{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:37:32Z","timestamp":1777703852577,"version":"3.51.4"},"reference-count":26,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2019,7,27]],"date-time":"2019-07-27T00:00:00Z","timestamp":1564185600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,10,25]]},"abstract":"<jats:p>Automatic Image Annotation (AIA) aims to provide a semantic description for the content of image by assigning a set of textual labels. The recent approaches mainly focus on the improvement of single model and neglect the potential advantages of different models. In order to make full use of the advantages of different annotation models, Dual Model based on Multi-Label Selection Algorithm(DM-SA) is proposed in this research which combines a discriminative model with a nearest-neighbor-based model. The algorithm takes consideration of the advantages of each model, thus provides better annotation performance. A deep Convolutional Neural Network (CNN) is used to obtain visual representation of images first, then a discriminative model, CNN with Label Smoothing (CNN-LS), and a nearest-neighbor-based model, 2PKNN with Canonical Correlation Analysis (2PKNN-CCA) generate candidate label set respectively. Finally, a multi-label selection algorithm based on inverse document frequency is adopted to assign the final labels from two candidate label sets. Experimental results based on Corel5K and IAPRTC-12 datasets show that the proposed method can achieve state-of-the-art performance for average recall, 0.52 and 0.42 on Corel5K and IAPRTC-12 respectively.<\/jats:p>","DOI":"10.3233\/jifs-182587","type":"journal-article","created":{"date-parts":[[2019,7,30]],"date-time":"2019-07-30T11:28:29Z","timestamp":1564486109000},"page":"4999-5008","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic image annotation using model fusion and multi-label selection algorithm"],"prefix":"10.1177","volume":"37","author":[{"given":"Liqin","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin, China"},{"name":"Hebei Province Key Laboratory of Big Data Calculation (Hebei University of Technology), Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aofan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin, China"},{"name":"Hebei Province Key Laboratory of Big Data Calculation (Hebei University of Technology), Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin, China"},{"name":"Hebei Province Key Laboratory of Big Data Calculation (Hebei University of Technology), Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2019,7,27]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"M. Meeker Internet Trends -Code Conference Los Angeles: Kleiner Perkins Caufield & Byers (2018). https:\/\/www.kleinerperkins.com\/files\/INTERNET_TRENDS_REPORT_2018.pdf."},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"MurthyV.N. CanE.F. and ManmathaR. A hybrid model for automatic image annotation Proceedings of International Conference on Multimedia Retrieval 2014 pp. 369\u2013373.","DOI":"10.1145\/2578726.2578774"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.05.013"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"WangC. ZhangL. and ZhangH.J. Learning to reduce the semantic gap in web image retrieval and annotation Proceedings of the 31st International ACM SIGIR Conference on Research and Development in Information Retrieval Singapore 2008 pp.\u00a0355\u2013362.","DOI":"10.1145\/1390334.1390396"},{"issue":"11","key":"e_1_3_2_6_2","first-page":"2483","article-title":"Multi-view mixed-norm sparse coding for image annotation","volume":"7","author":"Zang M","year":"2016","unstructured":"ZangM, XuH.M. and ZhangY.M., Multi-view mixed-norm sparse coding for image annotation, ICIC Express Letters Part B: Applications 7(11) (2016), 2483\u20132490.","journal-title":"ICIC Express Letters Part B: Applications"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"DongC. ChenC.L. and HeK. Image Super-Resolution Using Deep Convolutional Networks Proceedings of IEEE Trans Pattern Anal Mach Intell 2016 pp.\u00a0295\u2013307.","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_3_2_9_2","unstructured":"KrizhevskyA. SutskeverI. and HintonG.E. ImageNet classification with deep convolutional neural networks Proceedings of International Conference on Neural Information Processing Systems Curran Associates 2012 pp.\u00a01097\u20131105."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. and SunJ. Deep Residual Learning for Image Recognition Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 pp.\u00a0770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"VermaY. and JawaharC.V. Image Annotation Using Metric Learning in Semantic Neighbourhoods Proceedings of European Conference on Computer Vision 2012 pp.\u00a0836\u2013849.","DOI":"10.1007\/978-3-642-33712-3_60"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"MurthyV.N. VenkateshN.S. and ManmathaR. Automatic Image Annotation using Deep Learning Representations Proceedings of ACM on International Conference on Multimedia Retrieval 2015 pp.\u00a0603\u2013606.","DOI":"10.1145\/2671188.2749391"},{"issue":"11","key":"e_1_3_2_13_2","first-page":"3199","article-title":"Automatic image annotation based on transfer learning and multi-label smoothing strategy","volume":"38","author":"Wang P.","year":"2018","unstructured":"WangP., ZhangA. and WangL., Automatic image annotation based on transfer learning and multi-label smoothing strategy, Journal of Computer Applications 38(11) (2018), 3199\u20133203.","journal-title":"Journal of Computer Applications"},{"issue":"1","key":"e_1_3_2_14_2","first-page":"1","article-title":"A domain keyword analysis approach extending term frequency-keyword active index with google word2Vec model","volume":"114","author":"Kai H.","year":"2018","unstructured":"KaiH., WuH. and QiK., A domain keyword analysis approach extending term frequency-keyword active index with google word2Vec model, Scientometrics 114(1) (2018), 1\u201338.","journal-title":"Scientometrics"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560582"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.07.012"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"JeonJ. LavrenkoV. and ManmathaR. Automatic image annotation and retrieval using cross-media relevance models Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval 2003 pp.\u00a0119\u2013126.","DOI":"10.1145\/860435.860459"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"FengS.L. ManmathaR. and LavrenkoV. Multiple bernoulli relevance models for image and video annotation Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2004 pp.\u00a01002\u20131009.","DOI":"10.1109\/CVPR.2004.1315274"},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Ngo-TienD. Ngo-TienD. and Ngo-TienD. Fully automated multi-label image annotation by convolutional neural network and adaptive thresholding Proceedings of the Seventh Symposium on Information and Communication Technology ACM 2016 pp.\u00a0323\u2013330.","DOI":"10.1145\/3011077.3011118"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Kalayeh MahdiM. IdreesH. and ShahM. NMF-KNN: Image Annotation Using Weighted Multi-view Non-negative Matrix Factorization Proeceedings of IEEE Conference on Computer Vision and Pattern Recognition 2014 pp.\u00a0184\u2013191.","DOI":"10.1109\/CVPR.2014.31"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"LiJ. and YuanC. Automatic Image Annotation Using Adaptive Weighted Distance in Improved K Nearest Neighbors Framework Proceedings of Pacific Rim Conference on Multimedia 2016 pp.\u00a0345\u2013354.","DOI":"10.1007\/978-3-319-48890-5_34"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.10.017"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"KashaniM.M. and AmiriS.H. Leveraging deep learning representation for search-based image annotation Proceedings of 2017 Artificial Intelligence and Signal Processing Conference (AISP) 2017 pp.\u00a0156\u2013161.","DOI":"10.1109\/AISP.2017.8324073"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"WuB. ChenW. and SunP. Tagging like Humans: Diverse and Distinct Image Annotation Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 2018 pp.\u00a07967\u20137975.","DOI":"10.1109\/CVPR.2018.00831"},{"issue":"2","key":"e_1_3_2_25_2","first-page":"23:1","article-title":"A survey on ensemble learning for data stream classification","volume":"50","author":"Barddal J.P.","year":"2017","unstructured":"BarddalJ.P. and BifetA., A survey on ensemble learning for data stream classification, ACM Computing Surveys 50(2) (2017), 23:1\u201323:36.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_2_26_2","first-page":"249","author":"Glorot X.","year":"2010","unstructured":"GlorotX. and BengioY., Understanding the difficulty of training deep feedforward neural networks, Proceedings of AISTATS, 2010, pp.\u00a0249\u2013256.","journal-title":"Understanding the difficulty of training deep feedforward neural networks"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-014-0063-y"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-182587","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-182587","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-182587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:39:47Z","timestamp":1777455587000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-182587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,27]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,10,25]]}},"alternative-id":["10.3233\/JIFS-182587"],"URL":"https:\/\/doi.org\/10.3233\/jifs-182587","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,27]]}}}