{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T08:11:56Z","timestamp":1768464716700,"version":"3.49.0"},"reference-count":120,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T00:00:00Z","timestamp":1686355200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T00:00:00Z","timestamp":1686355200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15005-9","type":"journal-article","created":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T08:03:21Z","timestamp":1686384201000},"page":"9251-9278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Recent advances in scene image representation and classification"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4564-2985","authenticated-orcid":false,"given":"Chiranjibi","family":"Sitaula","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tej Bahadur","family":"Shahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faezeh","family":"Marzbanrad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagannath","family":"Aryal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,10]]},"reference":[{"issue":"9","key":"15005_CR1","doi-asserted-by":"crossref","first-page":"e0203,339","DOI":"10.1371\/journal.pone.0203339","volume":"13","author":"N Ali","year":"2018","unstructured":"Ali N, Zafar B, Riaz F, Dar SH, Ratyal NI, Bajwa KB, Iqbal MK, Sajid M (2018) A hybrid geometric spatial image representation for scene classification. PloS ONE 13(9):e0203,339","journal-title":"PloS ONE"},{"key":"15005_CR2","first-page":"64","volume":"5","author":"E Anu","year":"2016","unstructured":"Anu E, Anu K (2016) A survey on scene recognition. Int J Sci Eng Technol Res(IJSETR) 5:64\u201368","journal-title":"Int J Sci Eng Technol Res(IJSETR)"},{"issue":"4","key":"15005_CR3","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1016\/j.joi.2017.08.007","volume":"11","author":"M Aria","year":"2017","unstructured":"Aria M, Cuccurullo C (2017) Bibliometrix: an r-tool for comprehensive science mapping analysis. J Informetrics 11(4):959\u2013975","journal-title":"J Informetrics"},{"key":"15005_CR4","doi-asserted-by":"crossref","first-page":"103,530","DOI":"10.1016\/j.bspc.2022.103530","volume":"74","author":"AM Ayalew","year":"2022","unstructured":"Ayalew AM, Salau AO, Abeje BT, Enyew B (2022) Detection and classification of covid-19 disease from x-ray images using convolutional neural networks and histogram of oriented gradients. Biomed Signal Process Control 74:103,530","journal-title":"Biomed Signal Process Control"},{"key":"15005_CR5","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.eswa.2016.10.038","volume":"71","author":"S Bai","year":"2017","unstructured":"Bai S (2017) Growing random forest on deep convolutional neural networks for scene categorization. Expert Syst Appl 71:279\u2013287","journal-title":"Expert Syst Appl"},{"key":"15005_CR6","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.eswa.2018.08.056","volume":"120","author":"S Bai","year":"2019","unstructured":"Bai S, Tang H, An S (2019) Coordinate cnns and lstms to categorize scene images with multi-views and multi-levels of abstraction. Expert Syst Appl 120:298\u2013309","journal-title":"Expert Syst Appl"},{"key":"15005_CR7","doi-asserted-by":"crossref","unstructured":"Banerji S, Sinha A, Liu C (2012) Novel color, shape and texture-based scene image descriptors. In: 2012 IEEE 8th International conference on intelligent computer communication and processing, IEEE, pp 245\u2013248","DOI":"10.1109\/ICCP.2012.6356193"},{"key":"15005_CR8","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135\u2013146","journal-title":"Trans Assoc Comput Linguist"},{"issue":"4","key":"15005_CR9","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TPAMI.2007.70716","volume":"30","author":"A Bosch","year":"2008","unstructured":"Bosch A, Zisserman A, Mu\u00f1oz X (2008) Scene classification using a hybrid generative\/discriminative approach. IEEE Trans Pattern Anal Mach Intell 30(4):712\u2013727","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15005_CR10","doi-asserted-by":"crossref","first-page":"5877","DOI":"10.1109\/TIP.2020.2986599","volume":"29","author":"G Chen","year":"2020","unstructured":"Chen G, Song X, Zeng H, Jiang S (2020) Scene recognition with prototype-agnostic scene layout. IEEE Trans Image Process 29:5877\u20135888","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"15005_CR11","doi-asserted-by":"crossref","first-page":"4081","DOI":"10.1007\/s11042-017-4830-7","volume":"77","author":"H Chen","year":"2018","unstructured":"Chen H, Xie K, Wang H, Zhao C (2018) Scene image classification using locality-constrained linear coding based on histogram intersection. Multimed Tools Appl 77(3):4081\u20134092","journal-title":"Multimed Tools Appl"},{"key":"15005_CR12","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/j.patcog.2017.09.025","volume":"74","author":"X Cheng","year":"2018","unstructured":"Cheng X, Lu J, Feng J, Yuan B, Zhou J (2018) Scene recognition with objectness. Pattern Recognit 74:474\u2013487","journal-title":"Pattern Recognit"},{"key":"15005_CR13","doi-asserted-by":"crossref","unstructured":"Cho WS, Lam KM (2012) An efficient and effective hybrid pyramid kernel for un-segmented image classification. In: 2012 International conference on systems and informatics (ICSAI2012), IEEE, pp 2153\u20132158","DOI":"10.1109\/ICSAI.2012.6223478"},{"key":"15005_CR14","doi-asserted-by":"crossref","unstructured":"Choe S, Seong H, Kim E (2021) Indoor place category recognition for a cleaning robot by fusing a probabilistic approach and deep learning. IEEE Transactions on Cybernetics","DOI":"10.1109\/TCYB.2021.3052499"},{"key":"15005_CR15","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proc. ieee comput. soc. conf. comput. vis. pattern recognit. (CVPR), pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"15005_CR16","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. CVPR","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15005_CR17","doi-asserted-by":"crossref","unstructured":"Dixit M, Chen S, Gao D, Rasiwasia N, Vasconcelos N (2015) Scene classification with semantic fisher vectors. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp 2974\u20132983","DOI":"10.1109\/CVPR.2015.7298916"},{"issue":"12","key":"15005_CR18","doi-asserted-by":"crossref","first-page":"3102","DOI":"10.1109\/TPAMI.2019.2921960","volume":"42","author":"M Dixit","year":"2019","unstructured":"Dixit M, Li Y, Vasconcelos N (2019) Semantic fisher scores for task transfer: using objects to classify scenes. IEEE Trans Pattern Anal Mach Intell 42 (12):3102\u20133118","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"15005_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep03188","volume":"3","author":"R Dutta","year":"2013","unstructured":"Dutta R, Aryal J, Das A, Kirkpatrick JB (2013) Deep cognitive imaging systems enable estimation of continental-scale fire incidence from climate data. Sci Rep 3(1):1\u20134","journal-title":"Sci Rep"},{"key":"15005_CR20","unstructured":"Fei-Fei L, Perona P (2005) A Bayesian hierarchical model for learning natural scene categories. In: Proc. IEEE comput. Soc. Conf. Comput. Vis. and pattern recognit. (CVPR), vol 2, pp 524\u2013531"},{"key":"15005_CR21","doi-asserted-by":"crossref","unstructured":"Fornoni M, Caputo B (2014) Scene recognition with naive bayes non-linear learning. In: 2014 22nd International conference on pattern recognition, IEEE, pp 3404\u20133409","DOI":"10.1109\/ICPR.2014.586"},{"key":"15005_CR22","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: Proc. Eur. Conf. Comput. Vis. (ECCV), pp 392\u2013407","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"15005_CR23","unstructured":"Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset"},{"issue":"2","key":"15005_CR24","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1109\/TIP.2016.2629443","volume":"26","author":"S Guo","year":"2017","unstructured":"Guo S, Huang W, Wang L, Qiao Y (2017) Locally supervised deep hybrid model for scene recognition. IEEE Trans Image Process 26(2):808\u2013820","journal-title":"IEEE Trans Image Process"},{"key":"15005_CR25","doi-asserted-by":"crossref","unstructured":"Guo Y, Lew MS (2016) Bag of Surrogate parts: one inherent feature of deep cnns. In: Proc. of the British Machine Vision Conference (BMVC)","DOI":"10.5244\/C.30.96"},{"issue":"2","key":"15005_CR26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00138-021-01168-8","volume":"32","author":"S Gupta","year":"2021","unstructured":"Gupta S, Dileep AD, Thenkanidiyoor V (2021) Recognition of varying size scene images using semantic analysis of deep activation maps. Mach Vis Appl 32(2):1\u201319","journal-title":"Mach Vis Appl"},{"key":"15005_CR27","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc. IEEE conf. comput. vis. pattern recognit. (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"15005_CR28","doi-asserted-by":"crossref","unstructured":"Hu J, Guo P (2012) Spatial local binary patterns for scene image classification. In: 2012 6Th international conference on sciences of electronics, technologies of information and telecommunications, SETIT, IEEE, pp 326\u2013330","DOI":"10.1109\/SETIT.2012.6481936"},{"key":"15005_CR29","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proc. 22nd ACM Int. Conf. on Multimedia (ACMM), pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"issue":"1s","key":"15005_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3231738","volume":"15","author":"S Jiang","year":"2019","unstructured":"Jiang S, Chen G, Song X, Liu L (2019) Deep patch representations with shared codebook for scene classification. ACM Trans Multimed Comput Commun Appl 15(1s):1\u201317","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"15005_CR31","doi-asserted-by":"crossref","unstructured":"Juneja M, Vedaldi A, Jawahar C, Zisserman A (2013) Blocks that shout: distinctive parts for scene classification. In: Proc. IEEE conf. comput. vis. pattern recognit. (CVPR), pp 923\u2013930","DOI":"10.1109\/CVPR.2013.124"},{"key":"15005_CR32","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.neucom.2021.01.085","volume":"440","author":"A Khan","year":"2021","unstructured":"Khan A, Chefranov A, Demirel H (2021) Image scene geometry recognition using low-level features fusion at multi-layer deep cnn. Neurocomputing 440:111\u2013126","journal-title":"Neurocomputing"},{"issue":"7","key":"15005_CR33","doi-asserted-by":"crossref","first-page":"3372","DOI":"10.1109\/TIP.2016.2567076","volume":"25","author":"SH Khan","year":"2016","unstructured":"Khan SH, Hayat M, Bennamoun M, Togneri R, Sohel FA (2016) A discriminative representation of convolutional features for indoor scene recognition. IEEE Trans Image Process 25(7):3372\u20133383","journal-title":"IEEE Trans Image Process"},{"key":"15005_CR34","doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. arXiv:14085882","DOI":"10.3115\/v1\/D14-1181"},{"key":"15005_CR35","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Proc. adv. neural inf. process. syst. (NIPS), pp 1097\u20131105"},{"key":"15005_CR36","doi-asserted-by":"crossref","unstructured":"Kuzborskij I, Maria Carlucci F, Caputo B (2016) When naive bayes nearest neighbors meet convolutional neural networks. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp 2100\u20132109","DOI":"10.1109\/CVPR.2016.231"},{"key":"15005_CR37","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: Proc. IEEE comput. soc. conf. comput. vis. pattern recognit. (CVPR), pp 2169\u20132178","DOI":"10.1109\/CVPR.2006.68"},{"issue":"7553","key":"15005_CR38","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"15005_CR39","doi-asserted-by":"crossref","unstructured":"Li LJ, Li FF (2007) What, where and who? classifying events by scene and object recognition. In: Proc. 11th int. Conf. Comput. Vis. (ICCV), vol 2, p 6","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"15005_CR40","doi-asserted-by":"crossref","unstructured":"Li Q, Qin Z, Chai L, Zhang H, Guo J, Bhanu B (2013) Representative reference-set and betweenness centrality for scene image categorization. In: 2013 IEEE International conference on image processing, IEEE, pp 3254\u20133258","DOI":"10.1109\/ICIP.2013.6738670"},{"key":"15005_CR41","unstructured":"Li LJ, Su H, Fei-Fei L, Xing EP (2010) Object bank: a high-level image representation for scene classification & semantic feature sparsification. In: Proc. adv. neural inf. process. syst. (NIPS), pp 1378\u20131386"},{"issue":"1","key":"15005_CR42","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/LSP.2012.2228852","volume":"20","author":"Q Li","year":"2012","unstructured":"Li Q, Zhang H, Guo J, Bhanu B, An L (2012) Reference-based scheme combined with k-svd for scene image categorization. IEEE Signal Process Lett 20(1):67\u201370","journal-title":"IEEE Signal Process Lett"},{"issue":"3","key":"15005_CR43","first-page":"985","volume":"128","author":"C Lin","year":"2021","unstructured":"Lin C, Lee F, Cai J, Chen H, Chen Q (2021) Global and graph encoded local discriminative region representation for scene recognition. Comput Model Eng Sci 128(3):985\u20131006","journal-title":"Comput Model Eng Sci"},{"key":"15005_CR44","doi-asserted-by":"crossref","unstructured":"Lin D, Lu C, Liao R, Jia J (2014) Learning important spatial pooling regions for scene classification. In: Proc. IEEE conf. comput. vis. pattern recognit. (CVPR), pp 3726\u20133733","DOI":"10.1109\/CVPR.2014.476"},{"key":"15005_CR45","doi-asserted-by":"crossref","unstructured":"Lin TY, RoyChowdhury A, Maji S (2015) Bilinear cnn models for fine-grained visual recognition. In: Proc. IEEE int. conf. comput. vis. (ICCV), pp 1449\u20131457","DOI":"10.1109\/ICCV.2015.170"},{"issue":"6","key":"15005_CR46","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1109\/TPAMI.2017.2723400","volume":"40","author":"TYY Lin","year":"2018","unstructured":"Lin TYY, RoyChowdhury A, Maji S (2018) Bilinear convolutional neural networks for fine-grained visual recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1309\u20131322","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15005_CR47","doi-asserted-by":"crossref","first-page":"4629","DOI":"10.1109\/ACCESS.2018.2886597","volume":"7","author":"W Liu","year":"2018","unstructured":"Liu W, Li Y, Wu Q (2018) An attribute-based high-level image representation for scene classification. IEEE Access 7:4629\u20134640","journal-title":"IEEE Access"},{"key":"15005_CR48","doi-asserted-by":"crossref","unstructured":"Liu S, Tian G (2019) An indoor scene classification method for service robot based on cnn feature. J Robot 2019","DOI":"10.1155\/2019\/8591035"},{"key":"15005_CR49","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.neucom.2019.01.090","volume":"338","author":"S Liu","year":"2019","unstructured":"Liu S, Tian G, Xu Y (2019) A novel scene classification model combining resnet based transfer learning and data augmentation with a filter. Neurocomputing 338:191\u2013206","journal-title":"Neurocomputing"},{"key":"15005_CR50","doi-asserted-by":"crossref","first-page":"2392","DOI":"10.1109\/TMM.2021.3080076","volume":"24","author":"S Liu","year":"2021","unstructured":"Liu S, Tian G, Zhang Y, Duan P (2021) Scene recognition mechanism for service robot adapting various families: a cnn-based approach using multi-type cameras. IEEE Trans Multimed 24:2392\u20132406","journal-title":"IEEE Trans Multimed"},{"key":"15005_CR51","doi-asserted-by":"crossref","first-page":"107,256","DOI":"10.1016\/j.patcog.2020.107256","volume":"102","author":"A Lopez-Cifuentes","year":"2020","unstructured":"Lopez-Cifuentes A, Escudero-Vinolo M, Bescos J, Garcia-Martin A (2020) Semantic-aware scene recognition. Pattern Recognit 102:107,256","journal-title":"Pattern Recognit"},{"key":"15005_CR52","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features, vol 2, pp 1150\u20131157","DOI":"10.1109\/ICCV.1999.790410"},{"key":"15005_CR53","doi-asserted-by":"crossref","unstructured":"Margolin R, Zelnik-Manor L, Tal A (2014) OTC: a novel local descriptor for scene classification. In: Proc. Eur. Conf. Comput. Vis. (ECCV), pp 377\u2013391","DOI":"10.1007\/978-3-319-10584-0_25"},{"issue":"4","key":"15005_CR54","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","volume":"5","author":"WS McCulloch","year":"1943","unstructured":"McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115\u2013133","journal-title":"Bull Math Biophys"},{"key":"15005_CR55","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv:13013781"},{"issue":"2","key":"15005_CR56","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1109\/2945.597800","volume":"3","author":"T Moller","year":"1997","unstructured":"Moller T, Machiraju R, Mueller K, Yagel R (1997) Evaluation and design of filters using a taylor series expansion. IEEE Trans Vis Comput Graph 3(2):184\u2013199","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"15005_CR57","doi-asserted-by":"crossref","unstructured":"Nascimento G, Laranjeira C, Braz V, Lacerda A, Nascimento ER (2017) A robust indoor scene recognition method based on sparse representation. arXiv:1708.07555","DOI":"10.1007\/978-3-319-75193-1_49"},{"issue":"4","key":"15005_CR58","doi-asserted-by":"crossref","first-page":"808","DOI":"10.3390\/rs13040808","volume":"13","author":"B Neupane","year":"2021","unstructured":"Neupane B, Horanont T, Aryal J (2021) Deep learning-based semantic segmentation of urban features in satellite images: a review and meta-analysis. Remote Sens 13(4):808","journal-title":"Remote Sens"},{"key":"15005_CR59","unstructured":"Niu Z, Zhou Y, Shi K (2010) A hybrid image representation for indoor scene classification. In: 2010 25th International conference of image and vision computing New Zealand, IEEE, pp 1\u20137"},{"key":"15005_CR60","doi-asserted-by":"crossref","unstructured":"Oliva A (2005) Gist of the scene. In: Neurobiology of attention, Elsevier, pp 251\u2013256","DOI":"10.1016\/B978-012375731-9\/50045-8"},{"issue":"3","key":"15005_CR61","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"},{"key":"15005_CR62","doi-asserted-by":"crossref","unstructured":"Parizi N, Oberlin JG, Felzenszwalb PF (2012) Reconfigurable models for scene recognition. In: Proc. comput. vis. pattern recognit. (CVPR), pp 2775\u20132782","DOI":"10.1109\/CVPR.2012.6248001"},{"key":"15005_CR63","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proc. conf. on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"15005_CR64","doi-asserted-by":"crossref","unstructured":"Perronnin F, Sanchez J, Mensink T (2010) Improving the fisher kernel for large-scale image classification. In: Proc. Eur. Conf. Comput. Vis. (ECCV), pp 143\u2013156","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"15005_CR65","doi-asserted-by":"crossref","unstructured":"Qi M, Wang Y (2016) Deep-cssr: scene classification using category-specific salient region with deep features. In: 2016 IEEE International Conference on Image Processing (ICIP), IEEE, pp 1047\u20131051","DOI":"10.1109\/ICIP.2016.7532517"},{"key":"15005_CR66","doi-asserted-by":"crossref","unstructured":"Quattoni A, Torralba A (2009) Recognizing indoor scenes. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp 413\u2013420","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"15005_CR67","doi-asserted-by":"crossref","unstructured":"Rasiwasia N, Vasconcelos N (2008) Scene classification with low-dimensional semantic spaces and weak supervision. In: IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp 1\u20136","DOI":"10.1109\/CVPR.2008.4587372"},{"key":"15005_CR68","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"15005_CR69","unstructured":"Ren X, Bo L, Fox D (2012) Rgb-(d) scene labeling: features and algorithms. In: 2012 IEEE Conference on computer vision and pattern recognition, IEEE, pp 2759\u20132766"},{"issue":"3","key":"15005_CR70","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1038\/nbt0308-303","volume":"26","author":"M Ringn\u00e9r","year":"2008","unstructured":"Ringn\u00e9r M (2008) What is principal component analysis? Nat Biotechnol 26(3):303\u2013304","journal-title":"Nat Biotechnol"},{"issue":"3","key":"15005_CR71","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J Sa\u0307nchez","year":"2013","unstructured":"Sa\u0307nchez J, Perronnin F, Mensink T, Verbeek J (2013) Image classification with the fisher vector: theory and practice. Int J Comput Vis 105(3):222\u2013245","journal-title":"Int J Comput Vis"},{"issue":"1","key":"15005_CR72","doi-asserted-by":"crossref","first-page":"78","DOI":"10.3390\/e21010078","volume":"21","author":"M Shadman Roodposhti","year":"2019","unstructured":"Shadman Roodposhti M, Aryal J, Lucieer A, Bryan BA (2019) Uncertainty assessment of hyperspectral image classification: deep learning vs. random forest. Entropy 21(1):78","journal-title":"Entropy"},{"key":"15005_CR73","doi-asserted-by":"crossref","unstructured":"Shahi TB, Sitaula C (2021) Natural language processing for nepali text: a review. Artif Intell Rev 1\u201329","DOI":"10.1007\/s10462-021-10093-1"},{"issue":"2","key":"15005_CR74","doi-asserted-by":"crossref","first-page":"e0264,586","DOI":"10.1371\/journal.pone.0264586","volume":"17","author":"TB Shahi","year":"2022","unstructured":"Shahi TB, Sitaula C, Neupane A, Guo W (2022) Fruit classification using attention-based mobilenetv2 for industrial applications. PloS ONE 17(2):e0264,586","journal-title":"PloS ONE"},{"key":"15005_CR75","doi-asserted-by":"crossref","unstructured":"Sharma K, Gupta S, Dileep AD, Rameshan R (2018) Scene image classification using reduced virtual feature representation in sparse framework. In: 2018 IEEE International conference on acoustics, speech and signal processing, ICASSP, IEEE, pp 2701\u20132705","DOI":"10.1109\/ICASSP.2018.8462429"},{"key":"15005_CR76","unstructured":"ShenghuaGao IH, Liang-TienChia P (2010) Local features are not lonely\u2013Laplacian sparse coding for image classification. In: Proc. IEEE conf. comput. vis. pattern recognit. (CVPR), pp 3555\u20133561"},{"key":"15005_CR77","doi-asserted-by":"crossref","unstructured":"Silberman N, Fergus R (2011) Indoor scene segmentation using a structured light sensor. In: 2011 IEEE International conference on computer vision workshops, ICCV workshops, IEEE, pp 601\u2013608","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"15005_CR78","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"15005_CR79","unstructured":"Singh V, Girish D, Ralescu A (2017) Image understanding-a brief review of scene classification and recognition. In: Proc. modern artificial intelligence and cognitive science (MAICS), pp 85\u201391"},{"key":"15005_CR80","doi-asserted-by":"crossref","unstructured":"Sinha A, Banerji S, Liu C (2012) Novel gabor-phog features for object and scene image classification. In: Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition, SSPR, Springer, pp 584\u2013592","DOI":"10.1007\/978-3-642-34166-3_64"},{"key":"15005_CR81","doi-asserted-by":"crossref","unstructured":"Sinha A, Banerji S, Liu C (2014) Scene image classification using a wigner-based local binary patterns descriptor. In: 2014 International joint conference on neural networks, IJCNN, IEEE, pp 1614\u20131621","DOI":"10.1109\/IJCNN.2014.6889660"},{"issue":"2","key":"15005_CR82","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s00138-013-0561-6","volume":"25","author":"A Sinha","year":"2014","unstructured":"Sinha A, Banerji S, Liu C (2014) New color gphog descriptors for object and scene image classification. Mach Vis Appl 25(2):361\u2013375","journal-title":"Mach Vis Appl"},{"key":"15005_CR83","doi-asserted-by":"crossref","unstructured":"Sitaula C, Aryal S, Xiang Y, Basnet A, Lu X (2021b) Content and context features for scene image representation. Knowledge-Based Systems 107470","DOI":"10.1016\/j.knosys.2021.107470"},{"key":"15005_CR84","doi-asserted-by":"crossref","unstructured":"Sitaula C, Basnet A, Mainali A, Shahi T (2021) Deep learning-based methods for sentiment analysis on nepali covid-19-related tweets. Computational Intelligence and Neuroscience 2021","DOI":"10.1155\/2021\/2158184"},{"issue":"11","key":"15005_CR85","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-022-01868-2","volume":"46","author":"C Sitaula","year":"2022","unstructured":"Sitaula C, Shahi TB (2022) Monkeypox virus detection using pre-trained deep learning-based approaches. J Med Syst 46(11):1\u20139","journal-title":"J Med Syst"},{"key":"15005_CR86","doi-asserted-by":"crossref","unstructured":"Sitaula C, Xiang Y, Aryal S, Lu X (2019) Unsupervised deep features for privacy image classification. In: Proc. pacific-rim symposium on image and video technology (PSIVT), pp 404\u2013415","DOI":"10.1007\/978-3-030-34879-3_31"},{"key":"15005_CR87","doi-asserted-by":"crossref","unstructured":"Sitaula C, Xiang Y, Aryal S, Lu X (2021a) Scene image representation by foreground, background and hybrid features. Expert Systems with Applications 115285","DOI":"10.1016\/j.eswa.2021.115285"},{"key":"15005_CR88","doi-asserted-by":"crossref","unstructured":"Sitaula C, Xiang Y, Basnet A, Aryal S, Lu X (2019) Tag-based semantic features for scene image classification. In: Proc. int. conf. on neural inf. process. (ICONIP), pp 90\u2013102","DOI":"10.1007\/978-3-030-36718-3_8"},{"key":"15005_CR89","doi-asserted-by":"crossref","unstructured":"Sitaula C, Xiang Y, Basnet A, Aryal S, Lu X (2020) HDF: hybrid deep features for scene image representation. In: Proc. int. joint conf. on neural networks (IJCNN","DOI":"10.1109\/IJCNN48605.2020.9207106"},{"key":"15005_CR90","doi-asserted-by":"crossref","first-page":"84,967","DOI":"10.1109\/ACCESS.2019.2925002","volume":"7","author":"C Sitaula","year":"2019","unstructured":"Sitaula C, Xiang Y, Zhang Y, Lu X, Aryal S (2019) Indoor image representation by high-level semantic features. IEEE Access 7:84,967\u201384,979","journal-title":"IEEE Access"},{"key":"15005_CR91","doi-asserted-by":"crossref","unstructured":"Sorkhi AG, Hassanpour H, Fateh M (2020) A comprehensive system for image scene classification. Multimed Tools Appl 1\u201326","DOI":"10.1007\/s11042-019-08264-y"},{"issue":"6","key":"15005_CR92","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.1109\/TCSVT.2018.2848543","volume":"29","author":"N Sun","year":"2018","unstructured":"Sun N, Li W, Liu J, Han G, Wu C (2018) Fusing object semantics and deep appearance features for scene recognition. IEEE Trans Circ Syst Video Technol 29(6):1715\u20131728","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"15005_CR93","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. In: Proc. IEEE conf. comput. vis. pattern recognit. (CVPR), pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"15005_CR94","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.neucom.2016.11.023","volume":"225","author":"P Tang","year":"2017","unstructured":"Tang P, Wang H, Kwong S (2017) G-ms2f: Googlenet based multi-stage feature fusion of deep cnn for scene recognition. Neurocomputing 225:188\u2013197","journal-title":"Neurocomputing"},{"issue":"7","key":"15005_CR95","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1109\/TPAMI.2009.132","volume":"32","author":"JC Van Gemert","year":"2009","unstructured":"Van Gemert JC, Veenman CJ, Smeulders AW, Geusebroek JM (2009) Visual word ambiguity. IEEE Trans Pattern Anal Mach Intell 32(7):1271\u20131283","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"15005_CR96","doi-asserted-by":"crossref","first-page":"2985","DOI":"10.1109\/TMM.2019.2920620","volume":"21","author":"D Wang","year":"2019","unstructured":"Wang D, Mao K (2019) Learning semantic text features for web text-aided image classification. IEEE Trans Multimed 21(12):2985\u20132996","journal-title":"IEEE Trans Multimed"},{"key":"15005_CR97","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.neucom.2018.09.042","volume":"329","author":"D Wang","year":"2019","unstructured":"Wang D, Mao K (2019) Task-generic semantic convolutional neural network for web text-aided image classification. Neurocomputing 329:103\u2013115","journal-title":"Neurocomputing"},{"key":"15005_CR98","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1016\/j.ins.2022.07.188","volume":"610","author":"C Wang","year":"2022","unstructured":"Wang C, Peng G, De Baets B (2022) Joint global metric learning and local manifold preservation for scene recognition. Inf Sci 610:938\u2013956","journal-title":"Inf Sci"},{"issue":"6","key":"15005_CR99","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1109\/TMM.2016.2544099","volume":"18","author":"J Wang","year":"2016","unstructured":"Wang J, Wang W, Wang R, Gao W (2016) Csps: an adaptive pooling method for image classification. IEEE Trans Multimed 18(6):1000\u20131010","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"15005_CR100","doi-asserted-by":"crossref","first-page":"2028","DOI":"10.1109\/TIP.2017.2666739","volume":"26","author":"Z Wang","year":"2017","unstructured":"Wang Z, Wang L, Wang Y, Zhang B, Qiao Y (2017) Weakly supervised patchnets: describing and aggregating local patches for scene recognition. IEEE Trans Image Process 26(4):2028\u20132041","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"15005_CR101","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1007\/s10462-015-9448-4","volume":"45","author":"X Wei","year":"2016","unstructured":"Wei X, Phung SL, Bouzerdoum A (2016) Visual descriptors for scene categorization: experimental evaluation. Artif Intell Rev 45(3):333\u2013368","journal-title":"Artif Intell Rev"},{"issue":"8","key":"15005_CR102","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. IEEE Trans Pattern Anal Mach Intell 33(8):1489\u20131501","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15005_CR103","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":"15005_CR104","doi-asserted-by":"crossref","unstructured":"Xiao J, Hays J, Ehinger KA, Oliva A, Torralba A (2010) Sun database: large-scale scene recognition from abbey to zoo. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp 3485\u20133492","DOI":"10.1109\/CVPR.2010.5539970"},{"issue":"2","key":"15005_CR105","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":"15005_CR106","doi-asserted-by":"crossref","first-page":"69,393","DOI":"10.1109\/ACCESS.2018.2878553","volume":"6","author":"GS Xie","year":"2018","unstructured":"Xie GS, Jin XB, Zhang XY, Zang SF, Yang C, Wang Z, Pu J (2018) From class-specific to class-mixture: cascaded feature representations via restricted boltzmann machine learning. IEEE Access 6:69,393\u201369,406","journal-title":"IEEE Access"},{"key":"15005_CR107","doi-asserted-by":"crossref","unstructured":"Xie L, Lee F, Liu L, Kotani K, Chen Q (2020) Scene recognition: a comprehensive survey. Pattern Recognit 107205","DOI":"10.1016\/j.patcog.2020.107205"},{"key":"15005_CR108","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.patcog.2018.04.025","volume":"82","author":"L Xie","year":"2018","unstructured":"Xie L, Lee F, Liu L, Yin Z, Yan Y, Wang W, Zhao J, Chen Q (2018) Improved spatial pyramid matching for scene recognition. Pattern Recogn 82:118\u2013129","journal-title":"Pattern Recogn"},{"key":"15005_CR109","doi-asserted-by":"crossref","unstructured":"Yang S, Ramanan D (2015) Multi-scale recognition with DAG-CNNs. In: Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp 1215\u20131223","DOI":"10.1109\/ICCV.2015.144"},{"key":"15005_CR110","doi-asserted-by":"crossref","unstructured":"Zabih R, Woodfill J (1994) Non-parametric local transforms for computing visual correspondence. In: Proc. euro. conf. comput. vis. (ECCV), pp 151\u2013158","DOI":"10.1007\/BFb0028345"},{"key":"15005_CR111","doi-asserted-by":"crossref","unstructured":"Zeglazi O, Amine A, Rziza M (2016) Sift descriptors modeling and application in texture image classification. In: Proc. 13th int. Conf. Comput, Graphics, Imaging and Visualization (CGiV), pp 265\u2013268","DOI":"10.1109\/CGiV.2016.58"},{"key":"15005_CR112","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.neucom.2014.03.059","volume":"142","author":"C Zhang","year":"2014","unstructured":"Zhang C, Cheng J, Liu J, Pang J, Liang C, Huang Q, Tian Q (2014) Object categorization in sub-semantic space. Neurocomputing 142:248\u2013255","journal-title":"Neurocomputing"},{"key":"15005_CR113","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.neucom.2012.07.056","volume":"120","author":"C Zhang","year":"2013","unstructured":"Zhang C, Liu J, Tian Q, Liang C, Huang Q (2013) Beyond visual features: a weak semantic image representation using exemplar classifiers for classification. Neurocomputing 120:318\u2013324","journal-title":"Neurocomputing"},{"key":"15005_CR114","doi-asserted-by":"crossref","first-page":"107,167","DOI":"10.1016\/j.patcog.2019.107167","volume":"100","author":"B Zhang","year":"2020","unstructured":"Zhang B, Wang Q, Lu X, Wang F, Li P (2020) Locality-constrained affine subspace coding for image classification and retrieval. Pattern Recognit 100:107,167","journal-title":"Pattern Recognit"},{"issue":"8","key":"15005_CR115","doi-asserted-by":"crossref","first-page":"3241","DOI":"10.1109\/TIP.2014.2328894","volume":"23","author":"L Zhang","year":"2014","unstructured":"Zhang L, Zhen X, Shao L (2014) Learning object-to-class kernels for scene classification. IEEE Trans Image Process 23(8):3241\u20133253","journal-title":"IEEE Trans Image Process"},{"key":"15005_CR116","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.ins.2016.10.019","volume":"376","author":"C Zhang","year":"2017","unstructured":"Zhang C, Zhu G, Huang Q, Tian Q (2017) Image classification by search with explicitly and implicitly semantic representations. Inf Sci 376:125\u2013135","journal-title":"Inf Sci"},{"key":"15005_CR117","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Torralba A, Oliva A (2016) Places: an image database for deep scene understanding. arXiv:161002055","DOI":"10.1167\/17.10.296"},{"issue":"6","key":"15005_CR118","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou B, Lapedriza A, Khosla A, Oliva A, Torralba A (2017) Places: a 10 million image database for scene recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1452\u20131464","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15005_CR119","unstructured":"Zhu J, Li Lj, Fei-Fei L, Xing EP (2010) Large margin learning of upstream scene understanding models. In: Proc. Adv. Neural Inf. Process. Syst. (NIPS), pp 2586\u20132594"},{"issue":"10","key":"15005_CR120","doi-asserted-by":"crossref","first-page":"3004","DOI":"10.1016\/j.patcog.2015.02.003","volume":"48","author":"Z Zuo","year":"2015","unstructured":"Zuo Z, Wang G, Shuai B, Zhao L, Yang Q (2015) Exemplar based deep discriminative and shareable feature learning for scene image classification. Pattern Recogn 48(10):3004\u20133015","journal-title":"Pattern Recogn"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15005-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15005-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15005-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T07:21:39Z","timestamp":1704698499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15005-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,10]]},"references-count":120,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15005"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15005-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,10]]},"assertion":[{"value":"11 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}