{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:48:20Z","timestamp":1777697300712,"version":"3.51.4"},"reference-count":55,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDT"],"published-print":{"date-parts":[[2019,9,9]]},"DOI":"10.3233\/idt-180112","type":"journal-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T12:19:06Z","timestamp":1565093946000},"page":"315-327","source":"Crossref","is-referenced-by-count":3,"title":["Video summarization using sparse representation of local descriptors"],"prefix":"10.1177","volume":"13","author":[{"given":"Roya","family":"Jenabzadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alireza","family":"Behrad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"1","key":"10.3233\/IDT-180112_ref1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1198302.1198305","article-title":"Video abstraction: A systematic review and classification","volume":"3","author":"Truong","year":"2007","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"issue":"1","key":"10.3233\/IDT-180112_ref2","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s00138-013-0573-2","article-title":"Summarizing high-level scene behavior","volume":"25","author":"Streib","year":"2013","journal-title":"Machine Vision and Applications"},{"key":"10.3233\/IDT-180112_ref3","doi-asserted-by":"crossref","unstructured":"Gygli M, Grabner H, Van Gool L, editors. Video summarization by learning submodular mixtures of objectives. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015.","DOI":"10.1109\/CVPR.2015.7298928"},{"issue":"2","key":"10.3233\/IDT-180112_ref4","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/TMM.2017.2741423","article-title":"F-DES: Fast and deep event summarization","volume":"20","author":"Kumar","year":"2018","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.3233\/IDT-180112_ref5","first-page":"1","article-title":"Deep event learning boost-up approach: DELTA","author":"Kumar","year":"2018","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/IDT-180112_ref6","unstructured":"Xiaohua H, Ling J, editors. A Video summarization method based on key frames extracted by TMOF. International Conference on Image Analysis and Signal Processing (IASP); 2012."},{"key":"10.3233\/IDT-180112_ref7","unstructured":"Gong Y, Liu X, editors. Video summarization using singular value decomposition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2000."},{"issue":"1","key":"10.3233\/IDT-180112_ref8","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s11042-009-0307-7","article-title":"STIMO: STIll and MOving video storyboard for the web scenario","volume":"46","author":"Furini","year":"2010","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/IDT-180112_ref9","doi-asserted-by":"crossref","unstructured":"Majumdar j, Santhosh Kumar K, Venkatesh G, editors. Analysis of video shot detection using color layout descriptor and video summarization based on expectation-maximization clustering. International Conference on Cognitive Computing and Information Processing (CCIP) 2015.","DOI":"10.1109\/CCIP.2015.7100724"},{"key":"10.3233\/IDT-180112_ref10","doi-asserted-by":"crossref","unstructured":"Zong Z, Gong Q, editors. Key frame extraction based on dynamic color histogram and fast wavelet histogram. 2017 IEEE International Conference on Information and Automation (ICIA). 2017: IEEE.","DOI":"10.1109\/ICInfA.2017.8078903"},{"issue":"4","key":"10.3233\/IDT-180112_ref11","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1117\/1.1406508","article-title":"Evaluation of the effectiveness of color attributes for video indexing","volume":"10","author":"Chupeau","year":"2001","journal-title":"Journal of Electronic Imaging"},{"issue":"2","key":"10.3233\/IDT-180112_ref12","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s00799-005-0129-9","article-title":"Keyframe-based video summarization using Delaunay clustering","volume":"6","author":"Mundur","year":"2006","journal-title":"International Journal on Digital Libraries"},{"key":"10.3233\/IDT-180112_ref13","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.patrec.2016.01.027","article-title":"Weighted multi-view key-frame extraction","author":"Ioannidis","year":"2016","journal-title":"Pattern Recognition Letters"},{"issue":"9","key":"10.3233\/IDT-180112_ref14","doi-asserted-by":"crossref","first-page":"12097","DOI":"10.1007\/s11042-016-4061-3","article-title":"Video summarization using textual descriptions for authoring video blogs","volume":"76","author":"Otani","year":"2017","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/IDT-180112_ref15","doi-asserted-by":"crossref","unstructured":"Zhang T, Wen D, Ding X, editors. Person-based video summarization and retrieval by tracking and clustering temporal face sequences. IS&T\/SPIE Electronic Imaging; 2013: SPIE.","DOI":"10.1117\/12.2009127"},{"issue":"5","key":"10.3233\/IDT-180112_ref16","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1109\/TMM.2005.854410","article-title":"A generic framework of user attention model and its application in video summarization","volume":"7","author":"Ma","year":"2005","journal-title":"IEEE Transactions on Multimedia,"},{"issue":"3","key":"10.3233\/IDT-180112_ref17","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/s00138-004-0141-x","article-title":"Video shot characterization","volume":"15","author":"Osian","year":"2004","journal-title":"Machine Vision and Applications"},{"issue":"4","key":"10.3233\/IDT-180112_ref18","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1117\/1.1406507","article-title":"Video summarization using descriptors of motion activity: A motion activity based approach to key-frame extraction from video shots","volume":"10","author":"Divakaran","year":"2001","journal-title":"Journal of Electronic Imaging"},{"issue":"1","key":"10.3233\/IDT-180112_ref19","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","article-title":"VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method","volume":"32","author":"De Avila","year":"2011","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/IDT-180112_ref20","doi-asserted-by":"crossref","unstructured":"Furini M, Geraci F, Montangero M, Pellegrini M, editors. VISTO: Visual storyboard for web video browsing. 6th ACM International Conference on Image and Video Retrieval (CIVR\u201907); 2007.","DOI":"10.1145\/1282280.1282370"},{"key":"10.3233\/IDT-180112_ref21","first-page":"1","article-title":"A novel clustering method for static video summarization","author":"Wu","year":"2016","journal-title":"Multimedia Tools and Applications"},{"issue":"5","key":"10.3233\/IDT-180112_ref22","first-page":"1829","article-title":"Key frame extraction for video summarization using DWT wavelet statistics","volume":"2","author":"Tint","year":"2013","journal-title":"International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)"},{"key":"10.3233\/IDT-180112_ref23","doi-asserted-by":"crossref","unstructured":"Carvajal J, McCool C, Sanderson C, editors. Summarisation of short-term and long-term videos using texture and colour. IEEE Winter Conference on Applications of Computer Vision (WACV); 2014.","DOI":"10.1109\/WACV.2014.6836025"},{"key":"10.3233\/IDT-180112_ref24","doi-asserted-by":"crossref","unstructured":"Cahuina EJ, Camara CG, editors. A new method for static video summarization using local descriptors and video temporal segmentation. 26th SIBGRAPI - Conference on Graphics, Patterns and Images (SIBGRAPI); 2013.","DOI":"10.1109\/SIBGRAPI.2013.39"},{"key":"10.3233\/IDT-180112_ref25","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/978-3-642-24136-9_19","article-title":"Video summarization using a self-growing and self-organized neural gas network","author":"Papadopoulos","year":"2011","journal-title":"Computer Vision\/Computer Graphics Collaboration Techniques: Springer"},{"key":"10.3233\/IDT-180112_ref26","doi-asserted-by":"crossref","unstructured":"Mahmoud KM, Ismail MA, Ghanem NM, editors. Vscan: An enhanced video summarization using density-based spatial clustering. 17th International Conference on Image Analysis and Processing (ICIAP); 2013.","DOI":"10.1007\/978-3-642-41181-6_74"},{"issue":"3","key":"10.3233\/IDT-180112_ref27","doi-asserted-by":"crossref","first-page":"491","DOI":"10.15623\/ijret.2014.0303092","article-title":"Key frame extraction for video summarization using motion activity descriptors","volume":"3","author":"Kamoji","year":"2014","journal-title":"International Journal of Research in Engineering and Technology"},{"issue":"3","key":"10.3233\/IDT-180112_ref28","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s11042-005-0891-0","article-title":"Motion-based selection of relevant video segments for video summarization","volume":"26","author":"Peyrard","year":"2005","journal-title":"Multimedia Tools and Applications"},{"key":"10.3233\/IDT-180112_ref29","unstructured":"Li C, Wu YT, Yu SS, Chen T, editors. Motion-focusing key frame extraction and video summarization for lane surveillance system. 16th IEEE International Conference on Image Processing (ICIP); 2009."},{"key":"10.3233\/IDT-180112_ref30","doi-asserted-by":"crossref","unstructured":"Lu Z, Grauman K, editors. Story-driven summarization for egocentric video. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2013.","DOI":"10.1109\/CVPR.2013.350"},{"issue":"2","key":"10.3233\/IDT-180112_ref31","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TCSVT.2008.2009241","article-title":"Towards extracting semantically meaningful key frames from personal video clips: from humans to computers","volume":"19","author":"Luo","year":"2009","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.3233\/IDT-180112_ref32","doi-asserted-by":"crossref","unstructured":"Chakraborty S, Tickoo O, Iyer R, editors. Adaptive keyframe selection for video summarization. 2015 IEEE Winter Conference on Applications of Computer Vision (WACV); 2015: IEEE.","DOI":"10.1109\/WACV.2015.99"},{"issue":"1","key":"10.3233\/IDT-180112_ref33","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s11263-014-0794-5","article-title":"Predicting important objects for egocentric video summarization","volume":"114","author":"Lee","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/IDT-180112_ref34","doi-asserted-by":"crossref","unstructured":"Zhang K, Chao W-L, Sha F, Grauman K, editors. Video summarization with long short-term memory. European Conference on Computer Vision; 2016: Springer.","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"10.3233\/IDT-180112_ref35","doi-asserted-by":"crossref","unstructured":"Ejaz N, Khan UA, Mart\u00ednez-del-Amor MA, Sparenberg H, editors. Deep learning based beat event detection in action movie franchises. Tenth International Conference on Machine Vision; 2018: SPIE.","DOI":"10.1117\/12.2309629"},{"key":"10.3233\/IDT-180112_ref36","unstructured":"Yan X, Gilani SZ, Qin H, Feng M, Zhang L, Mian A. Deep keyframe detection in human action videos. arXiv preprint arXiv: 180410021; 2018."},{"issue":"2","key":"10.3233\/IDT-180112_ref37","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"International Journal of Computer Vision"},{"issue":"4","key":"10.3233\/IDT-180112_ref38","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1109\/TCSVT.2012.2214871","article-title":"Keypoint-based keyframe selection","volume":"23","author":"Guan","year":"2013","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"6","key":"10.3233\/IDT-180112_ref39","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1109\/TMM.2014.2319778","article-title":"A bag-of-importance model with locality-constrained coding based feature learning for video summarization","volume":"16","author":"Lu","year":"2014","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.3233\/IDT-180112_ref40","first-page":"2548","article-title":"BRISK: Binary robust invariant scalable keypoints","author":"Leutenegger","year":"2011","journal-title":"IEEE International Conference on Computer Vision (ICCV)"},{"issue":"1","key":"10.3233\/IDT-180112_ref41","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/TMM.2011.2166951","article-title":"Towards scalable summarization of consumer videos via sparse dictionary selection","volume":"14","author":"Cong","year":"2012","journal-title":"IEEE Transactions on Multimedia"},{"issue":"2","key":"10.3233\/IDT-180112_ref42","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1016\/j.patcog.2014.08.002","article-title":"Video summarization via minimum sparse reconstruction","volume":"48","author":"Mei","year":"2015","journal-title":"Pattern Recognition"},{"key":"10.3233\/IDT-180112_ref43","doi-asserted-by":"crossref","unstructured":"Kumar M, Loui AC, editors. Key frame extraction from consumer videos using sparse representation. 18th IEEE International Conference on Image Processing; 2011: IEEE.","DOI":"10.1109\/ICIP.2011.6116136"},{"issue":"12","key":"10.3233\/IDT-180112_ref44","doi-asserted-by":"crossref","first-page":"5136","DOI":"10.1109\/TIP.2013.2282081","article-title":"Fast video shot boundary detection based on SVD and pattern matching","volume":"22","author":"Lu","year":"2013","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.3233\/IDT-180112_ref45","unstructured":"Dalal N, Triggs B, editors. Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2005."},{"issue":"4","key":"10.3233\/IDT-180112_ref46","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1049\/iet-cvi:20080026","article-title":"Performance evaluation of local features in human classification and detection","volume":"2","author":"Paisitkriangkrai","year":"2008","journal-title":"IET Computer Vision"},{"key":"10.3233\/IDT-180112_ref47","unstructured":"Liang J, Ye Q, Chen J, Jiao J, editors. Evaluation of local feature descriptors and their combination for pedestrian representation. 21st International Conference on Pattern Recognition (ICPR); 2012: IEEE."},{"issue":"11","key":"10.3233\/IDT-180112_ref48","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","article-title":"SVD: An algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","author":"Aharon","year":"2006","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.3233\/IDT-180112_ref49","doi-asserted-by":"crossref","unstructured":"Lee H, Battle A, Raina R, Ng AY, editors. Efficient Sparse Coding Algorithms. Advances in Neural Information Processing Systems; 2006.","DOI":"10.7551\/mitpress\/7503.003.0105"},{"issue":"4","key":"10.3233\/IDT-180112_ref50","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"issue":"6","key":"10.3233\/IDT-180112_ref51","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Communications of the ACM"},{"issue":"388","key":"10.3233\/IDT-180112_ref52","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1080\/01621459.1984.10477105","article-title":"Least median of squares regression","volume":"79","author":"Rousseeuw","year":"1984","journal-title":"Journal of the American Statistical Association"},{"key":"10.3233\/IDT-180112_ref54","first-page":"1015","article-title":"Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation","author":"Sokolova","year":"2006","journal-title":"AI 2006: Advances in Artificial Intelligence. Lecture Notes in Computer Science"},{"key":"10.3233\/IDT-180112_ref55","doi-asserted-by":"crossref","unstructured":"Bay H, Ess A, Tuytelaars T, Van Gool L. Speeded-up robust features (SURF). Computer vision and image understanding. 2008; 110(3): 346-59.","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"10.3233\/IDT-180112_ref56","unstructured":"Krizhevsky A, Sutskever I, Hinton GE, editors. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems; 2012."}],"container-title":["Intelligent Decision Technologies"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDT-180112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:22:35Z","timestamp":1777454555000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDT-180112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,9]]},"references-count":55,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/idt-180112","relation":{},"ISSN":["1872-4981","1875-8843"],"issn-type":[{"value":"1872-4981","type":"print"},{"value":"1875-8843","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,9]]}}}