{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:02:50Z","timestamp":1774872170186,"version":"3.50.1"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:00:00Z","timestamp":1599436800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:00:00Z","timestamp":1599436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11042-020-09759-9","type":"journal-article","created":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T23:04:07Z","timestamp":1599519847000},"page":"1223-1245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Scale-space multi-view bag of words for scene categorization"],"prefix":"10.1007","volume":"80","author":[{"given":"Davar","family":"Giveki","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,7]]},"reference":[{"issue":"11","key":"9759_CR1","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","volume":"54","author":"M Aharon","year":"2006","unstructured":"Aharon M, Elad M, Bruckstein A (2006) K-SVD: an algorithm for designing Overcomplete dictionaries for sparse representation. IEEE Trans Signal Process 54(11):4311\u20134322","journal-title":"IEEE Trans Signal Process"},{"key":"9759_CR2","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.inffus.2018.11.004","volume":"51","author":"KT Ahmed","year":"2019","unstructured":"Ahmed KT, Ummesafi S, Iqbal A (2019) Content based image retrieval using image features information fusion. Info Fusion 51:76\u201399","journal-title":"Info Fusion"},{"key":"9759_CR3","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.neunet.2018.01.005","volume":"99","author":"\u00c1 Arcos-Garc\u00eda","year":"2018","unstructured":"Arcos-Garc\u00eda \u00c1, \u00c1lvarez-Garc\u00eda JA, Soria-Morillo LM (2018) Deep neural network for traffic sign recognition systems: an analysis of spatial transformers and stochastic optimisation methods. Neural Netw 99:158\u2013165","journal-title":"Neural Netw"},{"key":"9759_CR4","doi-asserted-by":"crossref","unstructured":"Babaee M, Rigoll G, Bahmanyar R, Datcu M (2014) Locally linear salient coding for image classification. In Proceeding of the International Workshop on Content-Based Multimedia Indexing (CBMI)","DOI":"10.1109\/CBMI.2014.6849822"},{"issue":"10","key":"9759_CR5","doi-asserted-by":"crossref","first-page":"2046","DOI":"10.1109\/LGRS.2015.2444666","volume":"12","author":"R Bahmanyar","year":"2015","unstructured":"Bahmanyar R, Murillo Montes de Oca A, Datcu M (2015) The semantic gap: an exploration of user and computer perspectives in earth observation images. IEEE Geosci Remote Sens Lett 12(10):2046\u20132050","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"9759_CR6","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.asoc.2018.03.007","volume":"67","author":"S Bai","year":"2018","unstructured":"Bai S, Tang H (2018) Softly combining an ensemble of classifiers learned from a single convolutional neural network for scene categorization. Appl Soft Comput 67:183\u2013196","journal-title":"Appl Soft Comput"},{"key":"9759_CR7","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.robot.2019.01.004","volume":"113","author":"L Bampis","year":"2019","unstructured":"Bampis L, Gasteratos A (2019) Revisiting the bag-of-visual-words model: a hierarchical localization architecture for mobile systems. Robot Auton Syst 113:104\u2013119","journal-title":"Robot Auton Syst"},{"key":"9759_CR8","doi-asserted-by":"crossref","unstructured":"Banerji, S., Sinha, A., & Liu, C. (2013, August). A new bag of words LBP (BoWL) descriptor for scene image classification.In International conference on computer analysis of images and patterns (pp. 490-497).Springer, Berlin, Heidelberg.","DOI":"10.1007\/978-3-642-40261-6_59"},{"issue":"3","key":"9759_CR9","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.patcog.2012.07.024","volume":"46","author":"A Bolovinou","year":"2013","unstructured":"Bolovinou A, Pratikakis I, Perantonis S (2013) Bag of spatio-visual words for context inference in scene classification. Pattern Recogn 46(3):1039\u20131053","journal-title":"Pattern Recogn"},{"key":"9759_CR10","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., & Munoz, X. (2007, July). Representing shape with a spatial pyramid kernel.In Proceedings of the 6th ACM international conference on Image and video retrieval (pp. 401-408).ACM.","DOI":"10.1145\/1282280.1282340"},{"issue":"11","key":"9759_CR11","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1016\/j.cviu.2011.07.007","volume":"115","author":"F Cakir","year":"2011","unstructured":"Cakir F, G\u00fcd\u00fckbay U, Ulusoy \u00d6 (2011) Nearest-neighbor based metric functions for indoor scene recognition. Comput Vis Image Underst 115(11):1483\u20131492","journal-title":"Comput Vis Image Underst"},{"issue":"12","key":"9759_CR12","doi-asserted-by":"crossref","first-page":"5017","DOI":"10.1109\/TIP.2015.2475625","volume":"24","author":"TH Chan","year":"2015","unstructured":"Chan TH, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2015) PCANet: a simple deep learning baseline for image classification? IEEE Trans Image Process 24(12):5017\u20135032","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"9759_CR13","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1109\/LGRS.2017.2731997","volume":"14","author":"G Cheng","year":"2017","unstructured":"Cheng G, Li Z, Yao X, Guo L, Wei Z (2017) Remote sensing image scene classification using bag of convolutional features. IEEE Geosci Remote Sens Lett 14(10):1735\u20131739","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"9759_CR14","doi-asserted-by":"crossref","unstructured":"Cheng C, Long X, Li Y (2019) VLAD encoding based on LLC for image classification. In Proceedings of the 2019 11th International Conference on Machine Learning and Computing (pp. 417-422). ACM","DOI":"10.1145\/3318299.3318322"},{"key":"9759_CR15","unstructured":"Csurka G, Dance C, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In Workshop on statistical learning in computer vision, ECCV (Vol. 1, no. 1-22, pp. 1-2)"},{"key":"9759_CR16","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005.IEEE Computer Society Conference on (Vol. 1, pp. 886-893)","DOI":"10.1109\/CVPR.2005.177"},{"key":"9759_CR17","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.eswa.2019.05.021","volume":"133","author":"GV de Lima","year":"2019","unstructured":"de Lima GV, Saito PT, Lopes FM, Bugatti PH (2019) Classification of texture based on bag-of-visual-words through complex networks. Expert Syst Appl 133:215\u2013224","journal-title":"Expert Syst Appl"},{"key":"9759_CR18","doi-asserted-by":"crossref","unstructured":"Dixit M, Chen S, Gao D, Rasiwasia N, Vasconcelos N (2015) Scene classification with semantic fisher vectors. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2974-2983)","DOI":"10.1109\/CVPR.2015.7298916"},{"key":"9759_CR19","unstructured":"Doersch C, Gupta A, Efros AA (2013) Mid-level visual element discovery as discriminative mode seeking. In Advances in neural information processing systems (pp. 494-502)"},{"key":"9759_CR20","unstructured":"Escalante HJ, Ponce-L\u00f3pez V, Escalera S, Bar\u00f3 X, Morales-Reyes A, Mart\u00ednez-Carranza J (2015) Evolving weighting schemes for the bag of visual words. Neural Comput & Applic:1\u201315"},{"key":"9759_CR21","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.imavis.2015.11.004","volume":"47","author":"H Fan","year":"2016","unstructured":"Fan H, Zhou E (2016) Approaching human level facial landmark localization by deep learning. Image Vis Comput 47:27\u201335","journal-title":"Image Vis Comput"},{"key":"9759_CR22","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res 9:1871\u20131874","journal-title":"J Mach Learn Res"},{"key":"9759_CR23","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.compbiomed.2016.07.006","volume":"77","author":"GM Farinella","year":"2016","unstructured":"Farinella GM, Allegra D, Moltisanti M, Stanco F, Battiato S (2016) Retrieval and classification of food images. Comput Biol Med 77:23\u201339","journal-title":"Comput Biol Med"},{"key":"9759_CR24","doi-asserted-by":"crossref","unstructured":"Fornoni M, Caputo B (2012) Indoor scene recognition using task and saliency-driven feature pooling. In Proceedings of the British Machine Vision Conference (no.EPFL-CONF-192418)","DOI":"10.5244\/C.26.98"},{"key":"9759_CR25","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.jvcir.2019.01.009","volume":"59","author":"SNM Foumani","year":"2019","unstructured":"Foumani SNM, Nickabadi A (2019) A probabilistic topic model using deep visual word representation for simultaneous image classification and annotation. J Vis Commun Image Represent 59:195\u2013203","journal-title":"J Vis Commun Image Represent"},{"key":"9759_CR26","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.sigpro.2014.08.034","volume":"112","author":"Z Gao","year":"2015","unstructured":"Gao Z, Zhang H, Xu GP, Xue YB, Hauptmann AG (2015) Multi-view discriminative and structured dictionary learning with group sparsity for human action recognition. Signal Process 112:83\u201397","journal-title":"Signal Process"},{"key":"9759_CR27","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.ijar.2017.08.014","volume":"91","author":"D Giveki","year":"2017","unstructured":"Giveki D, Montazer GA, Soltanshahi MA (2017) Atanassov's intuitionistic fuzzy histon for robust moving object detection. Int J Approx Reason 91:80\u201395","journal-title":"Int J Approx Reason"},{"key":"9759_CR28","doi-asserted-by":"crossref","first-page":"164563","DOI":"10.1016\/j.ijleo.2020.164563","volume":"209","author":"D Giveki","year":"2020","unstructured":"Giveki D, Soltanshahi MA, Yousefvand M (2020) Proposing a new feature descriptor for moving object detection. Optik 209:164563","journal-title":"Optik"},{"key":"9759_CR29","doi-asserted-by":"crossref","unstructured":"Harada, T., Ushiku, Y., Yamashita, Y., &Kuniyoshi, Y. (2011, June). Discriminative spatial pyramid. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on (pp. 1617-1624).","DOI":"10.1109\/CVPR.2011.5995691"},{"key":"9759_CR30","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.eswa.2017.09.016","volume":"92","author":"R Hern\u00e1ndez-Garc\u00eda","year":"2018","unstructured":"Hern\u00e1ndez-Garc\u00eda R, Ramos-C\u00f3zar J, Guil N, Garc\u00eda-Reyes E, Sahli H (2018) Improving bag-of-visual-words model using visual n-grams for human action classification. Expert Syst Appl 92:182\u2013191","journal-title":"Expert Syst Appl"},{"key":"9759_CR31","unstructured":"Huang X, Li SZ, Wang Y (2004) Shape localization based on statistical method using extended local binary pattern. In Multi-Agent Security and Survivability, 2004 IEEE First Symposium on (pp. 184-187)."},{"key":"9759_CR32","doi-asserted-by":"crossref","unstructured":"Huang Y, Huang K, Yu Y, Tan T (2011) Salient coding for image classification. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on (pp. 1753-1760)","DOI":"10.1109\/CVPR.2011.5995682"},{"issue":"1","key":"9759_CR33","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/s00138-017-0871-1","volume":"29","author":"FS Khan","year":"2018","unstructured":"Khan FS, Van De Weijer J, Anwer RM, Bagdanov AD, Felsberg M, Laaksonen J (2018) Scale coding bag of deep features for human attribute and action recognition. Mach Vis Appl 29(1):55\u201371","journal-title":"Mach Vis Appl"},{"key":"9759_CR34","doi-asserted-by":"crossref","unstructured":"Kim J, Liu C, Sha F, Grauman K (2013) Deformable spatial pyramid matching for fast dense correspondences.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2307-2314)","DOI":"10.1109\/CVPR.2013.299"},{"key":"9759_CR35","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105)"},{"key":"9759_CR36","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on (Vol. 2, pp. 2169-2178)","DOI":"10.1109\/CVPR.2006.68"},{"issue":"4","key":"9759_CR37","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s13735-013-0041-9","volume":"2","author":"C Li","year":"2013","unstructured":"Li C, Hamza AB (2013) Intrinsic spatial pyramid matching for deformable 3d shape retrieval. Int J Multimed Info Retriev 2(4):261\u2013271","journal-title":"Int J Multimed Info Retriev"},{"key":"9759_CR38","unstructured":"Li Y, Yang M, Zhang ZM (2018) A survey of multi-view representation Learning. IEEE Transactions on Knowledge and Data Engineering"},{"key":"9759_CR39","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.inffus.2018.02.005","volume":"45","author":"J Li","year":"2019","unstructured":"Li J, Zhang B, Lu G, Zhang D (2019) Generative multi-view and multi-feature learning for classification. Info Fusion 45:215\u2013226","journal-title":"Info Fusion"},{"issue":"2","key":"9759_CR40","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. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"9759_CR41","doi-asserted-by":"crossref","unstructured":"Lu C, Shi J, Jia J (2013) Online robust dictionary learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 415-422)","DOI":"10.1109\/CVPR.2013.60"},{"key":"9759_CR42","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.neucom.2015.05.104","volume":"168","author":"GA Montazer","year":"2015","unstructured":"Montazer GA, Giveki D (2015) An improved radial basis function neural network for object image retrieval. Neurocomputing 168:221\u2013233","journal-title":"Neurocomputing"},{"issue":"18","key":"9759_CR43","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1016\/j.ijleo.2015.05.002","volume":"126","author":"GA Montazer","year":"2015","unstructured":"Montazer GA, Giveki D (2015) Content based image retrieval system using clustered scale invariant feature transforms. Optik 126(18):1695\u20131699","journal-title":"Optik"},{"issue":"2","key":"9759_CR44","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1007\/s11063-017-9614-6","volume":"46","author":"GA Montazer","year":"2017","unstructured":"Montazer GA, Giveki D (2017) Scene classification using multi-resolution WAHOLB features and neural network classifier. Neural Process Lett 46(2):681\u2013704","journal-title":"Neural Process Lett"},{"key":"9759_CR45","doi-asserted-by":"crossref","unstructured":"Montazer GA, Soltanshahi MA, Giveki D (2015) Extended bag of visual words for face detection. In International Work-Conference on Artificial Neural Networks (pp. 503-510). Springer, Cham","DOI":"10.1007\/978-3-319-19258-1_41"},{"key":"9759_CR46","doi-asserted-by":"crossref","unstructured":"Nakayama H, Harada T, Kuniyoshi Y (2010) Global gaussian approach for scene categorization using information geometry. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on (pp. 2336\u20132343)","DOI":"10.1109\/CVPR.2010.5539921"},{"issue":"3","key":"9759_CR47","doi-asserted-by":"crossref","first-page":"3634","DOI":"10.1016\/j.eswa.2011.09.054","volume":"39","author":"L Nanni","year":"2012","unstructured":"Nanni L, Lumini A, Brahnam S (2012) Survey on LBP based texture descriptors for image classification. Expert Syst Appl 39(3):3634\u20133641","journal-title":"Expert Syst Appl"},{"issue":"7","key":"9759_CR48","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietik\u00e4inen M, M\u00e4enp\u00e4\u00e4 T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Patt Anal Mach Intell IEEE Transact 24(7):971\u2013987","journal-title":"Patt Anal Mach Intell IEEE Transact"},{"issue":"3","key":"9759_CR49","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 42(3):145\u2013175","journal-title":"Int J Comput Vis"},{"issue":"2","key":"9759_CR50","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/j.patcog.2013.08.012","volume":"47","author":"OA Penatti","year":"2014","unstructured":"Penatti OA, Silva FB, Valle E, Gouet-Brunet V, Torres RDS (2014) Visual word spatial arrangement for image retrieval and classification. Pattern Recogn 47(2):705\u2013720","journal-title":"Pattern Recogn"},{"key":"9759_CR51","doi-asserted-by":"crossref","unstructured":"Quattoni A, Torralba A (2009) Recognizing indoor scenes. In Computer Vision and Pattern Recognition, 2009.CVPR 2009. IEEE Conference on (pp. 413-420)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"9759_CR52","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.cviu.2017.08.004","volume":"167","author":"R Rantoson","year":"2018","unstructured":"Rantoson R, Bartoli A (2018) A 3D deformable model-based framework for the retrieval of near-isometric flattenable objects using bag-of-visual-Words. Comput Vis Image Underst 167:89\u2013108","journal-title":"Comput Vis Image Underst"},{"issue":"4","key":"9759_CR53","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JSTSP.2015.2407860","volume":"9","author":"S Ravishankar","year":"2015","unstructured":"Ravishankar S, Bresler Y (2015) Online sparsifyingtransform learning\u2014part II: convergence analysis. IEEE J Select Topics Signal Process 9(4):637\u2013646","journal-title":"IEEE J Select Topics Signal Process"},{"key":"9759_CR54","doi-asserted-by":"crossref","unstructured":"Saikia, A. R., Bora, K., Mahanta, L. B., & Das, A. K. (2019). Comparative assessment of CNN architectures for classification of breast FNAC images. Tissue Cell, 57, 8-14.","DOI":"10.1016\/j.tice.2019.02.001"},{"key":"9759_CR55","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.patcog.2019.03.026","volume":"92","author":"R Shang","year":"2019","unstructured":"Shang R, Meng Y, Wang W, Shang F, Jiao L (2019) Local discriminative based sparse subspace learning for feature selection. Pattern Recogn 92:219\u2013230","journal-title":"Pattern Recogn"},{"key":"9759_CR56","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.patcog.2017.09.018","volume":"74","author":"FB Silva","year":"2018","unstructured":"Silva FB, Werneck RDO, Goldenstein S, Tabbone S, Torres RDS (2018) Graph-based bag-of-words for classification. Pattern Recogn 74:266\u2013285","journal-title":"Pattern Recogn"},{"issue":"1","key":"9759_CR57","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/S0045-7906(01)00011-8","volume":"29","author":"RS Stankovi\u0107","year":"2003","unstructured":"Stankovi\u0107 RS, Falkowski BJ (2003) The Haar wavelet transform: its status and achievements. Comput Electr Eng 29(1):25\u201344","journal-title":"Comput Electr Eng"},{"issue":"12","key":"9759_CR58","doi-asserted-by":"crossref","first-page":"3180","DOI":"10.1109\/TSP.2016.2540599","volume":"64","author":"J Sulam","year":"2016","unstructured":"Sulam J, Ophir B, Zibulevsky M, Elad M (2016) Trainlets: dictionary learning in high dimensions. IEEE Trans Signal Process 64(12):3180\u20133193","journal-title":"IEEE Trans Signal Process"},{"issue":"7\u20138","key":"9759_CR59","doi-asserted-by":"crossref","first-page":"2031","DOI":"10.1007\/s00521-013-1362-6","volume":"23","author":"S Sun","year":"2013","unstructured":"Sun S (2013) A survey of multi-view machine learning. Neural Comput & Applic 23(7\u20138):2031\u20132038","journal-title":"Neural Comput & Applic"},{"issue":"2","key":"9759_CR60","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TEVC.2019.2916183","volume":"24","author":"Y Sun","year":"2019","unstructured":"Sun Y, Xue B, Zhang M, Yen GG (2019) Evolving deep convolutional neural networks for image classification. IEEE Trans Evol Comput 24(2):394\u2013407","journal-title":"IEEE Trans Evol Comput"},{"key":"9759_CR61","unstructured":"Szummer M, Picard RW (1998) Indoor-outdoor image classification. In Content-Based Access of Image and Video Database, 1998. Proceedings., 1998 IEEE International Workshop on (pp. 42-51)"},{"key":"9759_CR62","doi-asserted-by":"crossref","unstructured":"Tian Y, Luo P, Wang X, Tang X (2015) Deep learning strong parts for pedestrian detection. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1904-1912)","DOI":"10.1109\/ICCV.2015.221"},{"key":"9759_CR63","doi-asserted-by":"crossref","unstructured":"Tirilly P, Claveau V, Gros P (2010) Distances and weighting schemes for bag of visual words image retrieval. In Proceedings of the international conference on multimedia information retrieval (pp. 323-332). ACM","DOI":"10.1145\/1743384.1743438"},{"key":"9759_CR64","doi-asserted-by":"crossref","unstructured":"Upadhyay PK, Chandra S (2019) An improved bag of dense features for skin lesion recognition. J King Saud Univ-Comp Info Sci","DOI":"10.1016\/j.jksuci.2019.02.007"},{"key":"9759_CR65","doi-asserted-by":"crossref","unstructured":"Van Gemert JC, Geusebroek JM, Veenman CJ, Smeulders AW (2008) Kernel codebooks for scene categorization. In European conference on computer vision (pp. 696\u2013709). Springer Berlin Heidelberg","DOI":"10.1007\/978-3-540-88690-7_52"},{"issue":"2","key":"9759_CR66","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s11263-006-8614-1","volume":"72","author":"J Vogel","year":"2007","unstructured":"Vogel J, Schiele B (2007) Semantic modeling of natural scenes for content-based image retrieval. Int J Comput Vis 72(2):133\u2013157","journal-title":"Int J Comput Vis"},{"key":"9759_CR67","doi-asserted-by":"crossref","unstructured":"Wang Y, Gong S (2007) Conditional random field for natural scene categorization. In BMVC (pp. 1-10).","DOI":"10.5244\/C.21.59"},{"issue":"5","key":"9759_CR68","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1109\/TIP.2016.2541318","volume":"25","author":"R Wang","year":"2016","unstructured":"Wang R, Tao D (2016) Non-local auto-encoder with collaborative stabilization for image restoration. IEEE Trans Image Process 25(5):2117\u20132129","journal-title":"IEEE Trans Image Process"},{"key":"9759_CR69","doi-asserted-by":"crossref","unstructured":"Wang S, Wang Y, Zhu SC (2013) Hierarchical space tiling for scene modeling. In Computer Vision\u2013ACCV 2012 (pp. 796\u2013810). Springer Berlin Heidelberg","DOI":"10.1007\/978-3-642-37444-9_62"},{"issue":"6","key":"9759_CR70","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1109\/JPROC.2010.2044470","volume":"98","author":"J Wright","year":"2010","unstructured":"Wright J, Ma Y, Mairal J, Sapiro G, Huang TS, Yan S (2010) Sparse representation for computer vision and pattern recognition. Proc IEEE 98(6):1031\u20131044","journal-title":"Proc IEEE"},{"issue":"8","key":"9759_CR71","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TPAMI.2010.224","volume":"33","author":"J Wu","year":"2011","unstructured":"Wu J, Rehg JM (2011) CENTRIST: A visual descriptor for scene categorization. Patt Anal Mach Intell IEEE Transact 33(8):1489\u20131501","journal-title":"Patt Anal Mach Intell IEEE Transact"},{"key":"9759_CR72","doi-asserted-by":"crossref","unstructured":"Wu R, Wang B, Wang W, Yu Y (2015) Harvesting discriminative meta objects with deep CNN features for scene classification. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1287\u20131295)","DOI":"10.1109\/ICCV.2015.152"},{"key":"9759_CR73","doi-asserted-by":"crossref","unstructured":"Wu J, Lin Z, Zha H (2019) Essential tensor learning for multi-view spectral Clustering. IEEE Transact Image Process","DOI":"10.1109\/TIP.2019.2916740"},{"issue":"2","key":"9759_CR74","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1109\/TIP.2013.2295756","volume":"23","author":"Y Xiao","year":"2014","unstructured":"Xiao Y, Wu J, Yuan J (2014) mCENTRIST: a multi-channel feature generation mechanism for scene categorization. IEEE Trans Image Process 23(2):823\u2013836","journal-title":"IEEE Trans Image Process"},{"key":"9759_CR75","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.eswa.2019.01.085","volume":"126","author":"J Xie","year":"2019","unstructured":"Xie J, Zhu M (2019) Investigation of acoustic and visual features for acoustic scene classification. Expert Syst Appl 126:20\u201329","journal-title":"Expert Syst Appl"},{"key":"9759_CR76","unstructured":"Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In Computer Vision and Pattern Recognition, 2009.CVPR 2009. IEEE Conference on (pp. 1794-1801)"},{"issue":"10","key":"9759_CR77","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.1016\/j.patcog.2015.03.012","volume":"48","author":"YB Yang","year":"2015","unstructured":"Yang YB, Zhu QH, Mao XJ, Pan LY (2015) Visual feature coding for image classification integrating dictionary structure. Pattern Recogn 48(10):3067\u20133075","journal-title":"Pattern Recogn"},{"key":"9759_CR78","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.jvcir.2019.01.002","volume":"60","author":"W Yin","year":"2019","unstructured":"Yin W, Xu D, Wang Z, Zhao Z, Chen C, Yao Y (2019) Perceptually learning multi-view sparse representation for scene categorization. J Vis Commun Image Represent 60:59\u201363","journal-title":"J Vis Commun Image Represent"},{"key":"9759_CR79","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.neucom.2012.08.061","volume":"120","author":"J Yu","year":"2013","unstructured":"Yu J, Qin Z, Wan T, Zhang X (2013) Feature integration analysis of bag-of-features model for image retrieval. Neurocomputing 120:355\u2013364","journal-title":"Neurocomputing"},{"key":"9759_CR80","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.patcog.2019.03.006","volume":"91","author":"WJ Yu","year":"2019","unstructured":"Yu WJ, Chen ZD, Luo X, Liu W, Xu XS (2019) DELTA: a deep dual-stream network for multi-label image classification. Pattern Recogn 91:322\u2013331","journal-title":"Pattern Recogn"},{"key":"9759_CR81","unstructured":"Zhang W, Shan S, Gao W, Chen X, Zhang H (2005) Local gabor binary pattern histogram sequence (lgbphs): a novel non-statistical model for face representation and recognition. In Computer Vision, 2005.ICCV 2005.Tenth IEEE International Conference on (Vol. 1, pp. 786-791)"},{"key":"9759_CR82","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.cviu.2013.03.008","volume":"118","author":"S Zhang","year":"2014","unstructured":"Zhang S, Tian Q, Hua G, Huang Q, Gao W (2014) ObjectPatchNet: towards scalable and semantic image annotation and retrieval. Comput Vis Image Underst 118:16\u201329","journal-title":"Comput Vis Image Underst"},{"key":"9759_CR83","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/ACCESS.2015.2430359","volume":"3","author":"Z Zhang","year":"2015","unstructured":"Zhang Z, Xu Y, Yang J, Li X, Zhang D (2015) A survey of sparse representation: algorithms and applications. IEEE Access 3:490\u2013530","journal-title":"IEEE Access"},{"key":"9759_CR84","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.inffus.2017.02.007","volume":"38","author":"J Zhao","year":"2017","unstructured":"Zhao J, Xie X, Xu X, Sun S (2017) Multi-view learning overview: recent progress and new challenges. Info Fusion 38:43\u201354","journal-title":"Info Fusion"},{"issue":"1","key":"9759_CR85","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.patcog.2012.07.017","volume":"46","author":"L Zhou","year":"2013","unstructured":"Zhou L, Zhou Z, Hu D (2013) Scene classification using a multi-resolution bag-of-features model. Pattern Recogn 46(1):424\u2013433","journal-title":"Pattern Recogn"},{"issue":"6","key":"9759_CR86","doi-asserted-by":"crossref","first-page":"1561","DOI":"10.1007\/s00138-014-0622-5","volume":"25","author":"SS Zhu","year":"2014","unstructured":"Zhu SS, Yung NH (2014) Improve scene categorization via sub-scene recognition. Mach Vis Appl 25(6):1561\u20131572","journal-title":"Mach Vis Appl"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09759-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09759-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09759-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T09:45:40Z","timestamp":1723542340000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09759-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,7]]},"references-count":86,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["9759"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09759-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,7]]},"assertion":[{"value":"29 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"There is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}