{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T15:59:44Z","timestamp":1774713584830,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,9,28]],"date-time":"2014-09-28T00:00:00Z","timestamp":1411862400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2015,3]]},"DOI":"10.1007\/s13735-014-0069-5","type":"journal-article","created":{"date-parts":[[2014,9,27]],"date-time":"2014-09-27T09:26:51Z","timestamp":1411810011000},"page":"33-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":76,"title":["Video classification with Densely extracted HOG\/HOF\/MBH features: an evaluation of the accuracy\/computational efficiency trade-off"],"prefix":"10.1007","volume":"4","author":[{"given":"J.","family":"Uijlings","sequence":"first","affiliation":[]},{"given":"I. C.","family":"Duta","sequence":"additional","affiliation":[]},{"given":"E.","family":"Sangineto","sequence":"additional","affiliation":[]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,9,28]]},"reference":[{"key":"69_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107 R, Zisserman A (2012) Three things everyone should know to improve object retrieval. In: CVPR","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"69_CR2","doi-asserted-by":"crossref","unstructured":"Baker S, Scharstein D, Lewis JP, Roth S, Black MJ, Szeliski R (2011) A database and evaluation methodology for optical flow. Int J Comput Vis 92:1\u201331","DOI":"10.1007\/s11263-010-0390-2"},{"key":"69_CR3","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay H, Ess A, Tuytelaars T, Van L (2008) Speeded-Up Robust Features (SURF). Comput Vis Image Underst 110:346\u2013359","journal-title":"Comput Vis Image Underst"},{"issue":"1","key":"69_CR4","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"key":"69_CR5","doi-asserted-by":"crossref","unstructured":"Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. In: ECCV, pp 25\u201336","DOI":"10.1007\/978-3-540-24673-2_3"},{"issue":"3","key":"69_CR6","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","volume":"33","author":"T Brox","year":"2011","unstructured":"Brox T, Malik J (2011) Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500\u2013513","journal-title":"PAMI"},{"key":"69_CR7","doi-asserted-by":"crossref","unstructured":"Butler DJ, Wulff J, Stanley GB, Black MJ (2012) A naturalistic open source movie for optical flow evaluation. In: ECCV","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"69_CR8","doi-asserted-by":"crossref","unstructured":"Chang C-C, Lin C-J (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol. http:\/\/www.csie.ntu.edu.tw\/cjlin\/libsvm","DOI":"10.1145\/1961189.1961199"},{"key":"69_CR9","doi-asserted-by":"crossref","unstructured":"Chatfield K, Lempitsky V, Vedaldi A, Zisserman A (2011) The devil is in the details: an evaluation of recent feature encoding methods. In: BMVC","DOI":"10.5244\/C.25.76"},{"key":"69_CR10","unstructured":"Csurka G, Dance CR, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In: ECCV international workshop on statistical learning in computer vision, Prague"},{"key":"69_CR11","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: CVPR","DOI":"10.1109\/CVPR.2005.177"},{"key":"69_CR12","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. In: ECCV","DOI":"10.1007\/11744047_33"},{"key":"69_CR13","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features. In: VS-PETS","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"69_CR14","doi-asserted-by":"crossref","unstructured":"Everts I, van Gemert J, Gevers T (2013) Evaluation of color STIPs for human action recognition. In: CVPR","DOI":"10.1109\/CVPR.2013.367"},{"key":"69_CR15","doi-asserted-by":"crossref","unstructured":"Farneb\u00e4ck G (2003) Two-frame motion estimation based on polynomial expansion. In: Scandinavian conference on image analysis","DOI":"10.1007\/3-540-45103-X_50"},{"issue":"1","key":"69_CR16","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3\u201342","journal-title":"Mach Learn"},{"key":"69_CR17","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"B Horn","year":"1981","unstructured":"Horn B, Schunck B (1981) Determining optical flow. Artif Intell 17:185\u2013203","journal-title":"Artif Intell"},{"key":"69_CR18","unstructured":"Jaakkola T, Haussler D (1999) Exploiting generative models in discriminative classifiers. In: NIPS"},{"key":"69_CR19","doi-asserted-by":"crossref","unstructured":"J\u00e9gou H, Douze M, Schmid C, P\u00e9rez P (2010) Aggregating local descriptors into a compact image representation. In: CVPR, pp 3304\u20133311","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"69_CR20","doi-asserted-by":"crossref","unstructured":"Jurie F, Triggs B (2005) Creating efficient codebooks for visual recognition. In: ICCV","DOI":"10.1109\/ICCV.2005.66"},{"key":"69_CR21","doi-asserted-by":"crossref","unstructured":"Karaman S, Seidenari L, Bagdanov A, del Bimbo A (2013) L1-regularized logistic regression stacking and transductive CRF smoothing for action recognition in video. In: ICCV workshop on action recognition with a large number of classes","DOI":"10.5244\/C.28.112"},{"key":"69_CR22","doi-asserted-by":"crossref","unstructured":"Kl\u00e4ser A, Marszalek M, Schmid C (2008) A spatio-temporal descriptor based on 3d-gradients. In: BMVC","DOI":"10.5244\/C.22.99"},{"key":"69_CR23","doi-asserted-by":"crossref","unstructured":"Kliper-Gross O, Gurovich Y, Hassner T, Wolf L (2012) Motion interchange patterns for action recognition in unconstrained videos. In: ECCV","DOI":"10.1007\/978-3-642-33783-3_19"},{"key":"69_CR24","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: ICCV","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"69_CR25","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: CVPR","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"69_CR26","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Spatial pyramid matching for recognizing natural scene categories. In: CVPR. Beyond Bags of Features"},{"key":"69_CR27","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. IJCV 60:91\u2013110","journal-title":"IJCV"},{"key":"69_CR28","unstructured":"Lucas B, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: International joint conference on artificial intelligence"},{"key":"69_CR29","doi-asserted-by":"crossref","unstructured":"Maji S, Berg AC, Malik J (2008) Classification using intersection kernel support vector machines is efficient. In: CVPR","DOI":"10.1109\/CVPR.2008.4587630"},{"key":"69_CR30","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1109\/TPAMI.2007.70822","volume":"9","author":"F Moosmann","year":"2008","unstructured":"Moosmann F, Nowak E, Jurie F (2008) Randomized clustering forests for image classification. IEEE Trans Pattern Anal Mach Intell 9:1632\u20131646","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"69_CR31","doi-asserted-by":"crossref","unstructured":"Perronnin F, Sanchez J, Mensink T (2010) Improving the Fisher kernel for large-scale image classification. In: ECCV","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"69_CR32","doi-asserted-by":"crossref","unstructured":"Reddy K, Shah M (2013) Recognizing 50 human action categories of web videos. Mach Vis Appl 24(5):971\u2013981","DOI":"10.1007\/s00138-012-0450-4"},{"issue":"3","key":"69_CR33","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez J, Perronnin F, Mensink T, Verbeek JJ (2013) Image classification with the fisher vector: theory and practice. Int J Comput Vis 105(3):222\u2013245","journal-title":"Int J Comput Vis"},{"key":"69_CR34","doi-asserted-by":"crossref","unstructured":"Sangineto E (2013) Pose and expression independent facial landmark localization using dense-SURF and the Hausdorff distance. IEEE Trans Pattern Anal Mach Intell 35(3):624\u2013638","DOI":"10.1109\/TPAMI.2012.87"},{"key":"69_CR35","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local svm approach. In: ICIP","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"69_CR36","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: ACM MM","DOI":"10.1145\/1291233.1291311"},{"key":"69_CR37","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. In: ICCV","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"69_CR38","doi-asserted-by":"crossref","unstructured":"Smeaton AF, Over P, Kraaij W (2006) Evaluation campaigns and TRECVID. In: ACM SIGMM international workshop on multimedia information retrieval (MIR)","DOI":"10.1145\/1178677.1178722"},{"key":"69_CR39","doi-asserted-by":"crossref","unstructured":"Snoek CGM, Worring M, Gemert J, Geusebroek J, Smeulders A (2006) The challenge problem for automated detection of 101 semantic concepts in multimedia. In: ACM MM","DOI":"10.1145\/1180639.1180727"},{"key":"69_CR40","doi-asserted-by":"crossref","unstructured":"Solmaz B, Assari SM, Shah M (2013) Classifying web videos using a global video descriptor. Mach Vis Appl 24(7):1473\u20131485","DOI":"10.1007\/s00138-012-0449-x"},{"key":"69_CR41","doi-asserted-by":"crossref","unstructured":"Sun D, Roth S, Black M (2014) A quantitative analysis of current practices in optical flow estimation and the principles behind them. Int J Comput Vis 106:115\u2013137","DOI":"10.1007\/s11263-013-0644-x"},{"key":"69_CR42","doi-asserted-by":"crossref","unstructured":"Uijlings JRR, Smeulders AWM, Scha RJH (2010) Real-time visual concept classification. IEEE Trans Multimed 12(7):665\u2013681","DOI":"10.1109\/TMM.2010.2052027"},{"key":"69_CR43","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Fulkerson B (2010) VLFeat\u2014an open and portable library of computer vision algorithms. In: ACM MM","DOI":"10.1145\/1873951.1874249"},{"key":"69_CR44","first-page":"511","volume":"1","author":"P Viola","year":"2001","unstructured":"Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. Proc CVPR 1:511\u2013518","journal-title":"Proc CVPR"},{"key":"69_CR45","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Kl\u00e4ser A, Schmid C, Liu C (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103:60\u201379","journal-title":"Int J Comput Vis"},{"key":"69_CR46","doi-asserted-by":"crossref","unstructured":"Wang H, Ullah M, Kl\u00e4ser A, Laptev I, Schmid C (2009) Evaluation of local spatio-temporal features for action recognition. In: BMVC","DOI":"10.5244\/C.23.124"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-014-0069-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13735-014-0069-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-014-0069-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,15]],"date-time":"2019-08-15T14:04:07Z","timestamp":1565877847000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13735-014-0069-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9,28]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,3]]}},"alternative-id":["69"],"URL":"https:\/\/doi.org\/10.1007\/s13735-014-0069-5","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,9,28]]}}}