{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:06:12Z","timestamp":1753887972036,"version":"3.41.2"},"reference-count":20,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T00:00:00Z","timestamp":1613174400000},"content-version":"vor","delay-in-days":43,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2019CFC850"],"award-info":[{"award-number":["2019CFC850"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61761044"],"award-info":[{"award-number":["61761044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015744","name":"Jingchu University of Technology","doi-asserted-by":"publisher","award":["PY201904"],"award-info":[{"award-number":["PY201904"]}],"id":[{"id":"10.13039\/501100015744","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Current methods of chaos\u2010based action recognition in videos are limited to the artificial feature causing the low recognition accuracy. In this paper, we improve ChaosNet to the deep neural network and apply it to action recognition. First, we extend ChaosNet to deep ChaosNet for extracting action features. Then, we send the features to the low\u2010level LSTM encoder and high\u2010level LSTM encoder for obtaining low\u2010level coding output and high\u2010level coding results, respectively. The agent is a behavior recognizer for producing recognition results. The manager is a hidden layer, responsible for giving behavioral segmentation targets at the high level. Our experiments are executed on two standard action datasets: UCF101 and HMDB51. The experimental results show that the proposed algorithm outperforms the state of the art.<\/jats:p>","DOI":"10.1155\/2021\/6634156","type":"journal-article","created":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T04:55:08Z","timestamp":1613278508000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep ChaosNet for Action Recognition in Videos"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2816-1020","authenticated-orcid":false,"given":"Huafeng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maosheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengming","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,2,13]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_2_9_1_2","DOI":"10.1109\/tpami.2016.2533388"},{"doi-asserted-by":"publisher","key":"e_1_2_9_2_2","DOI":"10.1007\/s11263-012-0594-8"},{"doi-asserted-by":"crossref","unstructured":"AliS. BasharatA. andShahM. Chaotic invariants for human action recognition Proceedings of the 2007 IEEE 11th International Conference on Computer Vision October 2007 Rio De Janeiro Brazi IEEE 1\u20138.","key":"e_1_2_9_3_2","DOI":"10.1109\/ICCV.2007.4409046"},{"doi-asserted-by":"publisher","key":"e_1_2_9_4_2","DOI":"10.1007\/s11771-013-1841-z"},{"doi-asserted-by":"publisher","key":"e_1_2_9_5_2","DOI":"10.1109\/34.910878"},{"doi-asserted-by":"publisher","key":"e_1_2_9_6_2","DOI":"10.1007\/978-3-540-88693-8_60"},{"key":"e_1_2_9_7_2","first-page":"288","article-title":"Human action recognition in videos using kinematic features and multiple instance learning","volume":"32","author":"Ali S.","year":"2008","journal-title":"Institute of Electrical and Electronics Engineers Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"LaptevI. MarszalekM. SchmidC. andRozenfeldB. Learning realistic human actions from movies Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition June 2008 Anchorage AK USA IEEE 1\u20138.","key":"e_1_2_9_8_2","DOI":"10.1109\/CVPR.2008.4587756"},{"volume-title":"Mosift: Recognizing Human Actions in Surveillance Videos","year":"2009","author":"Chen M.-y.","key":"e_1_2_9_9_2"},{"doi-asserted-by":"crossref","unstructured":"ChenH. ChenJ. LiH. XuZ. andHuR. Compressed-domain based camera motion estimation for realtime action recognition Proceedings of the Pacific Rim Conference on Multimedia November 2006 Hangzhou China Springer 85\u201394.","key":"e_1_2_9_10_2","DOI":"10.1007\/978-3-319-24075-6_9"},{"doi-asserted-by":"crossref","unstructured":"WangH. Kl\u00e4serA. SchmidC. andLiuC.-L. Action recognition by dense trajectories Proceedings of the CVPR 2011 June 2011 Colorado Springs CO USA IEEE 3169\u20133176.","key":"e_1_2_9_11_2","DOI":"10.1109\/CVPR.2011.5995407"},{"unstructured":"SunS. KuangZ. ShengL. OuyangW. andZhangW. Optical flow guided feature: a fast and robust motion representation for video action recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 1994 Seattle WA USA 1390\u20131399.","key":"e_1_2_9_12_2"},{"unstructured":"WuZ. WangX. JiangY.-G. YeH. andXueX. Modeling spatial-temporal clues in a hybrid deep learning framework for video classification Proceedings of the 23rd ACM International Conference on Multimedia July 2017 Brisbane Australia 461\u2013470.","key":"e_1_2_9_13_2"},{"unstructured":"DonahueJ. Anne HendricksL. GuadarramaS.et al. Long-term recurrent convolutional networks for visual recognition and description Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 1994 Seattle WA USA 2625\u20132634.","key":"e_1_2_9_14_2"},{"unstructured":"WangL. QiaoY. TangX. andVan GoolL. Actionness estimation using hybrid fully convolutional networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 1994 Seattle WA USA 2708\u20132717.","key":"e_1_2_9_15_2"},{"doi-asserted-by":"publisher","key":"e_1_2_9_16_2","DOI":"10.1109\/cc.2017.7868164"},{"doi-asserted-by":"publisher","key":"e_1_2_9_17_2","DOI":"10.1063\/1.5120831"},{"unstructured":"SoomroK. ZamirA. R. andShahM. Ucf101: a dataset of 101 human actions classes from videos in the wild 2012 https:\/\/arxiv.org\/abs\/1212.0402.","key":"e_1_2_9_18_2"},{"doi-asserted-by":"crossref","unstructured":"KuehneH. JhuangH. GarroteE. PoggioT. andSerreT. Hmdb: a large video database for human motion recognition Proceedings of the 2011 International Conference on Computer Vision November 2011 Barcelona Spain IEEE 2556\u20132563.","key":"e_1_2_9_19_2","DOI":"10.1109\/ICCV.2011.6126543"},{"unstructured":"WangX. ChenW. WuJ. WangY. F. andWangW. Y. Video captioning via hierarchical reinforcement learning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA.","key":"e_1_2_9_20_2"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/6634156.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/6634156.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/6634156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T21:24:12Z","timestamp":1723238652000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/6634156"}},"subtitle":[],"editor":[{"given":"Zhouchao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/6634156"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6634156","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"type":"print","value":"1076-2787"},{"type":"electronic","value":"1099-0526"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-10-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6634156"}}