{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:12:44Z","timestamp":1765041164428,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T00:00:00Z","timestamp":1619222400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T00:00:00Z","timestamp":1619222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s00371-021-02135-0","type":"journal-article","created":{"date-parts":[[2021,4,25]],"date-time":"2021-04-25T07:11:32Z","timestamp":1619334692000},"page":"2603-2616","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["$$\\hbox {PISEP}{^2}$$: pseudo-image sequence evolution-based 3D pose prediction"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9224-8649","authenticated-orcid":false,"given":"Xiaoli","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqin","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,24]]},"reference":[{"key":"2135_CR1","first-page":"1","volume":"36","author":"M Afrasiabi","year":"2019","unstructured":"Afrasiabi, M., Mansoorizadeh, M., et al.: DTW-CNN: time series-based human interaction prediction in videos using CNN-extracted features. Vis. Comput. 36, 1\u201313 (2019)","journal-title":"Vis. Comput."},{"key":"2135_CR2","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R.H., Levine, S.: Stochastic variational video prediction. In: International Conference on Learning Representations (2017)"},{"key":"2135_CR3","doi-asserted-by":"crossref","unstructured":"Bloom, V., Makris, D., Argyriou, V.: G3d: A gaming action dataset and real time action recognition evaluation framework. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. IEEE, pp. 7\u201312 (2012)","DOI":"10.1109\/CVPRW.2012.6239175"},{"issue":"8","key":"2135_CR4","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1109\/83.855440","volume":"9","author":"AG Bors","year":"2000","unstructured":"Bors, A.G., Pitas, I.: Prediction and tracking of moving objects in image sequences. IEEE Trans. Image Process. 9(8), 1441\u20131445 (2000)","journal-title":"IEEE Trans. Image Process."},{"key":"2135_CR5","doi-asserted-by":"crossref","unstructured":"Butepage, J., Black, M.J., Kragic, D., Kjellstrom, H.: Deep representation learning for human motion prediction and classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6158\u20136166 (2017)","DOI":"10.1109\/CVPR.2017.173"},{"key":"2135_CR6","doi-asserted-by":"crossref","unstructured":"Chaudhry, R., Ofli, F., Kurillo, G., Bajcsy, R., Vidal, R.: Bio-inspired dynamic 3D discriminative skeletal features for human action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 471\u2013478 (2013)","DOI":"10.1109\/CVPRW.2013.153"},{"key":"2135_CR7","doi-asserted-by":"crossref","unstructured":"Chiu, H.k., Adeli, E., Wang, B., Huang, D.A., Niebles, J.C.: Action-agnostic human pose forecasting. In: 2019 IEEE Winter Conference on Applications of Computer Vision. IEEE, pp. 1423\u20131432 (2019)","DOI":"10.1109\/WACV.2019.00156"},{"key":"2135_CR8","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)"},{"key":"2135_CR9","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Advances in Neural Information Processing Systems, pp. 64\u201372 (2016)"},{"key":"2135_CR10","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4346\u20134354 (2015)","DOI":"10.1109\/ICCV.2015.494"},{"issue":"3","key":"2135_CR11","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/10867651.1998.10487493","volume":"3","author":"FS Grassia","year":"1998","unstructured":"Grassia, F.S.: Practical parameterization of rotations using the exponential map. J. Graph. Tools 3(3), 29\u201348 (1998)","journal-title":"J. Graph. Tools"},{"key":"2135_CR12","doi-asserted-by":"crossref","unstructured":"Gui, L.Y., Wang, Y.X., Liang, X., Moura, J.M.: Adversarial geometry-aware human motion prediction. In: Proceedings of the European Conference on Computer Vision, pp. 786\u2013803 (2018)","DOI":"10.1007\/978-3-030-01225-0_48"},{"key":"2135_CR13","doi-asserted-by":"crossref","unstructured":"Gui, L.Y., Wang, Y.X., Ramanan, D., Moura, J.M.: Few-shot human motion prediction via meta-learning. In: Proceedings of the European Conference on Computer Vision, pp 432\u2013450 (2018)","DOI":"10.1007\/978-3-030-01237-3_27"},{"issue":"5","key":"2135_CR14","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1109\/TCYB.2013.2265378","volume":"43","author":"J Han","year":"2013","unstructured":"Han, J., Shao, L., Xu, D., Shotton, J.: Enhanced computer vision with microsoft kinect sensor: a review. IEEE Trans. Cybern. 43(5), 1318\u20131334 (2013)","journal-title":"IEEE Trans. Cybern."},{"issue":"4","key":"2135_CR15","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1145\/2897824.2925975","volume":"35","author":"D Holden","year":"2016","unstructured":"Holden, D., Saito, J., Komura, T.: A deep learning framework for character motion synthesis and editing. ACM Trans. Graph. 35(4), 138 (2016)","journal-title":"ACM Trans. Graph."},{"key":"2135_CR16","unstructured":"Hsieh, J.T., Liu, B., Huang, D.A., Fei-Fei, L.F., Niebles, J.C.: Learning to decompose and disentangle representations for video prediction. In: Advances in Neural Information Processing Systems, pp. 517\u2013526 (2018)"},{"key":"2135_CR17","doi-asserted-by":"crossref","unstructured":"Hussein, N., Gavves, E., Smeulders, A.W.: Timeception for complex action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 254\u2013263 (2019)","DOI":"10.1109\/CVPR.2019.00034"},{"issue":"7","key":"2135_CR18","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human 3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2135_CR19","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R,. Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5308\u20135317 (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"2135_CR20","unstructured":"Kalchbrenner, N., van\u00a0den Oord, A., Simonyan, K., Danihelka, I., Vinyals, O., Graves, A., Kavukcuoglu, K.: Video pixel networks. In: Proceedings of the 34th International Conference on Machine Learning, vol.\u00a070, pp. 1771\u20131779 (2017)"},{"issue":"4","key":"2135_CR21","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/TIP.2015.2400818","volume":"24","author":"F Kamisli","year":"2015","unstructured":"Kamisli, F.: Block-based spatial prediction and transforms based on 2D Markov processes for image and video compression. IEEE Trans. Image Process. 24(4), 1247\u20131260 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"2135_CR22","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3288\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"2135_CR23","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. arXiv preprint arXiv:180611230 (2018)"},{"key":"2135_CR24","doi-asserted-by":"publisher","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. In: International Joint Conference on Artificial Intelligence, pp. 786\u2013792 (2018). https:\/\/doi.org\/10.24963\/ijcai.2018\/109","DOI":"10.24963\/ijcai.2018\/109"},{"issue":"6\u20138","key":"2135_CR25","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1007\/s00371-019-01692-9","volume":"35","author":"Y Li","year":"2019","unstructured":"Li, Y., Wang, Z., Yang, X., Wang, M., Poiana, S.I., Chaudhry, E., Zhang, J.: Efficient convolutional hierarchical autoencoder for human motion prediction. Vis. Comput. 35(6\u20138), 1143\u20131156 (2019)","journal-title":"Vis. Comput."},{"key":"2135_CR26","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion gan for future-flow embedded video prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1744\u20131752 (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"2135_CR27","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. In: International Conference on Learning Representations (2017)"},{"key":"2135_CR28","doi-asserted-by":"crossref","unstructured":"Lu, C., Hirsch, M., Scholkopf, B.: Flexible spatio-temporal networks for video prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6523\u20136531 (2017)","DOI":"10.1109\/CVPR.2017.230"},{"key":"2135_CR29","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2891\u20132900 (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"2135_CR30","doi-asserted-by":"publisher","first-page":"3959","DOI":"10.1109\/TIP.2019.2907048","volume":"28","author":"Q Nie","year":"2019","unstructured":"Nie, Q., Wang, J., Wang, X., Liu, Y.: View-invariant human action recognition based on a 3D bio-constrained skeleton model. IEEE Trans. Image Process. 28, 3959\u20133972 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"2135_CR31","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in atari games. In: Advances in Neural Information Processing Systems, pp. 2863\u20132871 (2015)"},{"issue":"3","key":"2135_CR32","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1007\/s00371-019-01644-3","volume":"36","author":"Y Qin","year":"2020","unstructured":"Qin, Y., Mo, L., Li, C., Luo, J.: Skeleton-based action recognition by part-aware graph convolutional networks. Vis. Comput. 36(3), 621\u2013631 (2020)","journal-title":"Vis. Comput."},{"key":"2135_CR33","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: Ntu rgb+ d: a large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"2135_CR34","doi-asserted-by":"crossref","unstructured":"Tang, Y., Ma, L., Liu, W., Zheng, W.: Long-term human motion prediction by modeling motion context and enhancing motion dynamic (2018). arXiv preprint arXiv:180502513","DOI":"10.24963\/ijcai.2018\/130"},{"key":"2135_CR35","doi-asserted-by":"crossref","unstructured":"Taylor, G.W., Hinton, G.E., Roweis, S.T.: Modeling human motion using binary latent variables. In: Advances in Neural Information Processing Systems, pp. 1345\u20131352 (2007)","DOI":"10.7551\/mitpress\/7503.003.0173"},{"key":"2135_CR36","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: convolutional 3d pose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2500\u20132509 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"2135_CR37","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"10","key":"2135_CR38","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1007\/s00371-012-0752-6","volume":"29","author":"S Vishwakarma","year":"2013","unstructured":"Vishwakarma, S., Agrawal, A.: A survey on activity recognition and behavior understanding in video surveillance. Vis. Comput. 29(10), 983\u20131009 (2013)","journal-title":"Vis. Comput."},{"key":"2135_CR39","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Patch to the future: unsupervised visual prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3302\u20133309 (2014)","DOI":"10.1109\/CVPR.2014.416"},{"key":"2135_CR40","unstructured":"Wang, Y., Long, M., Wang, J., Gao, Z., Philip, S.Y.: Predrnn: recurrent neural networks for predictive learning using spatiotemporal lstms. In: Advances in Neural Information Processing Systems, pp. 879\u2013888 (2017)"},{"key":"2135_CR41","unstructured":"Wang, Y., Gao, Z., Long, M., Wang, J., Yu, P.S.: Predrnn++: towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In: International Conference on Machine Learning (2018)"},{"key":"2135_CR42","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision, pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"2135_CR43","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional lstm network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"key":"2135_CR44","doi-asserted-by":"crossref","unstructured":"Xu, J., Ni, B., Li, Z., Cheng, S., Yang, X.: Structure preserving video prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1460\u20131469 (2018)","DOI":"10.1109\/CVPR.2018.00158"},{"key":"2135_CR45","doi-asserted-by":"crossref","unstructured":"Xu, Z., Wang, Y., Long, M., Wang, J., KLiss, M.: Predcnn: predictive learning with cascade convolutions. In: International Joint Conference on Artificial Intelligence, pp. 2940\u20132947 (2018)","DOI":"10.24963\/ijcai.2018\/408"},{"key":"2135_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Parker, L.E.: Bio-inspired predictive orientation decomposition of skeleton trajectories for real-time human activity prediction. In: 2015 IEEE International Conference on Robotics and Automation, IEEE, pp. 3053\u20133060 (2015)","DOI":"10.1109\/ICRA.2015.7139618"},{"key":"2135_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zheng, Y., Qi, D., Li, R., Yi, X.: Dnn-based prediction model for spatio-temporal data. In: Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, p.\u00a092. ACM (2016)","DOI":"10.1145\/2996913.2997016"},{"key":"2135_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zheng, Y., Qi, D.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10735"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02135-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02135-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02135-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T18:02:32Z","timestamp":1698948152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02135-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,24]]},"references-count":48,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["2135"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02135-0","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2021,4,24]]},"assertion":[{"value":"7 April 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}