Seidel, H. P., Castillo, S., Theobalt, C., & Magnor, M. (2021). High-fidelity neural human motion transfer from monocular video. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.00159"},{"key":"1832_CR47","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020). Analyzing and improving the image quality of stylegan. In IEEE IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"1832_CR48","unstructured":"Kim, Y., Nam, S., Cho, I., & Kim, S.J. (2019). Unsupervised keypoint learning for guiding class-conditional video prediction. In Advances in Neural Information Processing Systems."},{"key":"1832_CR49","unstructured":"Kim, Y., Nam, S., Cho, I., & Kim, S. J. (2019). Unsupervised keypoint learning for guiding class-conditional video prediction. In Advances in Neural Information Processing Systems."},{"key":"1832_CR50","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980."},{"key":"1832_CR51","unstructured":"Kingma, D.P., & Welling, M. (2014). Auto-encoding variational bayes. In The International Conference on Learning Representations."},{"key":"1832_CR52","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., & Akbas, E. (2019). Self-supervised learning of 3d human pose using multi-view geometry. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00117"},{"key":"1832_CR53","doi-asserted-by":"crossref","unstructured":"Kothari, P., Sifringer, B., & Alahi, A. (2021). Interpretable social anchors for human trajectory forecasting in crowds. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01530"},{"key":"1832_CR54","unstructured":"Kumar, M., Babaeizadeh, M., Erhan, D., Finn, C., Levine, S., Dinh, L., & Kingma, D. (2019). Videoflow: A flow-based generative model for video. arXiv:1903.01434"},{"key":"1832_CR55","doi-asserted-by":"crossref","unstructured":"Kwon, Y.H., & Park, M.G. (2019). Predicting future frames using retrospective cycle gan. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00191"},{"key":"1832_CR56","unstructured":"Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., & Levine, S. (2018). Stochastic adversarial video prediction. arXiv:1804.01523."},{"key":"1832_CR57","unstructured":"Lee, H. Y., Yang, X., Liu, M. Y., Wang, T. C., Lu, Y. D., Yang, M. H., & Kautz, J. (2019). Dancing to music. In Advances in Neural Information Processing Systems."},{"key":"1832_CR58","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, Z., Sun\u00a0Lee, W., & Hee\u00a0Lee, G. (2018). Convolutional sequence to sequence model for human dynamics. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00548"},{"key":"1832_CR59","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, S., Zhang, Z., Ding, Y., Zheng, Y., Yu, X., & Fan, C. (2021). Write-a-speaker: Text-based emotional and rhythmic talking-head generation. In AAAI.","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"1832_CR60","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, J., Li, K., Vyas, S., & Rawat, Y.S. (2022). Pose-guided generative adversarial net for novel view action synthesis. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision.","DOI":"10.1109\/WACV51458.2022.00316"},{"key":"1832_CR61","doi-asserted-by":"crossref","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., & Yang, M.H. (2018). Flow-grounded spatial-temporal video prediction from still images. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01240-3_37"},{"key":"1832_CR62","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Lu, J., Shechtman, E., Lee, Y. J., & Singh, K. K. (2021). Collaging class-specific gans for semantic image synthesis. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV48922.2021.01415"},{"key":"1832_CR63","doi-asserted-by":"crossref","unstructured":"Liu, D., Wu, L., Zheng, F., Liu, L., & Wang, M. (2022). Verbal-person nets: Pose-guided multi-granularity language-to-person generation. IEEE Transactions on Neural Networks and Learning Systems.","DOI":"10.1109\/TNNLS.2022.3151631"},{"key":"1832_CR64","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., & Van\u00a0Gool, L. (2017). Pose guided person image generation. In Advances in Neural Information Processing Systems.","DOI":"10.1109\/CVPR.2018.00018"},{"key":"1832_CR65","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., & Salzmann, M. (2020). History repeats itself: Human motion prediction via motion attention. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-58568-6_28"},{"key":"1832_CR66","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M., & Li, H. (2019). Learning trajectory dependencies for human motion prediction. In The European Conference on Computer Vision.","DOI":"10.1109\/ICCV.2019.00958"},{"key":"1832_CR67","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R. Y., Wang, Z., & Paul\u00a0Smolley, S. (2017). Least squares generative adversarial networks. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/ICCV.2017.304"},{"key":"1832_CR68","unstructured":"Mathieu, M., Couprie, C., & LeCun, Y. (2015). Deep multi-scale video prediction beyond mean square error. arXiv:1511.05440."},{"key":"1832_CR69","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u1ef3, J., & Khudanpur, S. (2010). Recurrent neural network based language model. In 11th Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"1832_CR70","unstructured":"Minderer, M., Sun, C., Villegas, R., Cole, F., Murphy, K. P., & Lee, H. (2019). Unsupervised learning of object structure and dynamics from videos. In Advances in Neural Information Processing Systems."},{"key":"1832_CR71","doi-asserted-by":"crossref","unstructured":"Neverova, N., Alp\u00a0Guler, R., & Kokkinos, I. (2018). Dense pose transfer. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01219-9_8"},{"key":"1832_CR72","doi-asserted-by":"crossref","unstructured":"Oliu, M., Selva, J., & Escalera, S. (2018). Folded recurrent neural networks for future video prediction. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"1832_CR73","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et\u00a0al. (2019). Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems."},{"key":"1832_CR74","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., & Auli, M. (2019). 3d human pose estimation in video with temporal convolutions and semi-supervised training. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1832_CR75","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De\u00a0Vries, H., Dumoulin, V., & Courville, A. (2018). Film: Visual reasoning with a general conditioning layer. In AAAI.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"1832_CR76","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Angelova, A., Toshev, A., & Ryoo, M.S. (2020). Adversarial generative grammars for human activity prediction. arXiv:2008.04888.","DOI":"10.1007\/978-3-030-58536-5_30"},{"key":"1832_CR77","unstructured":"Razavi, A., Oord, A. V. D., Poole, B., & Vinyals, O. (2019). Preventing posterior collapse with delta-vaes. In ICML"},{"key":"1832_CR78","doi-asserted-by":"crossref","unstructured":"Ren, X., Li, H., Huang, Z., & Chen, Q. (2020). Self-supervised dance video synthesis conditioned on music. In ACM International Conference on Multimedia.","DOI":"10.1145\/3394171.3413932"},{"key":"1832_CR79","doi-asserted-by":"crossref","unstructured":"Ren, Y., Fan, X., Li, G., Liu, S., & Li, T.H. (2022). Neural texture extraction and distribution for controllable person image synthesis. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01317"},{"key":"1832_CR80","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Sp\u00f6rri, J., Katircioglu, I., Constantin, V., Meyer, F., M\u00fcller, E., Salzmann, M., & Fua, P. (2018). Learning monocular 3d human pose estimation from multi-view images. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00880"},{"key":"1832_CR81","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T. T., & Wang, G. (2016). Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.115"},{"key":"1832_CR82","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., & Sebe, N. (2019). First order motion model for image animation. In Advances in Neural Information Processing Systems."},{"key":"1832_CR83","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 IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00248"},{"key":"1832_CR84","unstructured":"Simonyan, K., & Zisserman, A. (2014). Two-stream convolutional networks for action recognition in videos. In Advances in Neural Information Processing Systems."},{"key":"1832_CR85","doi-asserted-by":"crossref","unstructured":"Siyao, L., Yu, W., Gu, T., Lin, C., Wang, Q., Qian, C., Loy, C. C., & Liu, Z. (2022). Bailando: 3d dance generation by actor-critic gpt with choreographic memory. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"1832_CR86","unstructured":"Srivastava, N., Mansimov, E., & Salakhudinov, R. (2015). Unsupervised learning of video representations using lstms. In ICML."},{"key":"1832_CR87","doi-asserted-by":"crossref","unstructured":"Tang, H., Bai, S., Zhang, L., Torr, P.H., & Sebe, N. (2020). Xinggan for person image generation. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"1832_CR88","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., & Kautz, J. (2018). Mocogan: Decomposing motion and content for video generation. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00165"},{"key":"1832_CR89","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., & Gelly, S. (2018). Towards accurate generative models of video: A new metric & challenges. arXiv:1812.01717."},{"key":"1832_CR90","doi-asserted-by":"crossref","unstructured":"Villegas, R., Yang, J., Ceylan, D., & Lee, H. (2018). Neural kinematic networks for unsupervised motion retargetting. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00901"},{"key":"1832_CR91","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., & Lee, H. (2017). Decomposing motion and content for natural video sequence prediction. arXiv:1706.08033."},{"key":"1832_CR92","unstructured":"Villegas, R., Yang, J., Zou, Y., Sohn, S., Lin, X., & Lee, H. (2017). Learning to generate long-term future via hierarchical prediction. In ICML."},{"key":"1832_CR93","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., & Hebert, M. (2017). The pose knows: Video forecasting by generating pose futures. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2017.361"},{"key":"1832_CR94","doi-asserted-by":"crossref","unstructured":"Wandt, B., Rudolph, M., Zell, P., Rhodin, H., & Rosenhahn, B. (2021). Canonpose: Self-supervised monocular 3d human pose estimation in the wild. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01309"},{"key":"1832_CR95","doi-asserted-by":"crossref","unstructured":"Wang, B., Adeli, E., Chiu, H. K., Huang, D. A., & Niebles, J. C. (2019). Imitation learning for human pose prediction. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2019.00722"},{"key":"1832_CR96","unstructured":"Wang, T. C., Liu, M. Y., Zhu, J. Y., Liu, G., Tao, A., Kautz, J., & Catanzaro, B. (2018). Video-to-video synthesis. arXiv:1808.06601."},{"key":"1832_CR97","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., & Catanzaro, B. (2018). High-resolution image synthesis and semantic manipulation with conditional gans. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"1832_CR98","doi-asserted-by":"crossref","unstructured":"Wang, W., Alameda-Pineda, X., Xu, D., Fua, P., Ricci, E., & Sebe, N. (2018). Every smile is unique: Landmark-guided diverse smile generation. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00740"},{"key":"1832_CR99","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, M., Cai, H., Chen, W.M., & Han, S. (2022). Lite pose: Efficient architecture design for 2d human pose estimation. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.01278"},{"key":"1832_CR100","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, J., Zhu, H., Long, M., Wang, J., & Yu, P. S. (2019). Memory in memory: A predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00937"},{"key":"1832_CR101","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Process.","DOI":"10.1109\/TIP.2003.819861"},{"key":"1832_CR102","unstructured":"Wichers, N., Villegas, R., Erhan, D., & Lee, H. (2018). Hierarchical long-term video prediction without supervision. arXiv:1806.04768."},{"key":"1832_CR103","doi-asserted-by":"crossref","unstructured":"Wu, Q., Chen, X., Huang, Z., & Wang, W. (2020). Generating future frames with mask-guided prediction. In The IEEE International Conference on Multimedia and Expo.","DOI":"10.1109\/ICME46284.2020.9102876"},{"key":"1832_CR104","doi-asserted-by":"crossref","unstructured":"Xu, J., Ni, B., Li, Z., Cheng, S., & Yang, X. (2018). Structure preserving video prediction. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00158"},{"key":"1832_CR105","doi-asserted-by":"crossref","unstructured":"Yan, X., Rastogi, A., Villegas, R., Sunkavalli, K., Shechtman, E., Hadap, S., Yumer, E., & Lee, H. (2018). Mt-vae: Learning motion transformations to generate multimodal human dynamics. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01228-1_17"},{"key":"1832_CR106","doi-asserted-by":"crossref","unstructured":"Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., & Lin, D. (2018). Pose guided human video generation. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"1832_CR107","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhu, W., Wu, W., Qian, C., Zhou, Q., Zhou, B., & Loy, C.C. (2020). Transmomo: Invariance-driven unsupervised video motion retargeting. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00535"},{"key":"1832_CR108","doi-asserted-by":"crossref","unstructured":"Yoo, Y., Yun, S., Jin\u00a0Chang, H., Demiris, Y., & Young\u00a0Choi, J. (2017). Variational autoencoded regression: high dimensional regression of visual data on complex manifold. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.314"},{"key":"1832_CR109","doi-asserted-by":"crossref","unstructured":"Yoon, J.S., Liu, L., Golyanik, V., Sarkar, K., Park, H.S., & Theobalt, C. (2021). Pose-guided human animation from a single image in the wild. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01479"},{"key":"1832_CR110","doi-asserted-by":"crossref","unstructured":"Yuan, Y., & Kitani, K. (2020). Dlow: Diversifying latent flows for diverse human motion prediction. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"1832_CR111","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., & Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1832_CR112","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., & Derpanis, K.G. (2013). From actemes to action: A strongly-supervised representation for detailed action understanding. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2013.280"},{"key":"1832_CR113","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., & Metaxas, D. (2018). Learning to forecast and refine residual motion for image-to-video generation. In The European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01267-0_24"},{"key":"1832_CR114","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, S., Li, B., Li, Y., Li, J., & Zhang, Z. (2019). Text guided person image synthesis. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00378"},{"key":"1832_CR115","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., & Efros, A.A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV.2017.244"},{"key":"1832_CR116","doi-asserted-by":"crossref","unstructured":"Zhu, W., Yang, Z., Di, Z., Wu, W., Wang, Y., & Loy, C.C. (2022). Mocanet: Motion retargeting in-the-wild via canonicalization networks. In AAAI.","DOI":"10.1609\/aaai.v36i3.20274"},{"key":"1832_CR117","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., & Bai, X. (2019). Progressive pose attention transfer for person image generation. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00245"},{"key":"1832_CR118","doi-asserted-by":"crossref","unstructured":"Zhuang, W., Wang, C., Chai, J., Wang, Y., Shao, M., & Xia, S. (2022). Music2dance: Dancenet for music-driven dance generation. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)","DOI":"10.1145\/3485664"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01832-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01832-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01832-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T02:13:01Z","timestamp":1692411181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01832-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":118,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1832"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01832-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,18]]},"assertion":[{"value":"21 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}