{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:03:27Z","timestamp":1785211407730,"version":"3.55.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2017,5,13]],"date-time":"2017-05-13T00:00:00Z","timestamp":1494633600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s11042-017-4795-6","type":"journal-article","created":{"date-parts":[[2017,5,12]],"date-time":"2017-05-12T18:44:34Z","timestamp":1494614674000},"page":"22445-22472","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Efficient human action recognition using histograms of motion gradients and VLAD with descriptor shape information"],"prefix":"10.1007","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4009-8922","authenticated-orcid":false,"given":"Ionut C.","family":"Duta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasper R.","family":"R. Uijlings","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bogdan","family":"Ionescu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiyoharu","family":"Aizawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"G. Hauptmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,5,13]]},"reference":[{"key":"4795_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":"4795_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic R, Zisserman A (2013) All about VLAD. In: CVPR","DOI":"10.1109\/CVPR.2013.207"},{"key":"4795_CR3","doi-asserted-by":"crossref","unstructured":"Bilen H, Fernando B, Gavves E, Vedaldi A, Gould S (2016) Dynamic image networks for action recognition. In: CVPR","DOI":"10.1109\/CVPR.2016.331"},{"issue":"1","key":"4795_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"},{"issue":"3","key":"4795_CR5","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. TPAMI 33(3):500\u2013513","journal-title":"TPAMI"},{"key":"4795_CR6","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","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"4795_CR7","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":"4795_CR8","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":"4795_CR9","doi-asserted-by":"crossref","unstructured":"de Souza CR, Gaidon A, Vig E, L\u00f3pez AM (2016) Sympathy for the details: Dense trajectories and hybrid classification architectures for action recognition. In: ECCV","DOI":"10.1007\/978-3-319-46478-7_43"},{"key":"4795_CR10","doi-asserted-by":"crossref","unstructured":"Duta IC, Nguyen TA, Aizawa K, Ionescu B, Sebe N (2016) Boosting VLAD with double assignment using deep features for action recognition in videos. In: ICPR","DOI":"10.1109\/ICPR.2016.7899964"},{"key":"4795_CR11","doi-asserted-by":"crossref","unstructured":"Duta IC, Uijlings JRR, Nguyen TA, Aizawa K, Hauptmann AG, Ionescu B, Sebe N (2016) Histograms of motion gradients for real-time video classification. In: CBMI","DOI":"10.1109\/CBMI.2016.7500260"},{"key":"4795_CR12","doi-asserted-by":"crossref","unstructured":"Duta IC, Ionescu B, Aizawa K, Sebe N (2017) Spatio-temporal VLAD encoding for human action recognition in videos. In: MMM","DOI":"10.1007\/978-3-319-51811-4_30"},{"key":"4795_CR13","doi-asserted-by":"crossref","unstructured":"Farneb\u00e4ck G. (2003) Two-frame motion estimation based on polynomial expansion. In: Image analysis, pp 363\u2013370","DOI":"10.1007\/3-540-45103-X_50"},{"key":"4795_CR14","doi-asserted-by":"crossref","unstructured":"Horn B K, Schunck BG (1981) Determining optical flow. In: 1981 Technical symposium east, pp 319\u2013331. International Society for Optics and Photonics","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"4795_CR15","doi-asserted-by":"crossref","unstructured":"Jain M, J\u00e9gou H, Bouthemy P (2013) Better exploiting motion for better action recognition. In: CVPR","DOI":"10.1109\/CVPR.2013.330"},{"issue":"9","key":"4795_CR16","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou H, Perronnin F, Douze M, Sanchez J, Perez P, Schmid C (2012) Aggregating local image descriptors into compact codes. TPAMI 34(9):1704\u20131716","journal-title":"TPAMI"},{"key":"4795_CR17","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":"4795_CR18","doi-asserted-by":"crossref","unstructured":"Kantorov V, Laptev I (2014) Efficient feature extraction, encoding and classification for action recognition. In: CVPR","DOI":"10.1109\/CVPR.2014.332"},{"key":"4795_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: CVPR","DOI":"10.1109\/CVPR.2014.223"},{"key":"4795_CR20","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":"4795_CR21","doi-asserted-by":"crossref","unstructured":"Krapac J, Verbeek J, Jurie F (2011) Modeling spatial layout with fisher vectors for image categorization. In: ICCV","DOI":"10.1109\/ICCV.2011.6126406"},{"key":"4795_CR22","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"},{"issue":"2-3","key":"4795_CR23","doi-asserted-by":"crossref","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. IJCV 64(2-3):107\u2013123","journal-title":"IJCV"},{"key":"4795_CR24","doi-asserted-by":"crossref","unstructured":"Laptev I, Marsza\u0142ek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: CVPR","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"4795_CR25","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR"},{"issue":"2","key":"4795_CR26","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe D G (2004) Distinctive image features from scale-invariant keypoints. IJCV 60(2):91\u2013110","journal-title":"IJCV"},{"key":"4795_CR27","unstructured":"Lucas BD, Kanade T et al (1981) An iterative image registration technique with an application to stereo vision. In: IJCAI"},{"key":"4795_CR28","doi-asserted-by":"crossref","unstructured":"Mironic\u0103 I, Du\u0163\u0103 I C, Ionescu B, Sebe N (2016) A modified vector of locally aggregated descriptors approach for fast video classification. Multimed Tools Appl","DOI":"10.1007\/s11042-015-2819-7"},{"key":"4795_CR29","doi-asserted-by":"crossref","unstructured":"Oneata D, Verbeek J, Schmid C (2013) Action and event recognition with fisher vectors on a compact feature set. In: ICCV","DOI":"10.1109\/ICCV.2013.228"},{"key":"4795_CR30","doi-asserted-by":"crossref","unstructured":"Park E, Han X, Berg TL, Berg AC (2016) Combining multiple sources of knowledge in deep cnns for action recognition. In: WACV","DOI":"10.1109\/WACV.2016.7477589"},{"key":"4795_CR31","unstructured":"Peng X, Wang L, Wang X, Qiao Y (2014) Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. arXiv: 1405.4506"},{"key":"4795_CR32","doi-asserted-by":"crossref","unstructured":"Peng X, Wang L, Qiao Y, Peng Q (2014) Boosting vlad with supervised dictionary learning and high-order statistics. In: ECCV","DOI":"10.1007\/978-3-319-10578-9_43"},{"key":"4795_CR33","doi-asserted-by":"crossref","unstructured":"Perronnin F, S\u00e1nchez 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":"4795_CR34","doi-asserted-by":"crossref","unstructured":"Poularakis S, Avgerinakis K, Briassouli A, Kompatsiaris I (2015) Computationally efficient recognition of activities of daily living. In: ICIP","DOI":"10.1109\/ICIP.2015.7350797"},{"issue":"5","key":"4795_CR35","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1007\/s00138-012-0450-4","volume":"24","author":"KK Reddy","year":"2013","unstructured":"Reddy K K, Shah M (2013) Recognizing 50 human action categories of web videos. Mach Vis Appl 24(5):971\u2013981","journal-title":"Mach Vis Appl"},{"key":"4795_CR36","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: NIPS"},{"key":"4795_CR37","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556"},{"key":"4795_CR38","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: Ninth international conference on computer vision, 2003 Proceedings, pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"4795_CR39","doi-asserted-by":"crossref","unstructured":"Solmaz B, Assari S M, Shah M (2013) Classifying web videos using a global video descriptor. Mach Vis Appl","DOI":"10.1007\/s00138-012-0449-x"},{"key":"4795_CR40","unstructured":"Soomro K, Zamir A R, Shah M (2012) Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv: 1212.0402"},{"key":"4795_CR41","unstructured":"Sun J, Wu X, Yan S, Cheong L-F, Chua T-S, Li J (2009) Hierarchical spatio-temporal context modeling for action recognition. In: CVPR"},{"key":"4795_CR42","doi-asserted-by":"crossref","unstructured":"Sun L, Jia K, Yeung D-Y, Shi BE (2015) Human action recognition using factorized spatio-temporal convolutional networks. In: ICCV","DOI":"10.1109\/ICCV.2015.522"},{"issue":"7","key":"4795_CR43","first-page":"665","volume":"12","author":"JR Uijlings","year":"2010","unstructured":"Uijlings J R, Smeulders A W, Scha R J (2010) Real-time visual concept classification. TMR 12(7):665\u2013 681","journal-title":"TMR"},{"key":"4795_CR44","doi-asserted-by":"crossref","unstructured":"Uijlings JRR, Duta IC, Rostamzadeh N, Sebe N (2014) Realtime video classification using dense hof\/hog. In: ICMR","DOI":"10.1145\/2578726.2578744"},{"key":"4795_CR45","doi-asserted-by":"crossref","unstructured":"Uijlings J R R, Duta I C, Sangineto E, Sebe N (2015) Video classification with densely extracted hog\/hof\/mbh features: an evaluation of the accuracy\/computational efficiency trade-off. Int J Multimed Inf Retriev","DOI":"10.1007\/s13735-014-0069-5"},{"key":"4795_CR46","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Fulkerson B (2010) Vlfeat: an open and portable library of computer vision algorithms. In: ACM Multimedia","DOI":"10.1145\/1873951.1874249"},{"key":"4795_CR47","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: ICCV","DOI":"10.1109\/ICCV.2013.441"},{"key":"4795_CR48","unstructured":"Wang H, Schmid C (2013) Lear-inria submission for the thumos workshop. In: ICCV Workshop"},{"key":"4795_CR49","doi-asserted-by":"crossref","unstructured":"Wang H, Ullah MM, Klaser A, Laptev I, Schmid C (2009) Evaluation of local spatio-temporal features for action recognition. In: BMVC","DOI":"10.5244\/C.23.124"},{"issue":"1","key":"4795_CR50","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 -L (2013) Dense trajectories and motion boundary descriptors for action recognition. IJCV 103(1):60\u201379","journal-title":"IJCV"},{"key":"4795_CR51","doi-asserted-by":"crossref","unstructured":"Wang H, Oneata D, Verbeek J, Schmid C (2015) A robust and efficient video representation for action recognition. IJCV","DOI":"10.1007\/s11263-015-0846-5"},{"key":"4795_CR52","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: ECCV","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"4795_CR53","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: deep networks for video classification. In: CVPR","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"4795_CR54","doi-asserted-by":"crossref","unstructured":"Zach C, Pock T, Bischof H (2007) A duality based approach for realtime tv-l 1 optical flow. In: Pattern recognition","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"4795_CR55","doi-asserted-by":"crossref","unstructured":"Zhou X, Yu K, Zhang T, Huang T S (2010) Image classification using super-vector coding of local image descriptors. In: Computer Vision\u2013ECCV 2010, pp 141\u2013154","DOI":"10.1007\/978-3-642-15555-0_11"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-4795-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4795-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4795-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T11:42:11Z","timestamp":1569325331000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-4795-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,13]]},"references-count":55,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["4795"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-4795-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5,13]]}}}