{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:38:23Z","timestamp":1761061103853,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"crossref","award":["KQTD20140630150243062"],"award-info":[{"award-number":["KQTD20140630150243062"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11263-020-01354-7","type":"journal-article","created":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T08:43:07Z","timestamp":1596271387000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["View Transfer on Human Skeleton Pose: Automatically Disentangle the View-Variant and View-Invariant Information for Pose Representation Learning"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2778-4058","authenticated-orcid":false,"given":"Qiang","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3625-6679","authenticated-orcid":false,"given":"Yunhui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,1]]},"reference":[{"issue":"8","key":"1354_CR1","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798\u20131828.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Caetano, C., Br\u00e9mond, F., & Schwartz, W. R. (2019). Skeleton image representation for 3D action recognition based on tree structure and reference joints. In 2019 32nd SIBGRAPI conference on graphics, patterns and images (SIBGRAPI) (pp. 16\u201323). IEEE.","key":"1354_CR2","DOI":"10.1109\/SIBGRAPI.2019.00011"},{"doi-asserted-by":"crossref","unstructured":"Demisse, G. G., Papadopoulos, K., Aouada, D., & Ottersten, B. (2018). Pose encoding for robust skeleton-based action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp 188\u2013194).","key":"1354_CR3","DOI":"10.1109\/CVPRW.2018.00056"},{"key":"1354_CR4","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.patcog.2017.12.004","volume":"77","author":"W Ding","year":"2018","unstructured":"Ding, W., Liu, K., Belyaev, E., & Cheng, F. (2018). Tensor-based linear dynamical systems for action recognition from 3D skeletons. Pattern Recognition, 77, 75\u201386.","journal-title":"Pattern Recognition"},{"unstructured":"Du, Y., Wang, W., & Wang, L. (2015). Hierarchical recurrent neural network for skeleton based action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1110\u20131118).","key":"1354_CR5"},{"doi-asserted-by":"crossref","unstructured":"Holden, D., Saito, J., Komura, T., & Joyce, T. (2015). Learning motion manifolds with convolutional autoencoders. In SIGGRAPH Asia 2015 Technical Briefs (pp 1\u20134).","key":"1354_CR6","DOI":"10.1145\/2820903.2820918"},{"doi-asserted-by":"crossref","unstructured":"Huang, Z., Wan, C., Probst, T., & Van\u00a0Gool, L. (2017). Deep learning on lie groups for skeleton-based action recognition. In Proceedings of the 2017 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6099\u20136108). IEEE Computer Society.","key":"1354_CR7","DOI":"10.1109\/CVPR.2017.137"},{"key":"1354_CR8","first-page":"2466","volume":"13","author":"ME Hussein","year":"2013","unstructured":"Hussein, M. E., Torki, M., Gowayyed, M. A., & El-Saban, M. (2013). Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations. IJCAI, 13, 2466\u20132472.","journal-title":"IJCAI"},{"unstructured":"Irsoy, O., & Cardie, C. (2014). Deep recursive neural networks for compositionality in language. In Advances in neural information processing systems (pp. 2096\u2013210).","key":"1354_CR9"},{"issue":"2","key":"1354_CR10","doi-asserted-by":"publisher","first-page":"201","DOI":"10.3758\/BF03212378","volume":"14","author":"G Johansson","year":"1973","unstructured":"Johansson, G. (1973). Visual perception of biological motion and a model for its analysis. Perception & Psychophysics, 14(2), 201\u2013211.","journal-title":"Perception & Psychophysics"},{"issue":"6","key":"1354_CR11","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/LSP.2017.2690339","volume":"24","author":"Q Ke","year":"2017","unstructured":"Ke, Q., An, S., Bennamoun, M., Sohel, F., & Boussaid, F. (2017a). Skeletonnet: Mining deep part features for 3-d action recognition. IEEE Signal Processing Letters, 24(6), 731\u2013735.","journal-title":"IEEE Signal Processing Letters"},{"doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., & Boussaid, F. (2017b). A new representation of skeleton sequences for 3d action recognition. In 2017 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4570\u20134579). IEEE.","key":"1354_CR12","DOI":"10.1109\/CVPR.2017.486"},{"doi-asserted-by":"crossref","unstructured":"Kundu, J. N., Gor, M., Uppala, P. K., & Radhakrishnan, V. B. (2019). Unsupervised feature learning of human actions as trajectories in pose embedding manifold. In 2019 IEEE winter conference on applications of computer vision (WACV) (pp. 1459\u20131467). IEEE.","key":"1354_CR13","DOI":"10.1109\/WACV.2019.00160"},{"issue":"5","key":"1354_CR14","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/LSP.2017.2678539","volume":"24","author":"C Li","year":"2017","unstructured":"Li, C., Hou, Y., Wang, P., & Li, W. (2017). Joint distance maps based action recognition with convolutional neural networks. IEEE Signal Processing Letters, 24(5), 624\u2013628.","journal-title":"IEEE Signal Processing Letters"},{"unstructured":"Li, J., Wong, Y., Zhao, Q., & Kankanhalli, M. (2018). Unsupervised learning of view-invariant action representations. In Advances in neural information processing systems (pp. 1254\u20131264).","key":"1354_CR15"},{"unstructured":"Liao, S., Lyons, T., Yang, W., & Ni, H. (2019). Learning stochastic differential equations using rnn with log signature features. arXiv preprint arXiv:1908.08286.","key":"1354_CR16"},{"doi-asserted-by":"publisher","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L. Y., & Kot, A. C. (2019). NTU RGB+D 120: A large-scale benchmark for 3D human activity understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2019.2916873.","key":"1354_CR17","DOI":"10.1109\/TPAMI.2019.2916873"},{"doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Wang, G., Duan, L. Y., & Chichung, A. K. (2019b). Skeleton-based online action prediction using scale selection network. IEEE Transactions on Pattern Analysis and Machine Intelligence.","key":"1354_CR18","DOI":"10.1109\/TPAMI.2019.2898954"},{"issue":"12","key":"1354_CR19","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1109\/TPAMI.2017.2771306","volume":"40","author":"J Liu","year":"2017","unstructured":"Liu, J., Shahroudy, A., Xu, D., Kot, A. C., & Wang, G. (2017a). Skeleton-based action recognition using spatio-temporal lstm network with trust gates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 3007\u20133021.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Xu, D., & Wang, G. (2016). Spatio-temporal LSTM with trust gates for 3D human action recognition. In European conference on computer vision (pp. 816\u2013833). Berlin: Springer.","key":"1354_CR20","DOI":"10.1007\/978-3-319-46487-9_50"},{"issue":"4","key":"1354_CR21","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","volume":"27","author":"J Liu","year":"2018","unstructured":"Liu, J., Wang, G., Duan, L. Y., Abdiyeva, K., & Kot, A. C. (2018). Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Transactions on Image Processing, 27(4), 1586\u20131599.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1354_CR22","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu, M., Liu, H., & Chen, C. (2017b). Enhanced skeleton visualization for view invariant human action recognition. Pattern Recognition, 68, 346\u2013362.","journal-title":"Pattern Recognition"},{"doi-asserted-by":"crossref","unstructured":"Luo, Z., Peng, B., Huang, D. A., Alahi, A., & Fei-Fei, L. (2017). Unsupervised learning of long-term motion dynamics for videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2203\u20132212).","key":"1354_CR23","DOI":"10.1109\/CVPR.2017.751"},{"doi-asserted-by":"crossref","unstructured":"Moreno-Noguer, F. (2017). 3D human pose estimation from a single image via distance matrix regression. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2823\u20132832).","key":"1354_CR24","DOI":"10.1109\/CVPR.2017.170"},{"issue":"8","key":"1354_CR25","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. (2019). View-invariant human action recognition based on a 3D bio-constrained skeleton model. IEEE Transactions on Image Processing., 28(8), 3959\u20133972.","journal-title":"IEEE Transactions on Image Processing."},{"unstructured":"Papadopoulos, K., Ghorbel, E., Aouada, D., & Ottersten, B. (2019). Vertex feature encoding and hierarchical temporal modeling in a spatial-temporal graph convolutional network for action recognition. arXiv preprint arXiv:1912.09745.","key":"1354_CR26"},{"issue":"12","key":"1354_CR27","doi-asserted-by":"publisher","first-page":"2430","DOI":"10.1109\/TPAMI.2016.2533389","volume":"38","author":"H Rahmani","year":"2016","unstructured":"Rahmani, H., Mahmood, A., Huynh, D., & Mian, A. (2016). Histogram of oriented principal components for cross-view action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(12), 2430\u20132443.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Ramakrishna, V., Kanade, T., & Sheikh, Y. (2012). Reconstructing 3D human pose from 2D image landmarks. In European conference on computer vision (pp. 573\u2013586). Berlin: Springer.","key":"1354_CR28","DOI":"10.1007\/978-3-642-33765-9_41"},{"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.","key":"1354_CR29","DOI":"10.1109\/CVPR.2016.115"},{"unstructured":"Socher, R., Lin, C. C., Manning, C., & Ng, A. Y. (2011). Parsing natural scenes and natural language with recursive neural networks. In Proceedings of the 28th international conference on machine learning (ICML-11) (pp. 129\u2013136).","key":"1354_CR30"},{"unstructured":"Socher, R., Manning, C. D., & Ng, A. Y. (2010). Learning continuous phrase representations and syntactic parsing with recursive neural networks. In: Proceedings of the NIPS-2010 deep learning and unsupervised feature learning workshop (Vol. 2010, pp. 1\u20139).","key":"1354_CR31"},{"unstructured":"Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013). Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 conference on empirical methods in natural language processing (pp. 1631\u20131642).","key":"1354_CR32"},{"doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., & Wei, Y. (2017). Compositional human pose regression. In Proceedings of the IEEE international conference on computer vision (pp. 2602\u20132611).","key":"1354_CR33","DOI":"10.1109\/ICCV.2017.284"},{"doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., & Chellappa, R. (2014). Human action recognition by representing 3D skeletons as points in a lie group. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 588\u2013595).","key":"1354_CR34","DOI":"10.1109\/CVPR.2014.82"},{"issue":"Dec","key":"1354_CR35","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P. A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11(Dec), 3371\u20133408.","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"crossref","unstructured":"Wang, H., & Wang, L. (2017). Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In e Conference on computer vision and pattern recognition (CVPR).","key":"1354_CR36","DOI":"10.1109\/CVPR.2017.387"},{"key":"1354_CR37","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.patcog.2018.03.030","volume":"81","author":"H Wang","year":"2018","unstructured":"Wang, H., & Wang, L. (2018). Learning content and style: Joint action recognition and person identification from human skeletons. Pattern Recognition, 81, 23\u201335.","journal-title":"Pattern Recognition"},{"issue":"5","key":"1354_CR38","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/TPAMI.2013.198","volume":"36","author":"J Wang","year":"2013","unstructured":"Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2013). Learning actionlet ensemble for 3D human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5), 914\u2013927.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"1354_CR39","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/TPAMI.2013.198","volume":"36","author":"J Wang","year":"2014","unstructured":"Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2014a). Learning actionlet ensemble for 3D human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5), 914\u2013927.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., & Zhu, S. C. (2014b). Cross-view action modeling, learning and recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2649\u20132656).","key":"1354_CR40","DOI":"10.1109\/CVPR.2014.339"},{"doi-asserted-by":"crossref","unstructured":"Wei, S., Song, Y., & Zhang, Y. (2017). Human skeleton tree recurrent neural network with joint relative motion feature for skeleton based action recognition. In 2017 IEEE international conference on image processing (ICIP) (pp. 91\u201395). IEEE.","key":"1354_CR41","DOI":"10.1109\/ICIP.2017.8296249"},{"doi-asserted-by":"crossref","unstructured":"Xia, L., Chen, C. C., & Aggarwal, J. (2012). View invariant human action recognition using histograms of 3D joints. In 2012 IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW) (pp. 20\u201327). IEEE.","key":"1354_CR42","DOI":"10.1109\/CVPRW.2012.6239233"},{"doi-asserted-by":"crossref","unstructured":"Yang, X., & Tian, Y. L. (2012). Eigenjoints-based action recognition using naive-bayes-nearest-neighbor. In 2012 IEEE computer society conference on Computer vision and pattern recognition workshops (CVPRW) (pp. 14\u201319). IEEE.","key":"1354_CR43","DOI":"10.1109\/CVPRW.2012.6239232"},{"unstructured":"Yoshiyasu, Y., Sagawa, R., Ayusawa, K., & Murai, A. (2018). Skeleton transformer networks: 3D human pose and skinned mesh from single RGB image. arXiv preprint arXiv:1812.11328.","key":"1354_CR44"},{"doi-asserted-by":"crossref","unstructured":"Yu, T. H., Kim, T. K., & Cipolla, R. (2013). Unconstrained monocular 3D human pose estimation by action detection and cross-modality regression forest. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3642\u20133649).","key":"1354_CR45","DOI":"10.1109\/CVPR.2013.467"},{"issue":"8","key":"1354_CR46","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1109\/TPAMI.2019.2896631","volume":"41","author":"P Zhang","year":"2019","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., & Zheng, N. (2019). View adaptive neural networks for high performance skeleton-based human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence., 41(8), 1963\u20131978.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., & Gong, Z. (2018). Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In Thirty-Second AAAI conference on artificial intelligence.","key":"1354_CR47","DOI":"10.1609\/aaai.v32i1.11853"},{"unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., & Wei, Y. (2017). Weaklysupervised transfer for 3D human pose estimation in the wild. In IEEE international conference on computer vision, ICCV (vol. 3, p. 7).","key":"1354_CR48"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01354-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01354-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01354-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T11:20:51Z","timestamp":1667647251000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01354-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,1]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["1354"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01354-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2020,8,1]]},"assertion":[{"value":"23 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}