{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:01:59Z","timestamp":1782388919348,"version":"3.54.5"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030367176","type":"print"},{"value":"9783030367183","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36718-3_8","type":"book-chapter","created":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T03:03:52Z","timestamp":1575947032000},"page":"90-102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Tag-Based Semantic Features for Scene Image Classification"],"prefix":"10.1007","author":[{"given":"Chiranjibi","family":"Sitaula","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anish","family":"Basnet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunil","family":"Aryal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuequan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","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.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"8_CR2","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 886\u2013893 (2005)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings IEEE Conference Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8_CR4","unstructured":"Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 524\u2013531, June 2005"},{"key":"8_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-319-10584-0_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Gong","year":"2014","unstructured":"Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 392\u2013407. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10584-0_26"},{"issue":"2","key":"8_CR6","doi-asserted-by":"publisher","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.: Locally supervised deep hybrid model for scene recognition. IEEE Trans. Image Process. 26(2), 808\u2013820 (2017)","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"8_CR7","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1109\/TMM.2017.2766842","volume":"20","author":"Y Guo","year":"2018","unstructured":"Guo, Y., Liu, Y., Lao, S., Bakker, E.M., Bai, L., Lew, M.S.: Bag of surrogate parts feature for visual recognition. IEEE Trans. Multimedia 20(6), 1525\u20131536 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"8_CR8","volume-title":"Clustering Algorithms","author":"JA Hartigan","year":"1975","unstructured":"Hartigan, J.A.: Clustering Algorithms, 99th edn. Wiley, New York (1975)","edition":"99"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"8_CR10","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","volume":"13","author":"MA Hearst","year":"1998","unstructured":"Hearst, M.A.: Support vector machines. IEEE Intell. Syst. 13(4), 18\u201328 (1998)","journal-title":"IEEE Intell. Syst."},{"key":"8_CR11","unstructured":"Huang, A.: Similarity measures for text document clustering. In: Proceedings of Sixth New Zealand Computer Science Research Student Conference (NZCSRSC 2008), pp. 9\u201356 (2008)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Juneja, M., Vedaldi, A., Jawahar, C., Zisserman, A.: Blocks that shout: distinctive parts for scene classification. In: Proceedings of IEEE Conference Computer Vision Pattern Recognition (CVPR), pp. 923\u2013930, June 2013","DOI":"10.1109\/CVPR.2013.124"},{"issue":"7","key":"8_CR13","doi-asserted-by":"publisher","first-page":"3372","DOI":"10.1109\/TIP.2016.2567076","volume":"25","author":"SH Khan","year":"2016","unstructured":"Khan, S.H., Hayat, M., Bennamoun, M., Togneri, R., Sohel, F.A.: A discriminative representation of convolutional features for indoor scene recognition. IEEE Trans. Image Process. 25(7), 3372\u20133383 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint \narXiv:1408.5882\n\n (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Kuzborskij, I., Maria Carlucci, F., Caputo, B.: When Naive Bayes nearest neighbors meet convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2100\u20132109 (2016)","DOI":"10.1109\/CVPR.2016.231"},{"key":"8_CR16","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE Computer Society Conference on Computer Vision Pattern Recognition, pp. 2169\u20132178, June 2006"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Li, L.J., Li, F.F.: What, where and who? Classifying events by scene and object recognition. In: ICCV, vol. 2, p. 6 (2007)","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"8_CR18","unstructured":"Li, L.J., Su, H., Fei-Fei, L., Xing, E.P.: Object bank: a high-level image representation for scene classification & semantic feature sparsification. In: Proceedings of Advance Neural Information Processing Systems (NIPS), pp. 1378\u20131386 (2010)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Lin, D., Lu, C., Liao, R., Jia, J.: Learning important spatial pooling regions for scene classification. In: Proceedings of IEEE Conference Computer Vision Pattern Recognition (CVPR), pp. 3726\u20133733, June 2014","DOI":"10.1109\/CVPR.2014.476"},{"issue":"6","key":"8_CR20","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TPAMI.2017.2723400","volume":"40","author":"TY Lin","year":"2018","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear convolutional neural networks for fine-grained visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1309\u20131322 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/978-3-319-10584-0_25","volume-title":"Computer Vision \u2013 ECCV 2014","author":"R Margolin","year":"2014","unstructured":"Margolin, R., Zelnik-Manor, L., Tal, A.: OTC: a novel local descriptor for scene classification. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 377\u2013391. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10584-0_25"},{"key":"8_CR22","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint \narXiv:1301.3781\n\n (2013)"},{"issue":"11","key":"8_CR23","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Oliva, A.: Gist of the scene. In: Neurobiology of Attention, pp. 251\u2013256. Elsevier (2005)","DOI":"10.1016\/B978-012375731-9\/50045-8"},{"issue":"3","key":"8_CR25","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42(3), 145\u2013175 (2001)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Parizi, N., Oberlin, J.G., Felzenszwalb, P.F.: Reconfigurable models for scene recognition. In: Proceedings of Computer Vision Pattern Recognition (CVPR), pp. 2775\u20132782, June 2012","DOI":"10.1109\/CVPR.2012.6248001"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Patel, A., Sands, A., Callison-Burch, C., Apidianaki, M.: Magnitude: a fast, efficient universal vector embedding utility package. In: Proceedings Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 120\u2013126 (2018)","DOI":"10.18653\/v1\/D18-2021"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"8_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010). \nhttps:\/\/doi.org\/10.1007\/978-3-642-15561-1_11"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: Proceedings of IEEE Conference Computer Vision Pattern Recognition (CVPR), pp. 413\u2013420, June 2009","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"8_CR31","unstructured":"ShenghuaGao, I.H., Liang-TienChia, P.: Local features are not lonely-Laplacian sparse coding for image classification, pp. 3555\u20133561 (2010)"},{"key":"8_CR32","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-030-34879-3_31","volume-title":"Image and Video Technology","author":"Chiranjibi Sitaula","year":"2019","unstructured":"Sitaula, C., Xiang, Y., Aryal, S., Lu, X.: Unsupervised deep features for privacy image classification. arXiv preprint \narXiv:1909.10708\n\n (2019)"},{"key":"8_CR33","doi-asserted-by":"publisher","first-page":"84967","DOI":"10.1109\/ACCESS.2019.2925002","volume":"7","author":"C Sitaula","year":"2019","unstructured":"Sitaula, C., Xiang, Y., Zhang, Y., Lu, X., Aryal, S.: Indoor image representation by high-level semantic features. IEEE Access 7, 84967\u201384979 (2019)","journal-title":"IEEE Access"},{"key":"8_CR34","doi-asserted-by":"publisher","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.: G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition. Neurocomputing 225, 188\u2013197 (2017)","journal-title":"Neurocomputing"},{"key":"8_CR35","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neucom.2018.09.042","volume":"329","author":"D Wang","year":"2019","unstructured":"Wang, D., Mao, K.: Task-generic semantic convolutional neural network for web text-aided image classification. Neurocomputing 329, 103\u2013115 (2019)","journal-title":"Neurocomputing"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Wang, D., Mao, K.: Learning semantic text features for web text aided image classification. IEEE Trans. Multimedia PP, 1 (2019)","DOI":"10.1109\/TMM.2019.2920620"},{"issue":"8","key":"8_CR37","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2010.224","volume":"33","author":"J Wu","year":"2011","unstructured":"Wu, J., Rehg, J.M.: CENTRIST: a visual descriptor for scene categorization. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1489\u20131501 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"8_CR38","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1109\/TIP.2013.2295756","volume":"23","author":"Y Xiao","year":"2014","unstructured":"Xiao, Y., Wu, J., Yuan, J.: mCENTRIST: a multi-channel feature generation mechanism for scene categorization. IEEE Trans. Image Process. 23(2), 823\u2013836 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Zeglazi, O., Amine, A., Rziza, M.: Sift descriptors modeling and application in texture image classification. In: Proceedings of 13th International Conference Computer Graphics, Imaging and Visualization (CGiV), pp. 265\u2013268, March 2016","DOI":"10.1109\/CGiV.2016.58"},{"key":"8_CR40","doi-asserted-by":"publisher","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.: Image classification by search with explicitly and implicitly semantic representations. Inf. Sci. 376, 125\u2013135 (2017)","journal-title":"Inf. Sci."},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Torralba, A., Oliva, A.: Places: An image database for deep scene understanding. arXiv preprint \narXiv:1610.02055\n\n (2016)","DOI":"10.1167\/17.10.296"},{"key":"8_CR42","unstructured":"Zhu, J., Li, L.J., Fei-Fei, L., Xing, E.P.: Large margin learning of upstream scene understanding models. In: Proceedings of Advance Neural Information Processing Systems (NIPS), pp. 2586\u20132594 (2010)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36718-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T03:11:21Z","timestamp":1575947481000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36718-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367176","9783030367183"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36718-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}