{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T02:16:13Z","timestamp":1726366573294},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2019,10,2]],"date-time":"2019-10-02T00:00:00Z","timestamp":1569974400000},"content-version":"am","delay-in-days":458,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Singapore Ministry of Education Academic Research Fund Tier 2","doi-asserted-by":"publisher","award":["MOE2015-T2-2-114"],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research, US","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61501198"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2014CFB461"],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Wuhan Youth Science and Technology Chenguang program","award":["2014072704011248"]},{"name":"Dutch national program COMMIT"},{"name":"Dutch NWO TOP"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1016\/j.patcog.2018.01.020","type":"journal-article","created":{"date-parts":[[2018,2,10]],"date-time":"2018-02-10T06:04:19Z","timestamp":1518242659000},"page":"32-43","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":191,"special_numbering":"C","title":["Multi-stream CNN: Learning representations based on human-related regions for action recognition"],"prefix":"10.1016","volume":"79","author":[{"given":"Zhigang","family":"Tu","sequence":"first","affiliation":[]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Qianqing","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Ronald","family":"Poppe","sequence":"additional","affiliation":[]},{"given":"Remco C.","family":"Veltkamp","sequence":"additional","affiliation":[]},{"given":"Baoxin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.patcog.2018.01.020_bib0001","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 Vis. Comput."},{"issue":"16","key":"10.1016\/j.patcog.2018.01.020_bib0002","article-title":"Human activity analysis: a review","volume":"43","author":"Aggarwal","year":"2011","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patcog.2018.01.020_bib0003","article-title":"Advances in human action recognition: a Survey","author":"Cheng","year":"2015","journal-title":"CoRR abs\/1501.05964"},{"key":"10.1016\/j.patcog.2018.01.020_bib0004","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.patcog.2017.07.013","article-title":"Human action recognition in RGB-D videos using motion sequence information and deep learning","volume":"72","author":"Ijjina","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0005","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.patcog.2017.01.015","article-title":"Learning discriminative trajectorylet detector sets for accurate skeletonbased action recognition","volume":"66","author":"Qiao","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0006","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2018.01.020_bib0007","first-page":"3218","article-title":"P-CNN: Pose-based CNN features for action recognition","author":"Cheron","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0008","article-title":"Action recognition with trajectory-pooled deep-convolutional descriptors","author":"Wang","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0009","article-title":"MSR-CNN: Applying motion salient region based descriptors for action recognition","author":"Tu","year":"2016","journal-title":"Int. Conf. Pattern Recognit. (ICPR)"},{"key":"10.1016\/j.patcog.2018.01.020_bib0010","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.patcog.2017.01.027","article-title":"Do less and achieve more: training CNNs for action recognition utilizing action images from the web","volume":"68","author":"Ma","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0011","article-title":"Long-term temporal convolutions for action recognition","author":"Varol","year":"2016","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0012","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2018.01.020_bib0013","article-title":"Finding action tubes","author":"Gkioxari","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"issue":"2","key":"10.1016\/j.patcog.2018.01.020_bib0014","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective search for object recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0015","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1016\/j.patcog.2017.06.035","article-title":"Semantic action recognition by learning a pose lexicon","volume":"72","author":"Zhoua","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0016","article-title":"Action detection by implicit intentional motion clustering","author":"Chen","year":"2015","journal-title":"Int. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0017","first-page":"1933","article-title":"Convolutional two-stream network fusion for video action recognition","author":"Feichtenhofer","year":"2016","journal-title":"Comput. Vis. Pattern Recognit."},{"issue":"10","key":"10.1016\/j.patcog.2018.01.020_bib0018","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1109\/TPAMI.2014.2314663","article-title":"Block-sparse RPCA for salient motion detection","volume":"36","author":"Gao","year":"2014","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2018.01.020_bib0019","article-title":"UCF101: A dataset of 101 human action classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"CRCVTR-12-01"},{"key":"10.1016\/j.patcog.2018.01.020_bib0020","article-title":"HMDB: a large video database for human motion recognition","author":"Kuehne","year":"2011","journal-title":"Int. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0021","first-page":"3551","article-title":"Action recognition with improved trajectories","author":"Wang","year":"2013","journal-title":"Int. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0022","article-title":"Human action recognition using factorized spatio-temporal convolutional networks","author":"Sun","year":"2015","journal-title":"Int. Conf. Comput. Vis."},{"issue":"10","key":"10.1016\/j.patcog.2018.01.020_bib0023","doi-asserted-by":"crossref","first-page":"3343","DOI":"10.1016\/j.patcog.2014.04.018","article-title":"A survey on still image based human action recognition","volume":"47","author":"Guo","year":"2014","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0024","article-title":"Learning deep features for scene recognition using places database","author":"Zhou","year":"2014","journal-title":"Neural Inf. Process. Systems, 2014"},{"key":"10.1016\/j.patcog.2018.01.020_bib0025","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0026","article-title":"Deepface: closing the gap to human-level performance in face verification","author":"Taigman","year":"2014","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0027","article-title":"Learning to track for spatio-temporal action localization","author":"Weinzaepfel","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0028","article-title":"Motion part regularization: improving action recognition via trajectory group selection","author":"Ni","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2018.01.020_bib0029","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":"Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2018.01.020_bib0030","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"Wang","year":"2016","journal-title":"Eur. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0031","article-title":"Actions and attributes from wholes and parts","author":"Gkioxari","year":"2015","journal-title":"Int. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0032","article-title":"Contextual action recognition with R*CNN","author":"Gkioxari","year":"2015","journal-title":"Int. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0033","article-title":"A multi-stream bi-directional recurrent neural network for fine-grained action detection","author":"Singh","year":"2016","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0034","article-title":"Beyond short snippets: deep networks for video classification","author":"Ng","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0035","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"Donahue","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0036","article-title":"MatConvNet: convolutional neural networks for MATLAB","author":"Vedaldi","year":"2015","journal-title":"ACM Int. Conf. Multimedia"},{"issue":"5","key":"10.1016\/j.patcog.2018.01.020_bib0037","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1016\/j.patcog.2013.11.026","article-title":"A combined post-filtering method to improve accuracy of variational optical flow estimation","volume":"47","author":"Tu","year":"2014","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0038","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"Brox","year":"2004","journal-title":"Eur. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0039","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.patcog.2018.01.020_bib0040","article-title":"Return of the devil in the details: delving deep into convolutional nets","author":"Chatfield","year":"2014","journal-title":"British Machine Vis. Conf."},{"issue":"4","key":"10.1016\/j.patcog.2018.01.020_bib0041","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.cviu.2008.11.005","article-title":"Detection and segmentation of moving objects in complex scenes","volume":"113","author":"Bugeau","year":"2009","journal-title":"Comput. Vis. Image Understand."},{"key":"10.1016\/j.patcog.2018.01.020_bib0042","article-title":"Two-stream SR-CNNs for action recognition in videos","author":"Wang","year":"2016","journal-title":"British Machine Vis. Conf."},{"issue":"3","key":"10.1016\/j.patcog.2018.01.020_bib0043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1970392.1970395","article-title":"Robust principal component analysis?","volume":"58","author":"Candes","year":"2011","journal-title":"J. ACM"},{"key":"10.1016\/j.patcog.2018.01.020_bib0044","article-title":"The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrix","author":"Lin","year":"2010","journal-title":"Math. Program."},{"issue":"8","key":"10.1016\/j.patcog.2018.01.020_bib0045","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1109\/34.868680","article-title":"Detecting salient motion by accumulating directionally-consistent flow","volume":"22","author":"Wixson","year":"2000","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2018.01.020_bib0046","article-title":"Action mach: a spatio-temporal maximum average correlation height filter for action recognition","author":"Rodriguez","year":"2008","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0047","article-title":"Towards understanding action recognition","author":"Jhuang","year":"2013","journal-title":"Int. Conf. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0048","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2018.01.020_bib0049","article-title":"Efficient feature extraction, encoding, and classification for action recognition","author":"Kantorov","year":"2014","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0050","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.patcog.2015.09.002","article-title":"Weighted local intensity fusion method for variational optical flow estimation","volume":"50","author":"Tu","year":"2016","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0051","article-title":"EpicFlow: edge-preserving interpolation of correspondences for optical flow","author":"Revaud","year":"2015","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0052","article-title":"A naturalistic open source movie for optical flow evaluation","author":"Butler","year":"2012","journal-title":"Eur. Conf. Comput. Vis."},{"issue":"1","key":"10.1016\/j.patcog.2018.01.020_bib0053","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-010-0390-2","article-title":"A database and evaluation methodology for optical flow","volume":"92","author":"Baker","year":"2011","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2018.01.020_bib0054","article-title":"Action recognition by dense trajectories","author":"Wang","year":"2011","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0055","first-page":"978","article-title":"Multilayer and multimodal fusion of deep neural networks for video classification","author":"Yang","year":"2016","journal-title":"ACM Multimedia"},{"key":"10.1016\/j.patcog.2018.01.020_bib0056","article-title":"Dynamic image networks for action recognition","author":"Bilen","year":"2016","journal-title":"Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2018.01.020_bib0057","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"Int. Conf. Machine Learn."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320318300359?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320318300359?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T11:13:16Z","timestamp":1656069196000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320318300359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":57,"alternative-id":["S0031320318300359"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2018.01.020","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2018,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-stream CNN: Learning representations based on human-related regions for action recognition","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2018.01.020","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2018 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}