{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:33:44Z","timestamp":1769819624491,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T00:00:00Z","timestamp":1620000000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T00:00:00Z","timestamp":1620000000000},"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":["Appl Intell"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s10489-021-02367-6","type":"journal-article","created":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T10:02:58Z","timestamp":1620036178000},"page":"452-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Linear dynamical systems approach for human action recognition with dual-stream deep features"],"prefix":"10.1007","volume":"52","author":[{"given":"Zhouning","family":"Du","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6740-7102","authenticated-orcid":false,"given":"Hiroaki","family":"Mukaidani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,3]]},"reference":[{"key":"2367_CR1","doi-asserted-by":"crossref","unstructured":"Du Z, Mukaidani H, Saravanakumar R (2020) Action recognition based on linear dynamical systems with deep features in videos. In: Proceedings of the IEEE international conference on systems, man, and cybernetics, pp 2634\u20132639. IEEE","DOI":"10.1109\/SMC42975.2020.9283429"},{"key":"2367_CR2","unstructured":"Simonyan K, Zisserman A (2014) Two\u2013stream convolutional networks for action recognition in videos. In: Proceedings of the advances in neural information processing systems, pp 568\u2013576"},{"key":"2367_CR3","doi-asserted-by":"crossref","unstructured":"Huang Q, Sun S, Wang F (2017) A compact pairwise trajectory representation for action recognition. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp 1767\u20131771. IEEE","DOI":"10.1109\/ICASSP.2017.7952460"},{"key":"2367_CR4","doi-asserted-by":"crossref","unstructured":"Duta IC, Nguyen TA, Aizawa K, Ionescu B, Sebe N (2016) Boosting vlad with double assignment using deep features for action recognition in videos. In: Proceedings of the 23rd international conference on pattern recognition, pp 2210\u20132215. IEEE","DOI":"10.1109\/ICPR.2016.7899964"},{"key":"2367_CR5","doi-asserted-by":"crossref","unstructured":"Sun L, Jia K, Yeung DY, Shi BE (2015) Human action recognition using factorized spatio\u2013temporal convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4597\u20134605. IEEE","DOI":"10.1109\/ICCV.2015.522"},{"key":"2367_CR6","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6450\u20136459 IEEE","DOI":"10.1109\/CVPR.2018.00675"},{"key":"2367_CR7","doi-asserted-by":"crossref","unstructured":"Zhou Y, Sun X, Zha ZJ, Zeng W (2018) Mict: Mixed 3d\/2d convolutional tube for human action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 449\u2013458 IEEE","DOI":"10.1109\/CVPR.2018.00054"},{"key":"2367_CR8","doi-asserted-by":"crossref","unstructured":"Liu K, Liu W, Gan C, Tan M, Ma H (2018) T\u2013c3d: Temporal convolutional 3d network for real\u2013time action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.12333"},{"key":"2367_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2018.07.028","volume":"85","author":"H Yang","year":"2019","unstructured":"Yang H, Yuan C, Li B, Du Y, Xing J, Hu W, Maybank SJ (2019) Asymmetric 3d convolutional neural networks for action recognition. Pattern Recognit 85:1\u201312","journal-title":"Pattern Recognit"},{"issue":"12","key":"2367_CR10","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1109\/TCSVT.2016.2576761","volume":"27","author":"P Wang","year":"2016","unstructured":"Wang P, Cao Y, Shen C, Liu L, Shen HT (2016) Temporal pyramid pooling\u2013based convolutional neural network for action recognition. IEEE Transactions on Circuits and Systems for Video Technology 27 (12):2613\u20132622","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2367_CR11","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large\u2013scale image recognition. In: Proceedings of the international conference on learning representations"},{"key":"2367_CR12","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A, Vadis Q (2018) Action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4724\u20134733 IEEE","DOI":"10.1109\/CVPR.2017.502"},{"issue":"2","key":"2367_CR13","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/A:1021669406132","volume":"51","author":"G Doretto","year":"2003","unstructured":"Doretto G, Chiuso A, Wu YN, Soatto S (2003) Dynamic textures. Int J Comput Vis 51(2):91\u2013109","journal-title":"Int J Comput Vis"},{"issue":"2","key":"2367_CR14","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1109\/TPAMI.2012.83","volume":"35","author":"A Ravichandran","year":"2012","unstructured":"Ravichandran A, Chaudhry R, Vidal R (2012) Categorizing dynamic textures using a bag of dynamical systems. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(2):342\u2013353","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2367_CR15","doi-asserted-by":"crossref","unstructured":"Vidal R, Favaro P (2007) Dynamicboost: Boosting time series generated by dynamical systems. In: Proceedings of the IEEE 11th international conference on computer vision, pp 1\u20136. IEEE","DOI":"10.1109\/ICCV.2007.4408847"},{"key":"2367_CR16","doi-asserted-by":"crossref","unstructured":"Luo G, Hu W (2013) Learning silhouette dynamics for human action recognition. In: Proceedings of the IEEE international conference on image processing, pp 2832\u20132836. IEEE","DOI":"10.1109\/ICIP.2013.6738583"},{"key":"2367_CR17","doi-asserted-by":"publisher","first-page":"3052","DOI":"10.1109\/TIP.2019.2955561","volume":"29","author":"G Luo","year":"2019","unstructured":"Luo G, Wei J, Hu W, Maybank SJ (2019) Tangent fisher vector on matrix manifolds for action recognition. IEEE Trans Image Process 29:3052\u20133064","journal-title":"IEEE Trans Image Process"},{"key":"2367_CR18","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3\u2013dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM international conference on multimedia, pp 357\u2013360","DOI":"10.1145\/1291233.1291311"},{"key":"2367_CR19","doi-asserted-by":"crossref","unstructured":"Noguchi A, Yanai K (2010) A surf\u2013based spatio-temporal feature for feature-fusion-based action recognition. In: Proceedings of the European conference on computer vision, pp 153\u2013167. Springer","DOI":"10.1007\/978-3-642-35749-7_12"},{"key":"2367_CR20","doi-asserted-by":"crossref","unstructured":"Sahoo SP, Silambarasi R, Ari S (2019) Fusion of histogram based features for human action recognition. In: Proceedings of the international conference on advanced computing & communication systems, pp 1012\u20131016. IEEE","DOI":"10.1109\/ICACCS.2019.8728473"},{"key":"2367_CR21","doi-asserted-by":"crossref","unstructured":"Xiao X, Hu H, Wang W (2017) Trajectories\u2013based motion neighborhood feature for human action recognition. In: Proceedings of the international conference on image processing, pp 4147\u20134151. IEEE","DOI":"10.1109\/ICIP.2017.8297063"},{"key":"2367_CR22","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/j.patcog.2018.04.015","volume":"81","author":"JM Carmona","year":"2018","unstructured":"Carmona JM, Climent J (2018) Human action recognition by means of subtensor projections and dense trajectories. Pattern Recogn 81:443\u2013455","journal-title":"Pattern Recogn"},{"key":"2367_CR23","doi-asserted-by":"crossref","unstructured":"Ahmed K, El-Henawy I, Mahmoud HA (2017) Action recognition technique based on fast hog3d of integral foreground snippets and random forest. In: Proceedings of the Intelligent Systems and Computer Vision, pp 1\u20137. IEEE","DOI":"10.1109\/ISACV.2017.8054899"},{"key":"2367_CR24","doi-asserted-by":"crossref","unstructured":"Liu J, Huang Y, Peng X, Wang L (2015) Multi\u2013view descriptor mining via codeword net for action recognition. In: Proceedings of the IEEE International Conference on Image Processing, pp 793\u2013797. IEEE","DOI":"10.1109\/ICIP.2015.7350908"},{"key":"2367_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","volume":"150","author":"X Peng","year":"2016","unstructured":"Peng X, Wang L, Wang X, Qiao Y (2016) Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice. Comput Vis Image Underst 150:109\u2013125","journal-title":"Comput Vis Image Underst"},{"key":"2367_CR26","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.sigpro.2015.10.035","volume":"124","author":"Y Yang","year":"2016","unstructured":"Yang Y, Liu R, Deng C, Gao X (2016) Multi\u2013task human action recognition via exploring supercategory. Signal Process 124:36\u201344","journal-title":"Signal Process"},{"issue":"3","key":"2367_CR27","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang H, Oneata D, Verbeek J, Schmid C (2016) A robust and efficient video representation for action recognition. Int J Comput Vis 119(3):219\u2013238","journal-title":"Int J Comput Vis"},{"issue":"21","key":"2367_CR28","doi-asserted-by":"publisher","first-page":"22445","DOI":"10.1007\/s11042-017-4795-6","volume":"76","author":"IC Duta","year":"2017","unstructured":"Duta IC, Uijlings JR, Ionescu B, Aizawa K, Hauptmann AG, Sebe N (2017) Efficient human action recognition using histograms of motion gradients and vlad with descriptor shape information. Multimed Tools Appl 76(21):22445\u201322472","journal-title":"Multimed Tools Appl"},{"key":"2367_CR29","first-page":"190","volume":"105217","author":"L Fiorini","year":"2020","unstructured":"Fiorini L, Mancioppi G, Semeraro F, Fujita H, Cavallo F (2020) Unsupervised emotional state classification through physiological parameters for social robotics applications. Knowledge\u2013Based Systems 105217:190","journal-title":"Knowledge\u2013Based Systems"},{"issue":"6","key":"2367_CR30","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1007\/s10489-018-1347-3","volume":"49","author":"G Yao","year":"2019","unstructured":"Yao G, Lei T, Zhong J, Jiang P (2019) Learning multi\u2013temporal\u2013scale deep information for action recognition. Appl Intell 49(6):2017\u20132029","journal-title":"Appl Intell"},{"key":"2367_CR31","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patrec.2020.04.031","volume":"135","author":"SR Mishra","year":"2020","unstructured":"Mishra SR, Mishra TK, Sanyal G, Sarkar A, Satapathy SC (2020) Real time human action recognition using triggered frame extraction and a typical cnn heuristic. Pattern Recogn Lett 135:329\u2013336","journal-title":"Pattern Recogn Lett"},{"key":"2367_CR32","doi-asserted-by":"crossref","unstructured":"Sun L, Jia K, Chen K, Yeung DY, Shi BE, Savarese S (2017) Lattice long short\u2013term memory for human action recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2147\u20132156","DOI":"10.1109\/ICCV.2017.236"},{"key":"2367_CR33","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.neucom.2018.10.095","volume":"396","author":"M Majd","year":"2020","unstructured":"Majd M, Safabakhsh R (2020) Correlational convolutional lstm for human action recognition. Neurocomputing 396:224\u2013229","journal-title":"Neurocomputing"},{"key":"2367_CR34","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1109\/ACCESS.2017.2778011","volume":"6","author":"A Ullah","year":"2017","unstructured":"Ullah A, Ahmad J, Muhammad K, Sajjad M, Baik SW (2017) Action recognition in video sequences using deep bi\u2013directional lstm with cnn features. IEEE Access 6:1155\u20131166","journal-title":"IEEE Access"},{"key":"2367_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2020.11.012","volume":"141","author":"A Stergiou","year":"2020","unstructured":"Stergiou A, Poppe R (2020) Learn to cycle: Time\u2013consistent feature discovery for action recognition. Pattern Recogn Lett 141:1\u20137","journal-title":"Pattern Recogn Lett"},{"key":"2367_CR36","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1016\/j.neucom.2020.06.032","volume":"410","author":"Z Zhang","year":"2020","unstructured":"Zhang Z, Lv Z, Gan C, Zhu Q (2020) Human action recognition using convolutional lstm and fullyconnected lstm with different attentions. Neurocomputing 410:304\u2013316","journal-title":"Neurocomputing"},{"key":"2367_CR37","doi-asserted-by":"crossref","unstructured":"Gammulle H, Denman S, Sridharan S, Fookes C (2017) Two stream lstm: a deep fusion framework for human action recognition. In: Proceedings of the IEEE winter conference on applications of computer vision, pp 177\u2013186. IEEE","DOI":"10.1109\/WACV.2017.27"},{"key":"2367_CR38","first-page":"35","volume":"100204","author":"B Garcia-Garcia","year":"2020","unstructured":"Garcia-Garcia B, Bouwmans T, Silva AJR (2020) Background subtraction in real applications: Challenges, current models and future directions. Comp Sci Rev 100204:35","journal-title":"Comp Sci Rev"},{"key":"2367_CR39","doi-asserted-by":"crossref","unstructured":"Li L, Prakash BA, Faloutsos C (2010) Parsimonious linear fingerprinting for time series. In: Proceedings of the VLDB endowment 3(1)","DOI":"10.14778\/1920841.1920893"},{"issue":"5","key":"2367_CR40","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2013","unstructured":"Reddy KK, Shah M (2013) Recognizing 50 human action categories of web videos. Mach Vis Appl 24(5):971\u2013981","journal-title":"Mach Vis Appl"},{"key":"2367_CR41","unstructured":"Soomro K, Zamir AR, Shah M (2012) A dataset of 101 human action classes from videos in the wild Center for Research in Computer Vision 2(11)"},{"key":"2367_CR42","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) Hmdb: a large video database for human motion recognition. In: Proceedings of the international conference on computer vision, pp 2556\u20132563. IEEE","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2367_CR43","doi-asserted-by":"crossref","unstructured":"Klaser A (2008) Marsza\u0142ek, M., Schmid, C.: A spatio\u2013temporal descriptor based on 3d\u2013gradients. In: Proceedings of the 19th British machine vision conference, pp 275:1\u201310. British Machine Vision Association","DOI":"10.5244\/C.22.99"},{"key":"2367_CR44","doi-asserted-by":"crossref","unstructured":"Shu Y, Shi Y, Wang Y, Zou Y, Yuan Q, Tian Y (2018) Odn: Opening the deep network for open\u2013set action recognition. In: Proceedings of the IEEE international conference on multimedia and expo, pp 1\u20136. IEEE","DOI":"10.1109\/ICME.2018.8486601"},{"issue":"1","key":"2367_CR45","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s11063-018-9932-3","volume":"50","author":"H Hu","year":"2019","unstructured":"Hu H, Liao Z, Xiao X (2019) Action recognition using multiple pooling strategies of cnn features. Neural Process Lett 50(1):379\u2013396","journal-title":"Neural Process Lett"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02367-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02367-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02367-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T06:20:17Z","timestamp":1672035617000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02367-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,3]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["2367"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02367-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,3]]},"assertion":[{"value":"17 March 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}