{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T16:27:01Z","timestamp":1726849621315},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1016\/j.neucom.2018.06.071","type":"journal-article","created":{"date-parts":[[2018,7,17]],"date-time":"2018-07-17T19:24:25Z","timestamp":1531855465000},"page":"221-233","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":36,"special_numbering":"C","title":["Action recognition using spatial-optical data organization and sequential learning framework"],"prefix":"10.1016","volume":"315","author":[{"given":"Yuan","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7028-4956","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2018.06.071_bib0001","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.patcog.2017.03.030","article-title":"Locality constraint distance metric learning for traffic congestion detection","volume":"75","author":"Wang","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2018.06.071_bib0002","first-page":"1","article-title":"Deep metric learning for crowdedness regression","author":"Wang","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2018.06.071_bib0003","series-title":"Proceedings of the International Conference on Pattern Recognition","first-page":"4630","article-title":"Unsupervised surveillance video retrieval based on human action and appearance","author":"Ger\u00f3nimo","year":"2014"},{"key":"10.1016\/j.neucom.2018.06.071_bib0004","series-title":"Proceedings of the International Conference on Multimedia and Expo Workshops","first-page":"1","article-title":"Abnormal action warning on encrypted-coded surveillance video for home safety","author":"Zeng","year":"2013"},{"key":"10.1016\/j.neucom.2018.06.071_bib0005","series-title":"Proceedings of the International Conference on Advanced Robotics and Intelligent Systems","first-page":"1","article-title":"Robot vision to recognize both object and rotation for robot pick-and-place operation","author":"Lin","year":"2015"},{"issue":"2","key":"10.1016\/j.neucom.2018.06.071_bib0006","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1109\/TITS.2013.2247760","article-title":"Real-time detection system of driver distraction using machine learning","volume":"14","author":"Tango","year":"2013","journal-title":"IEEE Trans. Intel. Transp. Syst."},{"key":"10.1016\/j.neucom.2018.06.071_bib0007","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1016\/j.neucom.2015.05.092","article-title":"Video-based road detection via online structural learning","volume":"168","author":"Yuan","year":"2015","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2018.06.071_bib0008","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.neucom.2015.01.054","article-title":"Adaptive road detection via context-aware label transfer","volume":"158","author":"Wang","year":"2015","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.neucom.2018.06.071_bib0009","doi-asserted-by":"crossref","first-page":"1126","DOI":"10.1109\/TIP.2010.2076821","article-title":"Spatiotemporal localization and categorization of human actions in unsegmented image sequences","volume":"20","author":"Oikonomopoulos","year":"2011","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"10.1016\/j.neucom.2018.06.071_bib0010","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1109\/TIP.2014.2302677","article-title":"Evaluation of color spatio-temporal interest points for human action recognition","volume":"23","author":"Everts","year":"2014","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"10.1016\/j.neucom.2018.06.071_bib0011","doi-asserted-by":"crossref","first-page":"5701","DOI":"10.1007\/s11042-015-2536-2","article-title":"A survey on aggregating methods for action recognition with dense trajectories","volume":"75","author":"Xu","year":"2016","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.neucom.2018.06.071_bib0012","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.imavis.2017.01.010","article-title":"Going deeper into action recognition: a survey","volume":"60","author":"Herath","year":"2017","journal-title":"Image Vision Comput."},{"issue":"6","key":"10.1016\/j.neucom.2018.06.071_bib0013","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","article-title":"A survey on vision-based human action recognition","volume":"28","author":"Poppe","year":"2010","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.neucom.2018.06.071_bib0014","series-title":"Proceedings of the International Conference on Pattern Recognition","first-page":"32","article-title":"Recognizing human actions: a local SVM approach","author":"Sch\u00fcldt","year":"2004"},{"key":"10.1016\/j.neucom.2018.06.071_bib0015","series-title":"Proceedings of the International Conference on Computer Vision","first-page":"2556","article-title":"HMDB: a large video database for human motion recognition","author":"Kuehne","year":"2011"},{"key":"10.1016\/j.neucom.2018.06.071_sbref0016","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"CoRR"},{"issue":"2\u20133","key":"10.1016\/j.neucom.2018.06.071_bib0017","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","article-title":"On space-time interest points","volume":"64","author":"Laptev","year":"2005","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"10.1016\/j.neucom.2018.06.071_bib0018","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","article-title":"Dense trajectories and motion boundary descriptors for action recognition","volume":"103","author":"Wang","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2018.06.071_bib0019","series-title":"Proceedings of the IEEE China Summit & International Conference on Signal and Information Processing, ChinaSIP 2014, Xi\u2019an, China, July 9\u201313, 2014","first-page":"626","article-title":"Action recognition based on semantic feature description and cross classification","author":"Zhao","year":"2014"},{"key":"10.1016\/j.neucom.2018.06.071_bib0020","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"140","article-title":"Convolutional learning of spatio-temporal features","author":"Taylor","year":"2010"},{"issue":"1","key":"10.1016\/j.neucom.2018.06.071_bib0021","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3d convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intel."},{"key":"10.1016\/j.neucom.2018.06.071_bib0022","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"357","article-title":"A 3-dimensional sift descriptor and its application to action recognition","author":"Scovanner","year":"2007"},{"key":"10.1016\/j.neucom.2018.06.071_bib0023","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"404","article-title":"SURF: speeded up robust features","author":"Bay","year":"2006"},{"key":"10.1016\/j.neucom.2018.06.071_bib0024","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.neucom.2018.06.071_bib0025","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","article-title":"Learning realistic human actions from movies","author":"Laptev","year":"2008"},{"key":"10.1016\/j.neucom.2018.06.071_bib0026","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"Wang","year":"2013"},{"key":"10.1016\/j.neucom.2018.06.071_bib0027","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"Tran","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0028","series-title":"Advances in Neural Information Processing Systems","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.1016\/j.neucom.2018.06.071_bib0029","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"3218","article-title":"P-CNN: pose-based CNN features for action recognition","author":"Ch\u00e9ron","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0030","series-title":"Proceedings of the Fourteenth European Conference on Computer Vision","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"Wang","year":"2016"},{"key":"10.1016\/j.neucom.2018.06.071_bib0031","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4724","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira","year":"2017"},{"issue":"1","key":"10.1016\/j.neucom.2018.06.071_bib0032","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/TITS.2017.2749964","article-title":"Embedding structured contour and location prior in siamesed fully convolutional networks for road detection","volume":"19","author":"Wang","year":"2018","journal-title":"IEEE Trans. Intel. Transp. Syst."},{"issue":"8","key":"10.1016\/j.neucom.2018.06.071_bib0033","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2018.06.071_bib0034","series-title":"Proceedings of the IEEE Conference on International Conference on Computer Vision","first-page":"4041","article-title":"Differential recurrent neural networks for action recognition","author":"Veeriah","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0035","article-title":"TS-LSTM and temporal-inception: exploiting spatiotemporal dynamics for activity recognition","volume":"abs\/1703.10667","author":"Ma","year":"2017","journal-title":"CoRR"},{"issue":"8","key":"10.1016\/j.neucom.2018.06.071_bib0036","doi-asserted-by":"crossref","first-page":"3893","DOI":"10.1109\/TIP.2018.2821921","article-title":"Triplet-based deep hashing network for cross-modal retrieval","volume":"27","author":"Deng","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"10.1016\/j.neucom.2018.06.071_bib0037","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1109\/LGRS.2017.2691013","article-title":"Transfer learning with fully pretrained deep convolution networks for land-use classification","volume":"14","author":"Zhao","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.neucom.2018.06.071_bib0038","series-title":"Advances in Neural Information Processing Systems","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.neucom.2018.06.071_bib0039","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4694","article-title":"Beyond short snippets: deep networks for video classification","author":"Ng","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2625","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"Donahue","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0041","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"Srivastava","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_sbref0042","article-title":"Skeleton-based action recognition using spatio-temporal LSTM network with trust gates","author":"Liu","year":"2017","journal-title":"CoRR"},{"key":"10.1016\/j.neucom.2018.06.071_bib0043","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3054","article-title":"Regularizing long short term memory with 3d human-skeleton sequences for action recognition","author":"Mahasseni","year":"2016"},{"issue":"4","key":"10.1016\/j.neucom.2018.06.071_bib0044","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1109\/TIP.2017.2781424","article-title":"Robust object co-segmentation using background prior","volume":"27","author":"Han","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2018.06.071_bib0045","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern","first-page":"2141","article-title":"Efficient hierarchical graph-based video segmentation","author":"Grundmann","year":"2010"},{"issue":"2","key":"10.1016\/j.neucom.2018.06.071_bib0046","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","article-title":"Efficient graph-based image segmentation","volume":"59","author":"Felzenszwalb","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2018.06.071_bib0047","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1202","article-title":"Evaluation of super-voxel methods for early video processing","author":"Xu","year":"2012"},{"key":"10.1016\/j.neucom.2018.06.071_bib0048","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"593","article-title":"Good features to track","author":"Shi","year":"1994"},{"key":"10.1016\/j.neucom.2018.06.071_bib0049","series-title":"Proceedings of the Pattern Recognition Symposium","first-page":"214","article-title":"A duality based approach for realtime tv-L1optical flow","author":"Zach","year":"2007"},{"key":"10.1016\/j.neucom.2018.06.071_bib0050","series-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1494","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"Venugopalan","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0051","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"204","article-title":"Beyond Gaussian pyramid: multi-skip feature stacking for action recognition","author":"Lan","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0052","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Dynamic image networks for action recognition","author":"Bilen","year":"2016"},{"key":"10.1016\/j.neucom.2018.06.071_bib0053","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015","first-page":"4305","article-title":"Action recognition with trajectory-pooled deep-convolutional descriptors","author":"Wang","year":"2015"},{"key":"10.1016\/j.neucom.2018.06.071_bib0054","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"3","key":"10.1016\/j.neucom.2018.06.071_bib0055","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2018.06.071_bib0056","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"Feichtenhofer","year":"2016"},{"key":"10.1016\/j.neucom.2018.06.071_bib0057","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1725","article-title":"Large-scale video classification with convolutional neural networks","author":"Karpathy","year":"2014"},{"key":"10.1016\/j.neucom.2018.06.071_sbref0058","article-title":"Towards good practices for very deep two-stream convnets","author":"Wang","year":"2015","journal-title":"CoRR"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523121830849X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523121830849X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,9,12]],"date-time":"2018-09-12T18:47:21Z","timestamp":1536778041000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S092523121830849X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":58,"alternative-id":["S092523121830849X"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2018.06.071","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2018,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Action recognition using spatial-optical data organization and sequential learning framework","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2018.06.071","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2018 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}