{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:13Z","timestamp":1770917233356,"version":"3.50.1"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2015,8,21]],"date-time":"2015-08-21T00:00:00Z","timestamp":1440115200000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2016,8]]},"DOI":"10.1007\/s11042-015-2819-7","type":"journal-article","created":{"date-parts":[[2015,8,20]],"date-time":"2015-08-20T05:05:21Z","timestamp":1440047121000},"page":"9045-9072","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["A modified vector of locally aggregated descriptors approach for fast video classification"],"prefix":"10.1007","volume":"75","author":[{"given":"Ionu\u0163","family":"Mironic\u0103","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ionu\u0163 Cosmin","family":"Du\u0163\u0103","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Ionescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,8,21]]},"reference":[{"key":"2819_CR1","doi-asserted-by":"crossref","unstructured":"Almeida J, Pedronette DC, Penatti OA (2014) Unsupervised Manifold Learning for Video Genre Retrieval. In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Springer International Publishing, pp 604\u2013612","DOI":"10.1007\/978-3-319-12568-8_74"},{"key":"2819_CR2","doi-asserted-by":"crossref","unstructured":"Bilinski P, Corvee E, Bak S, Bremond F (2013) Relative dense tracklets for human action recognition. In: IEEE International Conference of Automatic Face and Gesture Recognition (FG)","DOI":"10.1109\/FG.2013.6553699"},{"key":"2819_CR3","unstructured":"Bouckaert RR, Frank E, Hall M, Kirkby R, Reutemann P, Seewald A, Scuse D (2013) WEKA Manual for Version 3\u20137\u20138"},{"issue":"3","key":"2819_CR4","first-page":"416","volume":"38","author":"D Brezeale","year":"2008","unstructured":"Brezeale D, Cook DJ (2008) Automatic video classification: A survey of the literature, in Systems, Man, and Cybernetics, Part C: Applications and Reviews. IEEE Trans 38(3):416\u2013430","journal-title":"IEEE Trans"},{"issue":"1","key":"2819_CR5","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":"2819_CR6","doi-asserted-by":"crossref","unstructured":"Bosch A, Zisserman A, Munoz X (2007) Image classification using random forests and ferns. In: IEEE International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2007.4409066"},{"key":"2819_CR7","unstructured":"Csurka G, Dance CR, Fan L, Willamowski J, Bray C (2004) Visual Categorization with Bags of Keypoints, European Conference on Computer Vision (ECCV):1\u20132"},{"issue":"1","key":"2819_CR8","first-page":"1238","volume":"22","author":"DC Ciresan","year":"2011","unstructured":"Ciresan DC, Meier U, Masci J, Maria Gambardella L, Schmidhuber J (2011) Flexible, high performance convolutional neural networks for image classification. Proc-Int Joint Conf Artif Intell (IJCAI) 22(1):1238\u20131242","journal-title":"Proc-Int Joint Conf Artif Intell (IJCAI)"},{"issue":"3","key":"2819_CR9","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.cviu.2011.09.010","volume":"116","author":"B Chakraborty","year":"2012","unstructured":"Chakraborty B, Holte MB, Moeslund TB, Gonzlez J (2012) Selective spatio-temporal interest points. Computer Vision and Image Understanding 116(3):396\u2013410","journal-title":"Computer Vision and Image Understanding"},{"key":"2819_CR10","doi-asserted-by":"crossref","unstructured":"Demarty C-H, Penet C, Soleymani M, Gravier G (2013) VSD, a public dataset for the detection of violent scenes in movies: design, annotation, analysis and evaluation. Media Tools and Applications","DOI":"10.1007\/s11042-014-1984-4"},{"key":"2819_CR11","doi-asserted-by":"crossref","unstructured":"Demarty C-H, Penet C, Schedl M, Ionescu B, Quang VL, Jiang Y-G (2013) The MediaEval 2013 Affect Task: Violent Scenes Detection. Working Notes Proceedings [3]","DOI":"10.1109\/CBMI.2014.6849827"},{"key":"2819_CR12","doi-asserted-by":"crossref","unstructured":"Demarty C-H, Ionescu B, Jiang Y-G, Quang VL, Schedl M, Penet C (2014) Banchmarking Violent Scenes Detection in Movies. IEEE International Workshop on Content-Based Multimedia Indexing - CBMI","DOI":"10.1109\/CBMI.2014.6849827"},{"key":"2819_CR13","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2012) The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results, http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"2819_CR14","volume-title":"Overview of the ImageCLEF 2013 medical tasks, Working Notes of CLEF 2013","author":"A Garc\u00eda Seco De Herrera","year":"2013","unstructured":"Garc\u00eda Seco De Herrera A, Kalpathy-Cramer J, Demner Fushman D, Antani S, M\u00fcller H (2013) Overview of the ImageCLEF 2013 medical tasks, Working Notes of CLEF 2013. Cross Language Evaluation Forum, Valencia, Spain"},{"key":"2819_CR15","unstructured":"Goto S, Aoki T (2013) TUDCL at MediaEval 2013 Violent Scenes Detection: Training with Multimodal Features by MKL. Working Notes Proceedings [3]"},{"key":"2819_CR16","doi-asserted-by":"crossref","unstructured":"Gold K, Petrosino A (2010) Using information gain to build meaningful decision forests for multilabel classification. In: Development and Learning (ICDL), 2010 IEEE 9th International Conference on. IEEE, pp 58\u201363","DOI":"10.1109\/DEVLRN.2010.5578864"},{"key":"2819_CR17","unstructured":"Ionescu B, Mironic\u0103 I, Seyerlehner K, Knees P, Schluter J, Schedl M, Cucu H, Buzo A, Lambert P (2012) ARF @ mediaeval 2012: Multimodal video classification. In: MediaEval workshop"},{"key":"2819_CR18","unstructured":"Imre C, Korner J (2011) Information theory: coding theorems for discrete memoryless systems. Cambridge University Press"},{"key":"2819_CR19","unstructured":"Ikizler-Cinbis N, Sclaroff S (2011) Object, scene and actions: combining multiple features for human action recognition. In: Proceedings of the European Conference on Computer vision (ECCV), pp 494\u2013507"},{"key":"2819_CR20","unstructured":"Jiang Y-G, Liu J, Roshan Zamir A, Laptev I, Piccardi M, Shah M, Sukthankar R (2013) THUMOS challenge: Action recognition with a large number of classes, ICCV Workshop on Action Recognition with a Large Number of Classes, http:\/\/crcv.ucf.edu\/ICCV13-Action-Workshop"},{"key":"2819_CR21","doi-asserted-by":"crossref","unstructured":"Jain M, Jegou H, Bouthemy P (2013) Better exploiting motion for better action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2013.330"},{"key":"2819_CR22","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: Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"2819_CR23","doi-asserted-by":"crossref","unstructured":"Jegou H, Perronnin F, Douze M, Sanchez J, Perez P, Schmid C (2012) Aggregating local image descriptors into compact codes. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)","DOI":"10.1109\/TPAMI.2011.235"},{"key":"2819_CR24","unstructured":"Karaman S, Seidenari L, Bagdanov AD, Bagdanov A (2013) L1-regularized logistic regression stacking and transductive CRF smoothing for action recognition in video. ICCV workshop on action recognition with a large number of classes"},{"key":"2819_CR25","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fe L (2014) Large-scale video classification with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2014.223"},{"key":"2819_CR26","unstructured":"Khurram S, Zamir AR, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. CoRR. arXiv: 1212.0402"},{"key":"2819_CR27","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp 1097\u20131105"},{"key":"2819_CR28","first-page":"432","volume":"1","author":"O Ludwig","year":"2009","unstructured":"Ludwig O, Delgado D, Goncalves V, Nunes U (2009) Trainable classifier-fusion schemes: an application to pedestrian detection. IEEE Int Conf Intell Trans Syst 1:432\u2013437","journal-title":"IEEE Int Conf Intell Trans Syst"},{"key":"2819_CR29","unstructured":"Lucas B, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: Proceedings of Imaging Understanding Workshop"},{"key":"2819_CR30","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"2819_CR31","doi-asserted-by":"crossref","unstructured":"Liu J, Luo J, Shah M. (2009) Recognizing realistic actions from videos in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1996\u20132003","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"2819_CR32","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. Computer Vision and Pattern Recognition"},{"key":"2819_CR33","unstructured":"MediaEval 2013 Workshop Larson M, Anguera X, Reuter T, Jones GJF, Ionescu B, Schedl M, Piatrik T, Hauff C, Soleymani M (eds) (2013) co-located with ACM Multimedia, Barcelona, Spain, October 18-19, CEUR-WS.org, ISSN 1613-0073, Vol. 1043, http:\/\/ceur-ws.org\/Vol-1043\/"},{"key":"2819_CR34","doi-asserted-by":"crossref","unstructured":"Mironica I, Uijlings J, Rostamzadeh N, Ionescu B, Sebe N (2013) Time matters!: capturing variation in time in video using fisher kernels. In: Proceedings of the 21st ACM International Conference on Multimedia, pp 701\u2013704","DOI":"10.1145\/2502081.2502183"},{"key":"2819_CR35","doi-asserted-by":"crossref","unstructured":"Marin J, Vzquez D, Lpez AM, Amores J, Leibe B (2013) Random Forests of Local Experts for Pedestrian Detection. In: IEEE International Conference on Computer Vision (ICCV), pp 2592\u20132599","DOI":"10.1109\/ICCV.2013.322"},{"key":"2819_CR36","doi-asserted-by":"crossref","unstructured":"Messing R, Pal C, Kautz H (2009) Activity recognition using the velocity histories of tracked keypoints. In: ICCV","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"2819_CR37","unstructured":"Mathieu B, Essid S, Fillon T, Prado J, Richard G (2010) YAAFE, an Easy to Use and Efficient Audio Feature Extraction Software. Proceedings of the 11th ISMIR conference, pp 441\u2013446"},{"key":"2819_CR38","doi-asserted-by":"crossref","unstructured":"Murthy OV, Goecke R (2013) Ordered Trajectories for Large Scale Human Action Recognition. IEEE International Conference on Computer Vision","DOI":"10.1109\/ICCVW.2013.61"},{"issue":"9","key":"2819_CR39","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1109\/TPAMI.2014.2306419","volume":"36","author":"Z Ma","year":"2014","unstructured":"Ma Z, Yang Y, Sebe N, Hauptmann A (2014) Knowledge adaptation with partially shared features for event detection using few exemplars. IEEE Trans Pattern Anal Mach Intell 36(9):1789\u20131802","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2819_CR40","unstructured":"Nakayama H (2012) Aggregating Descriptors with Local Gaussian Metrics. In: proceedings of NIPS 2012 Workshop on Large Scale Visual Recognition and Retrieval"},{"key":"2819_CR41","unstructured":"Nowozin S (2012) Improved information gain estimates for decision tree induction, arXiv preprint arXiv: 1206.4620"},{"key":"2819_CR42","unstructured":"Over P, Awad G, Michel M, Fiscus J, Sanders G, Kraaij W, Smeaton AF, Qu\u00e9enot G (2013) TRECVID 2013 \u2013 An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics, Proceedings of TRECVID 2013, http:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv13.papers\/tv13overview.pdf , NIST. USA"},{"key":"2819_CR43","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. CoRR , abs\/1405.4506"},{"key":"2819_CR44","doi-asserted-by":"crossref","unstructured":"Perronnin F, Sanchez J, Mensink T. (2010) Improving the fisher kernel for large-scale image classification. In: European Conference of Computer Vision (ECCV), pp 143\u2013156","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"2819_CR45","unstructured":"Penet C, Demarty C-H, Gravier G, Gros P (2013) Technicolor\/INRIA Team at the MediaEval 2013 Violent Scenes Detection Task. Working Notes Proceedings [3]"},{"key":"2819_CR46","doi-asserted-by":"crossref","unstructured":"Picard D, Gosselin P-H. (2011) Improving image similarity with vectors of locally aggregated tensors. IEEE Image Processing (ICIP), 2011 18th IEEE International Conference on","DOI":"10.1109\/ICIP.2011.6116641"},{"key":"2819_CR47","unstructured":"Quoc V (2013) Building high-level features using large scale unsupervised learning. In: IEEE International Conference of Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"2819_CR48","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Amin S, Andriluka M, Schiele B (2012) A database for fine grained activity detection of cooking activities. In: International Conference of Computer Vision and Pattern Recognition. CVPR","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"2819_CR49","doi-asserted-by":"crossref","unstructured":"Rostamzadeh N, Zen G, Mironic I, Uijlings J, Sebe N (2013) Daily Living Activities Recognition via Efficient High and Low Level Cues Combination and Fisher Kernel Representation. In: IEEE International Conference on Image Analysis and Processing. ICIAP","DOI":"10.1007\/978-3-642-41181-6_44"},{"key":"2819_CR50","unstructured":"Raptis M, Soatto S (2011) Tracklet descriptors for action modeling and video analysis. In: European Conference of Computer Vision (ECCV), pp 577\u2013590"},{"key":"2819_CR51","unstructured":"Simonyan K, Vedaldi A, Zisserman A (2013) Deep Fisher networks for large-scale image classification. In: NIPS"},{"key":"2819_CR52","doi-asserted-by":"crossref","DOI":"10.1145\/2483977.2483988","volume-title":"Blip10000: A Social Video Dataset Containing SPUG Content for Tagging and Retrieval","author":"S Schmiedeke","year":"2013","unstructured":"Schmiedeke S, Xu P, Ferran\u00e9 I, Eskevich M, Kofler C, Larson M, Est\u00e8ve Y, Lamel L, Jones G, Sikora T (2013) Blip10000: A Social Video Dataset Containing SPUG Content for Tagging and Retrieval, vol 1. ACM Multimedia Systems Conference, Oslo, Norway"},{"key":"2819_CR53","unstructured":"Schmiedeke S, Kofler C, Ferran\u00e9 I Overview of the MediaEval 2012 Tagging Task, Working Notes Proceedings of the MediaEval 2012 Workshop, Pisa, Italy, October 4-5, 2012, CEUR-WS.org, ISSN 1613-0073, http:\/\/ceur-ws.org\/Vol-927\/mediaeval2012_submission_2.pdf"},{"key":"2819_CR54","unstructured":"Semela T, Tapaswi M, Ekenel H, Stiefelhagen R (2012) Kit at mediaeval 2012 - content-based genre classification with visual cues. In: MediaEval workshop"},{"key":"2819_CR55","unstructured":"Schmiedeke S, Kelm P, Sikora T (2012) TUB @ MediaEval 2012 tagging task: Feature selection methods for bag-of- (visual)-words approaches. In: MediaEval Workshop"},{"key":"2819_CR56","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Conference of Computer Vision and Patern Recognition"},{"issue":"7","key":"2819_CR57","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1007\/s00138-012-0449-x","volume":"24","author":"B Solmaz","year":"2013","unstructured":"Solmaz B, Assari SM, Mubarak S (2013) Classifying web videos using a global video descriptor. Mach Vi Appl (MVAP) 24(7):1473\u20131485","journal-title":"Mach Vi Appl (MVAP)"},{"key":"2819_CR58","unstructured":"Sj\u00f6berg M, Schl\u00fcter J, Ionescu B, Schedl M (2013) FAR at MediaEval 2013 Violent Scenes Detection: Concept-based Violent Scenes Detection in Movies. In: MediaEval 2014 Workshop, Barcelona"},{"issue":"7","key":"2819_CR59","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1109\/TMM.2010.2052027","volume":"12","author":"JRR Uijlings","year":"2010","unstructured":"Uijlings JRR, Smeulders AWM, Scha RJH (2010) Real-time visual concept classification. IEEE Trans Multimed 12(7):665\u2013681","journal-title":"IEEE Trans Multimed"},{"key":"2819_CR60","unstructured":"Uijlings JRR, Duta IC, Sangineto E, Sebe N (2014) Video classification with Densely extracted HOG\/HOF\/MBH features: an evaluation of the accuracy\/computational efficiency trade-off. In: International Journal of Multimedia Information Retrieval, pp 1\u201312"},{"issue":"7","key":"2819_CR61","doi-asserted-by":"crossref","first-page":"1512","DOI":"10.1109\/TIP.2009.2019809","volume":"18","author":"J Van deWeijer","year":"2009","unstructured":"Van deWeijer J, Schmid C, Verbeek J, Larlus D (2009) Learning color names for real-world applications. IEEE Trans Image Process 18(7):1512\u20131523","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"2819_CR62","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Klaser A, Schmid C, Liu C (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103(1):60\u201379","journal-title":"Int J Comput Vis"},{"key":"2819_CR63","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: ICCV, Proceedings, pp 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"2819_CR64","doi-asserted-by":"crossref","unstructured":"Wang J, Chen Z, Wu Y (2011) Action recognition with multiscale spatio-temporal contexts. In: CVPR","DOI":"10.1109\/CVPR.2011.5995493"},{"key":"2819_CR65","unstructured":"Wang H, Schmid C (2013) LEAR-INRIA submission for the THUMOS workshop. ICCV Workshop on Action Recognition with a Large Number of Classes"},{"issue":"12","key":"2819_CR66","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang Y, Ramanan D (2013) Articulated human detection with flexible mixtures of parts. IEEE Trans Pattern Anal Mach Intell 35(12):2878\u20132890","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-015-2819-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-015-2819-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-015-2819-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,29]],"date-time":"2019-08-29T12:30:54Z","timestamp":1567081854000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-015-2819-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,8,21]]},"references-count":66,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2016,8]]}},"alternative-id":["2819"],"URL":"https:\/\/doi.org\/10.1007\/s11042-015-2819-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,8,21]]}}}