{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T07:00:57Z","timestamp":1769065257461,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T00:00:00Z","timestamp":1674518400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T00:00:00Z","timestamp":1674518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61262016"],"award-info":[{"award-number":["61262016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51668043"],"award-info":[{"award-number":["51668043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["62166025"],"award-info":[{"award-number":["62166025"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013077","name":"National Science and Technology Planning Project","doi-asserted-by":"publisher","award":["21YF5GA073"],"award-info":[{"award-number":["21YF5GA073"]}],"id":[{"id":"10.13039\/501100013077","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s11042-023-14355-8","type":"journal-article","created":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T11:03:58Z","timestamp":1674558238000},"page":"20251-20268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Research on human behavior recognition in video based on 3DCCA"],"prefix":"10.1007","volume":"82","author":[{"given":"Hong","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8497-2824","authenticated-orcid":false,"given":"Juan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Weijie","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,24]]},"reference":[{"key":"14355_CR1","unstructured":"Action recognition. UCF101: a large human motion database (n.d.). https:\/\/www.crcv.ucf.edu\/data\/UCF101.php"},{"key":"14355_CR2","unstructured":"Action recognition. HMDB: a large human motion database (n.d.). http:\/\/serre-lab.clps.brown.edu\/resource\/hmdb-a-large-human-motion-database\/"},{"key":"14355_CR3","doi-asserted-by":"crossref","unstructured":"Cai Z, Wang L, Peng X, et al, \u201cMulti-view super vector for action recognition,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 596\u2013603, Columbus, OH, USA, June 2014.","DOI":"10.1109\/CVPR.2014.83"},{"key":"14355_CR4","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308, Honolulu, HI, USA","DOI":"10.1109\/CVPR.2017.502"},{"key":"14355_CR5","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1109\/TIP.2017.2778563","volume":"27","author":"W Du","year":"2018","unstructured":"Du W, Wang Y, Qia Y (2018) Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans Image Process 27:1347\u20131360","journal-title":"IEEE Trans Image Process"},{"key":"14355_CR6","volume-title":"T-VLAD: temporal vector of locally aggregated descriptor for Multiview human action recognition","author":"A Hbn","year":"2021","unstructured":"Hbn A, Fmb C, Mhya C et al (2021) T-VLAD: temporal vector of locally aggregated descriptor for Multiview human action recognition. Pattern Recognition Letters"},{"key":"14355_CR7","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.ins.2020.01.002","volume":"517","author":"YL Hsueh","year":"2020","unstructured":"Hsueh YL, Lie WN, Guo GY (2020) Human Behavior Recognition from Multiview Videos. Inf Sci 517:275\u2013296","journal-title":"Inf Sci"},{"key":"14355_CR8","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.patrec.2018.10.011","volume":"130","author":"H Hu","year":"2020","unstructured":"Hu H, Cheng K, Li Z, Chen J, Hu H (2020) Workflow recognition with structured two-stream convolutional networks. Pattern Recogn Lett 130:267\u2013274","journal-title":"Pattern Recogn Lett"},{"issue":"1","key":"14355_CR9","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1109\/JBHI.2019.2909688","volume":"24","author":"J Huang","year":"2020","unstructured":"Huang J, Lin S, Wang N, Dai G, Xie Y, Zhou J (2020) TSE-CNN: a two-stage end-to-end CNN for human activity recognition. IEEE J Biomed Health Inform 24(1):292\u2013299","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"14355_CR10","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji S, Xu W, Yang M, Yu K (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"14355_CR11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.20306\/kces.2020.30.5.55","volume":"25","author":"JH Kim","year":"2020","unstructured":"Kim JH, Cho YI (2020) A new residual attention network based on attention models for human action recognition in video. J Korea Soc Comp Inform 25(1):55\u201361","journal-title":"J Korea Soc Comp Inform"},{"key":"14355_CR12","doi-asserted-by":"crossref","unstructured":"Klaser A, Marszalek M, Schmid C (2008) A Spatio-Temporal Descriptor Based on 3D-Gradients. In: Proceedings of the 19th British Machine Vision Conference, pp. 1\u201310, Leeds, United Kingdom","DOI":"10.5244\/C.22.99"},{"issue":"3","key":"14355_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I (2005) On space-time interest points. Int J Comput Vis 64(3):107\u2013123","journal-title":"Int J Comput Vis"},{"issue":"1","key":"14355_CR14","first-page":"35","volume":"27","author":"R Li","year":"2014","unstructured":"Li R, Wang L, Wang K (2014) A review of research on human movement and behavior recognition. Pattern Recogn Artif Intell 27(1):35\u201348","journal-title":"Pattern Recogn Artif Intell"},{"key":"14355_CR15","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li Z, Gavrilyuk K, Gavves E, Jain M, Snoek CGM (2018) VideoLSTM convolves, attends and flows for action recognition, Comput. Vis Image Underst 166:41\u201350","journal-title":"Vis Image Underst"},{"key":"14355_CR16","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1016\/j.neucom.2018.10.104","volume":"396","author":"D Liciotti","year":"2020","unstructured":"Liciotti D, Bernardini M, Romeo L, Frontoni E (2020) A sequential deep learning application for recognising human activities in smart homes. Neurocomputing 396:501\u2013513","journal-title":"Neurocomputing"},{"issue":"3","key":"14355_CR17","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TCSVT.2018.2808685","volume":"29","author":"Y Peng","year":"2019","unstructured":"Peng Y, Zhao Y, Zhang J (2019) Two-stream collaborative learning with spatialtemporal attention for video classification. IEEE Trans Circuits Syst Video Technol 29(3):773\u2013786","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"14355_CR18","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Mei T (2017) Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541, Venice, Italy","DOI":"10.1109\/ICCV.2017.590"},{"key":"14355_CR19","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM International Conference on Multimedia, pp. 357\u2013360, Augsburg, Germany","DOI":"10.1145\/1291233.1291311"},{"key":"14355_CR20","volume-title":"Action recognition using visual attention","author":"S Sharma","year":"2015","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention. CoRR"},{"key":"14355_CR21","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Proceedings of the 28th Neural Information Processing Systems, pp. 568\u2013576, Montreal, Canada"},{"key":"14355_CR22","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, et al (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497, Santiago, Chile","DOI":"10.1109\/ICCV.2015.510"},{"issue":"3","key":"14355_CR23","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1109\/TCSVT.2018.2816960","volume":"29","author":"NA Tu","year":"2019","unstructured":"Tu NA, Huynh-The T, Khan KU, Lee YK (2019) ML-HDP: a hierarchical Bayesian nonparametric model for recognizing human actionsin video. IEEE Trans Circuits Syst for Video Technol 29(3):800\u2013814","journal-title":"IEEE Trans Circuits Syst for Video Technol"},{"key":"14355_CR24","first-page":"1","volume":"120","author":"L Wang","year":"2018","unstructured":"Wang L (2018) Three-dimensional convolutional restricted Boltzmann machine for human behavior recognition from RGB-D video. EURASIP J Image Video Process 120:1\u201311","journal-title":"EURASIP J Image Video Process"},{"key":"14355_CR25","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558, Sydney, Australia","DOI":"10.1109\/ICCV.2013.441"},{"key":"14355_CR26","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, et al (2016) Temporal segment networks: Towards good practices for deep action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 20\u201336, Springer, Cham","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"14355_CR27","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J Y, et al (2018) CBAM: Convolutional Block Attention Module. In: Proceedings of the European Conference on Computer Vision, pp. 3\u201319, Springer, Cham","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"14355_CR28","first-page":"1","volume":"40","author":"F Yao","year":"2020","unstructured":"Yao F (2020) Deep learning analysis of human behaviour recognition based on convolutional neural network analysis. Behav Inform Technol 40:1\u20139","journal-title":"Behav Inform Technol"},{"key":"14355_CR29","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","volume":"118","author":"G Yao","year":"2019","unstructured":"Yao G, Lei T, Zhong J (2019) A review of Convolutional-neural-network-based action recognition. Pattern Recogn Lett 118:14\u201322","journal-title":"Pattern Recogn Lett"},{"key":"14355_CR30","doi-asserted-by":"crossref","unstructured":"Ye Q, Liang Z, Zhong H, et al (2022) \u201cHuman behavior recognition based on time correlation sampling two-stream heterogeneous grafting network,\u201d in Optik - International Journal for Light and Electron Optics, vol. 251, Elsevier,168402","DOI":"10.1016\/j.ijleo.2021.168402"},{"issue":"2\u20134","key":"14355_CR31","first-page":"375","volume":"126","author":"S Yeung","year":"2015","unstructured":"Yeung S, Russakovsky O, Jin N et al (2015) Every moment counts: dense detailed labeling of actions in complex videos. Int J Comput Vis 126(2\u20134):375\u2013389","journal-title":"Int J Comput Vis"},{"key":"14355_CR32","doi-asserted-by":"crossref","unstructured":"T. Yu, C. Guo, L. Wang, et al, \u201cJoint spatial-temporal attention for action recognition,\u201d Pattern Recognit, Lett, vol. 112, pp. 226\u2013233, 2018.","DOI":"10.1016\/j.patrec.2018.07.034"},{"key":"14355_CR33","doi-asserted-by":"publisher","first-page":"1840","DOI":"10.1109\/ACCESS.2019.2962284","volume":"8","author":"S Yu","year":"2020","unstructured":"Yu S, Xie L, Liu L, Xia D (2020) Learning long-term temporal features with deep neural networks for human action recognition. IEEE Access 8:1840\u20131850","journal-title":"IEEE Access"},{"key":"14355_CR34","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, et al (2015) Beyond short snippets: Deep networks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4694\u20134702, Boston, MA, USA","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"14355_CR35","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.patcog.2019.01.027","volume":"90","author":"J Zhang","year":"2019","unstructured":"Zhang J, Hu H (2019) Domain learning joint with semantic adaptation for human action recognition. Pattern Recogn 90:196\u2013209","journal-title":"Pattern Recogn"},{"issue":"5","key":"14355_CR36","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang B, Wang L, Wang Z, Qiao Y, Wang H (May 2018) Real-time action recognition with deeply transferred motion vector CNNS. IEEE TransImage Process 27(5):2326\u20132339","journal-title":"IEEE TransImage Process"},{"key":"14355_CR37","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.sigpro.2017.12.008","volume":"145","author":"M Zhang","year":"2018","unstructured":"Zhang M, Yang Y, Ji Y, Xie N, Shen F (2018) Recurrent attention network using spatial-temporal relations for action recognition. Proceed Signal Process 145:137\u2013145","journal-title":"Proceed Signal Process"},{"key":"14355_CR38","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.sigpro.2017.12.008","volume":"145","author":"M Zhang","year":"2018","unstructured":"Zhang M, Yang Y, Ji Y, Xie N, Shen F (2018) Recurrent attention network using spatial-temporal relations for action recognition. Signal Process 145:137\u2013145","journal-title":"Signal Process"},{"issue":"3","key":"14355_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3321511","volume":"15","author":"J Zhang","year":"2019","unstructured":"Zhang J, Hu H, Lu X (2019) Moving foreground-aware visual attention and key volume mining for human action recognition. ACM Trans Multimedia Comput Commun Appl 15(3):1\u201316","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"key":"14355_CR40","doi-asserted-by":"crossref","unstructured":"Zufan Zhang, Zongming Lv, Chenquan Gan et al, \u201cHuman action recognition using convolutional LSTM and fully-connected LSTM with different attentions,\u201d in Proceedings of the Neurocomputing, vol. 410, pp. 304\u2013316, 2020.","DOI":"10.1016\/j.neucom.2020.06.032"},{"issue":"8","key":"14355_CR41","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1109\/TCSVT.2017.2682196","volume":"28","author":"S Zhao","year":"2018","unstructured":"Zhao S, Liu Y, Han Y, Hong R, Hu Q, Tian Q (2018) Pooling the convolutional layers in deep convNets for video action recognition. Proceed IEEE Trans, Circuits Syst, VideoTechnol 28(8):1839\u20131849","journal-title":"Proceed IEEE Trans, Circuits Syst, VideoTechnol"},{"key":"14355_CR42","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.imavis.2016.06.007","volume":"55","author":"F Zhu","year":"2016","unstructured":"Zhu F, Shao L, Xie J, Fang Y (2016) From handcrafted to learned representations for human action recognition: a survey. Image Vis Comput 55:42\u201352","journal-title":"Image Vis Comput"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14355-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14355-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14355-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,22]],"date-time":"2023-04-22T04:23:33Z","timestamp":1682137413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14355-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,24]]},"references-count":42,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["14355"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14355-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,24]]},"assertion":[{"value":"11 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2023","order":4,"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 there are no conflicts of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}