{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:37:01Z","timestamp":1777127821211,"version":"3.51.4"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"IITP","award":["2014-0-00077"],"award-info":[{"award-number":["2014-0-00077"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s10489-021-02487-z","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T06:20:54Z","timestamp":1623219654000},"page":"2317-2331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Predictively encoded graph convolutional network for noise-robust skeleton-based action recognition"],"prefix":"10.1007","volume":"52","author":[{"given":"Yongsang","family":"Yoon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongmin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2775-7789","authenticated-orcid":false,"given":"Moongu","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,9]]},"reference":[{"issue":"8","key":"2487_CR1","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.1002\/j.1538-7305.1970.tb04297.x","volume":"49","author":"BS Atal","year":"1970","unstructured":"Atal BS, Schroeder MR (1970) Adaptive predictive coding of speech signals. Bell Syst Technic J 49(8):1973\u20131986","journal-title":"Bell Syst Technic J"},{"issue":"12","key":"2487_CR2","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Machine Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"issue":"4","key":"2487_CR3","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/TNN.2007.912312","volume":"19","author":"Y Bengio","year":"2008","unstructured":"Bengio Y, Sen\u00e9cal JS (2008) Adaptive importance sampling to accelerate training of a neural probabilistic language model. IEEE Trans Neural Netw 19(4):713\u2013722","journal-title":"IEEE Trans Neural Netw"},{"key":"2487_CR4","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, Wei SE, Sheikh Y (2017) Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7291\u20137299","DOI":"10.1109\/CVPR.2017.143"},{"key":"2487_CR5","doi-asserted-by":"crossref","unstructured":"Cao Z, Hidalgo G, Simon T, Wei SE, Sheikh Y (2018) Openpose: Realtime multi-person 2d pose estimation using part affinity fields. arXiv:181208008","DOI":"10.1109\/CVPR.2017.143"},{"key":"2487_CR6","unstructured":"Cao Z, Hidalgo Martinez G, Simon T, Wei S, Sheikh YA (2019) Openpose: Realtime multi-person 2d pose estimation using part affinity fields. IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2487_CR7","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:14123555"},{"key":"2487_CR8","doi-asserted-by":"crossref","unstructured":"Ding Z, Wang P, Ogunbona PO, Li W (2017) Investigation of different skeleton features for cnn-based 3d action recognition. In: 2017 IEEE International conference on multimedia & expo workshops (ICMEW). IEEE, pp 617\u2013622","DOI":"10.1109\/ICMEW.2017.8026286"},{"key":"2487_CR9","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"},{"issue":"1","key":"2487_CR10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TIT.1955.1055126","volume":"1","author":"P Elias","year":"1955","unstructured":"Elias P (1955) Predictive coding\u2013i. IRE Trans Inform Theory 1 (1):16\u201324. https:\/\/doi.org\/10.1109\/TIT.1955.1055126","journal-title":"IRE Trans Inform Theory"},{"key":"2487_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.213"},{"key":"2487_CR12","doi-asserted-by":"crossref","unstructured":"Fernando B, Gavves E, Oramas JM, Ghodrati A, Tuytelaars T (2015) Modeling video evolution for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5378\u20135387","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"2487_CR13","doi-asserted-by":"crossref","unstructured":"Gao T, Packer B, Koller D (2011) A segmentation-aware object detection model with occlusion handling. In: CVPR 2011. IEEE, pp 1361\u20131368","DOI":"10.1109\/CVPR.2011.5995623"},{"key":"2487_CR14","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TIP.2020.3038372","volume":"30","author":"Z Gao","year":"2020","unstructured":"Gao Z, Guo L, Guan W, Liu AA, Ren T, Chen S (2020a) A pairwise attentive adversarial spatiotemporal network for cross-domain few-shot action recognition-r2. IEEE Trans Image Process 30:767\u2013782","journal-title":"IEEE Trans Image Process"},{"key":"2487_CR15","doi-asserted-by":"crossref","unstructured":"Gao Z, Guo L, Ren T, Liu AA, Cheng ZY, Chen S (2020b) Pairwise two-stream convnets for cross-domain action recognition with small data. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2020.3041018"},{"key":"2487_CR16","doi-asserted-by":"crossref","unstructured":"Girdhar R, Ramanan D, Gupta A, Sivic J, Russell B (2017) Actionvlad: Learning spatio-temporal aggregation for action classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 971\u2013980","DOI":"10.1109\/CVPR.2017.337"},{"key":"2487_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u2013 1448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2487_CR18","unstructured":"Gutmann M, Hyv\u00e4rinen A (2010) Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 297\u2013304"},{"key":"2487_CR19","doi-asserted-by":"crossref","unstructured":"Hussain M, Chen D, Cheng A, Wei H, Stanley D (2013) Change detection from remotely sensed images: From pixel-based to object-based approaches. In: ISPRS Journal of photogrammetry and remote sensing, vol 80, pp 91\u2013106","DOI":"10.1016\/j.isprsjprs.2013.03.006"},{"key":"2487_CR20","unstructured":"Jozefowicz R, Vinyals O, Schuster M, Shazeer N, Wu Y (2016) Exploring the limits of language modeling. arXiv:160202410"},{"key":"2487_CR21","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev P, et al. (2017) The kinetics human action video dataset. arXiv:170506950"},{"key":"2487_CR22","doi-asserted-by":"crossref","unstructured":"Ke Q, Bennamoun M, An S, Sohel F, Boussaid F (2017) 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","DOI":"10.1109\/CVPR.2017.486"},{"key":"2487_CR23","doi-asserted-by":"crossref","unstructured":"Kim TS, Reiter A (2017) Interpretable 3d human action analysis with temporal convolutional networks. In: 2017 IEEE Conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 1623\u20131631","DOI":"10.1109\/CVPRW.2017.207"},{"key":"2487_CR24","unstructured":"Li B, Dai Y, Cheng X, Chen H, Lin Y, He M (2017) Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn. In: 2017 IEEE International conference on multimedia & expo workshops (ICMEW). IEEE, pp 601\u2013604"},{"key":"2487_CR25","doi-asserted-by":"crossref","unstructured":"Li M, Chen S, Chen X, Zhang Y, Wang Y, Tian Q (2019) Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3595\u20133603","DOI":"10.1109\/CVPR.2019.00371"},{"issue":"45","key":"2487_CR26","doi-asserted-by":"publisher","first-page":"34011","DOI":"10.1007\/s11042-020-09248-z","volume":"79","author":"YM Li","year":"2020","unstructured":"Li YM, Gao Z, Tao YB, Wang LL, Xue YB (2020) 3d object retrieval based on non-local graph neural networks. Multimed Tools Appl 79(45):34011\u201334027","journal-title":"Multimed Tools Appl"},{"key":"2487_CR27","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. Springer, pp 816\u2013833","DOI":"10.1007\/978-3-319-46487-9_50"},{"issue":"4","key":"2487_CR28","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","volume":"27","author":"J Liu","year":"2017","unstructured":"Liu J, Wang G, Duan LY, Abdiyeva K, Kot AC (2017a) Skeleton-based human action recognition with global context-aware attention lstm networks. IEEE Trans Image Process 27(4):1586\u20131599","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"2487_CR29","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1007\/s11263-019-01192-2","volume":"127","author":"J Liu","year":"2019","unstructured":"Liu J, Rahmani H, Akhtar N, Mian A (2019) Learning human pose models from synthesized data for robust rgb-d action recognition. Int J Comput Vis 127(10):1545\u20131564","journal-title":"Int J Comput Vis"},{"key":"2487_CR30","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 Recogn 68:346\u2013362","journal-title":"Pattern Recogn"},{"key":"2487_CR31","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv:13013781"},{"key":"2487_CR32","unstructured":"Mnih A, Teh YW (2012) A fast and simple algorithm for training neural probabilistic language models. arXiv:12066426"},{"key":"2487_CR33","unstructured":"Oord Avd, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv:180703748"},{"key":"2487_CR34","doi-asserted-by":"crossref","unstructured":"Peng W, Hong X, Chen H, Zhao G (2019) Learning graph convolutional network for skeleton-based human action recognition by neural searching. arXiv:191104131","DOI":"10.1609\/aaai.v34i03.5652"},{"key":"2487_CR35","doi-asserted-by":"crossref","unstructured":"Qian R, Meng T, Gong B, Yang MH, Wang H, Belongie S, Cui Y (2020) Spatiotemporal contrastive video representation learning. arXiv:200803800","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"2487_CR36","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT, Wang G (2016) 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","DOI":"10.1109\/CVPR.2016.115"},{"key":"2487_CR37","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J, Lu H (2019a) Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7912\u20137921","DOI":"10.1109\/CVPR.2019.00810"},{"key":"2487_CR38","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J, LU H (2019b) Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. arXiv:191206971","DOI":"10.1109\/CVPR.2019.00810"},{"key":"2487_CR39","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J, Lu H (2019c) Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12026\u201312035","DOI":"10.1109\/CVPR.2019.01230"},{"key":"2487_CR40","doi-asserted-by":"crossref","unstructured":"Si C, Jing Y, Wang W, Wang L, Tan T (2018) Skeleton-based action recognition with spatial reasoning and temporal stack learning. In: Proceedings of the european conference on computer vision (ECCV), pp 103\u2013118","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"2487_CR41","doi-asserted-by":"crossref","unstructured":"Si C, Chen W, Wang W, Wang L, Tan T (2019) An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1227\u2013 1236","DOI":"10.1109\/CVPR.2019.00132"},{"key":"2487_CR42","doi-asserted-by":"crossref","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2017) An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Thirty-first AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"2487_CR43","doi-asserted-by":"crossref","unstructured":"Song YF, Zhang Z, Wang L (2019) Richly activated graph convolutional network for action recognition with incomplete skeletons. In: 2019 IEEE international conference on image processing (ICIP). IEEE, pp 1\u20135","DOI":"10.1109\/ICIP.2019.8802917"},{"key":"2487_CR44","doi-asserted-by":"publisher","unstructured":"Song YF, Zhang Z, Shan C, Wang L (2020) Stronger, faster and more explainable: A graph convolutional baseline for skeleton-based action recognition. In: Proceedings of the 28th ACM international conference on multimedia (ACMMM), association for computing machinery, New York, NY, USA, pp 1625\u20131633. https:\/\/doi.org\/10.1145\/3394171.3413802","DOI":"10.1145\/3394171.3413802"},{"key":"2487_CR45","doi-asserted-by":"crossref","unstructured":"Sultani W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"2487_CR46","doi-asserted-by":"crossref","unstructured":"Tang Y, Tian Y, Lu J, Li P, Zhou J (2018) Deep progressive reinforcement learning for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5323\u20135332","DOI":"10.1109\/CVPR.2018.00558"},{"key":"2487_CR47","unstructured":"Thakkar K, Narayanan P (2018) Part-based graph convolutional network for action recognition. arXiv:180904983"},{"issue":"1","key":"2487_CR48","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1109\/TII.2011.2172450","volume":"8","author":"C Tran","year":"2011","unstructured":"Tran C, Trivedi MM (2011) 3-d posture and gesture recognition for interactivity in smart spaces. IEEE Trans Indust Inform 8(1):178\u2013187","journal-title":"IEEE Trans Indust Inform"},{"key":"2487_CR49","doi-asserted-by":"crossref","unstructured":"Vondrick C, Pirsiavash H, Torralba A (2016) Anticipating visual representations from unlabeled video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 98\u2013 106","DOI":"10.1109\/CVPR.2016.18"},{"key":"2487_CR50","doi-asserted-by":"crossref","unstructured":"Wang C, Xu D, Zhu Y, Mart\u00edn-Mart\u00edn R, Lu C, Fei-Fei L, Savarese S (2019a) Densefusion: 6d object pose estimation by iterative dense fusion. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3343\u20133352","DOI":"10.1109\/CVPR.2019.00346"},{"key":"2487_CR51","doi-asserted-by":"crossref","unstructured":"Wang L, Koniusz P, Huynh DQ (2019b) Hallucinating idt descriptors and i3d optical flow features for action recognition with cnns. In: Proceedings of the IEEE international conference on computer vision, pp 8698\u20138708","DOI":"10.1109\/ICCV.2019.00879"},{"key":"2487_CR52","doi-asserted-by":"crossref","unstructured":"Wang X, Han TX, Yan S (2009) An hog-lbp human detector with partial occlusion handling. In: 2009 IEEE 12th international conference on computer vision. IEEE, pp 32\u201339","DOI":"10.1109\/ICCV.2009.5459207"},{"issue":"3","key":"2487_CR53","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1109\/TMM.2017.2749159","volume":"20","author":"X Wang","year":"2017","unstructured":"Wang X, Gao L, Wang P, Sun X, Liu X (2017a) Two-stream 3-d convnet fusion for action recognition in videos with arbitrary size and length. IEEE Trans Multimed 20(3):634\u2013644","journal-title":"IEEE Trans Multimed"},{"key":"2487_CR54","doi-asserted-by":"crossref","unstructured":"Wang X, Shrivastava A, Gupta A (2017b) A-fast-rcnn: Hard positive generation via adversary for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2606\u20132615","DOI":"10.1109\/CVPR.2017.324"},{"key":"2487_CR55","doi-asserted-by":"crossref","unstructured":"Xia L, Chen CC, Aggarwal JK (2012) View invariant human action recognition using histograms of 3d joints. In: 2012 IEEE computer society conference on computer vision and pattern recognition workshops. IEEE, pp 20\u201327","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"2487_CR56","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12328"},{"issue":"7","key":"2487_CR57","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1007\/s00138-018-0961-8","volume":"29","author":"J Yu","year":"2018","unstructured":"Yu J, Yow KC, Jeon M (2018) Joint representation learning of appearance and motion for abnormal event detection. Mach Vis Appl 29(7):1157\u20131170","journal-title":"Mach Vis Appl"},{"issue":"11","key":"2487_CR58","doi-asserted-by":"publisher","first-page":"4206","DOI":"10.1109\/TITS.2018.2883823","volume":"20","author":"J Yu","year":"2019","unstructured":"Yu J, Park S, Lee S, Jeon M (2019) Driver drowsiness detection using condition-adaptive representation learning framework. IEEE Trans Intell Transp Syst 20 (11):4206\u20134218. https:\/\/doi.org\/10.1109\/TITS.2018.2883823","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2487_CR59","doi-asserted-by":"crossref","unstructured":"Zhang P, Lan C, Xing J, Zeng W, Xue J, Zheng N (2017) View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: Proceedings of the IEEE international conference on computer vision, pp 2117\u2013 2126","DOI":"10.1109\/ICCV.2017.233"},{"issue":"2","key":"2487_CR60","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MMUL.2012.24","volume":"19","author":"Z Zhang","year":"2012","unstructured":"Zhang Z (2012) Microsoft kinect sensor and its effect. IEEE Multimed 19(2):4\u201310","journal-title":"IEEE Multimed"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02487-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02487-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02487-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T11:08:51Z","timestamp":1672398531000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02487-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,9]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["2487"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02487-z","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,9]]},"assertion":[{"value":"28 April 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}