{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T19:35:41Z","timestamp":1648928141863},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2014,12,27]],"date-time":"2014-12-27T00:00:00Z","timestamp":1419638400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s11042-014-2420-5","type":"journal-article","created":{"date-parts":[[2014,12,26]],"date-time":"2014-12-26T06:23:16Z","timestamp":1419574996000},"page":"3027-3051","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Weakly-supervised region annotation for understanding scene images"],"prefix":"10.1007","volume":"75","author":[{"given":"Hao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Tong","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Palaiahnakote","family":"Shivakumara","sequence":"additional","affiliation":[]},{"given":"Chew Lim","family":"Tan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,12,27]]},"reference":[{"key":"2420_CR1","unstructured":"Blei DM, McAuliffe JD (2007) Supervised topic models. NIPS"},{"key":"2420_CR2","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res (JMLR) 3:993\u20131022","journal-title":"J Mach Learn Res (JMLR)"},{"key":"2420_CR3","doi-asserted-by":"crossref","unstructured":"Blei DM, Jordan MI (2003) Modeling annotated data. SIGIR, pp 127\u2013134","DOI":"10.1145\/860435.860460"},{"key":"2420_CR4","doi-asserted-by":"crossref","unstructured":"Cao L, Li F-F (2007) Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes. ICCV, pp 1\u20138","DOI":"10.1109\/ICCV.2007.4408965"},{"issue":"5","key":"2420_CR5","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu D, Meer P, Shift M (2002) A robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell (PAMI) 24(5):603\u2013619","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"2420_CR6","doi-asserted-by":"crossref","unstructured":"Crandall DJ, Huttenlocher DP (2007) Composite models of objects and scenes for category recognition. CVPR","DOI":"10.1109\/CVPR.2007.383155"},{"issue":"2","key":"2420_CR7","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis (IJCV) 59(2):167\u2013181","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2420_CR8","unstructured":"Hoiem D, Efros AA, Hebert M Putting Objects in Perspective. CVPR 2006:2137\u20132144"},{"key":"2420_CR9","doi-asserted-by":"crossref","unstructured":"Holzinger A, Malle B, Bloice M, Wiltgen M, Ferri M, Stanganelli I, Hofmann-Wellenhof R (2014). In: Holzinger A, Jurisica I (eds) On the generation of point cloud data sets: the first step in the knowledge discovery process. In interactive knowledge discovery and data mining: state-of-the-art and future challenges in biomedical informatics. Springer Lecture Notes in Computer Science, Berlin, Heidelberg, pp 57\u201380. LNCS 8401","DOI":"10.1007\/978-3-662-43968-5_4"},{"key":"2420_CR10","unstructured":"Holzinger A, Malle B, Giuliani N (2014). In: Slezak D, Peters JF, Tan A-H, Schwabe L (eds) On graph extraction from image data. In brain informatics and health (BIH) 2014, Lecture notes in artificial intelligence, vol 8609. Heidelberg Berlin, LNAI, pp 552\u2013563"},{"issue":"3","key":"2420_CR11","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1007\/s11263-008-0202-0","volume":"82","author":"P Kohli","year":"2009","unstructured":"Kohli P, Ladicky L, Torr PHS (2009) Robust higher order potentials for enforcing label consistency. Int J Comput Vis (IJCV) 82(3):302\u2013324","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2420_CR12","doi-asserted-by":"crossref","unstructured":"Ladicky L, Russell C, Kohli P, Torr PHS Associative hierarchical CRFs for object class image segmentation. ICCV 2009:739-746","DOI":"10.1109\/ICCV.2009.5459248"},{"key":"2420_CR13","unstructured":"Lafferty JD, McCallum A, Pereira FCN Conditional random fields: probabilistic models for segmenting and labeling sequence data. ICML 2001:282-289"},{"key":"2420_CR14","doi-asserted-by":"crossref","unstructured":"LeCun Y, Huang FJ, Bottou L Learning methods for generic object recognition with invariance to pose and lighting. CVPR 2004:97-104","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"2420_CR15","unstructured":"Li L-J, Li F-F (2007) What, where and who? Classifying events by scene and object recognition. ICCV:1\u20138"},{"issue":"3","key":"2420_CR16","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1109\/TSMCB.2003.811120","volume":"33","author":"N Li","year":"2003","unstructured":"Li N, Li YF (2003) Feature encoding for unsupervised segmentation of color images. IEEE Trans Syst Man Cybern Part B (TSMC) 33(3):438\u2013447","journal-title":"IEEE Trans Syst Man Cybern Part B (TSMC)"},{"key":"2420_CR17","doi-asserted-by":"crossref","unstructured":"Lin W, Lu T, Su F (2012) A novel multi-modal integration and propagation model for cross-media information retrieval. MMM, pp 740\u2013749","DOI":"10.1007\/978-3-642-27355-1_78"},{"key":"2420_CR18","unstructured":"Li F-F, Perona P (2005) A bayesian hierarchical model for learning natural scene categories. CVPR:524\u2013531"},{"key":"2420_CR19","unstructured":"Li L-J, Socher R, Li F-F (2009) Towards total scene understanding: Classification, annotation and segmentation in an automatic framework. CVPR, pp 2036\u20132043"},{"issue":"12","key":"2420_CR20","doi-asserted-by":"crossref","first-page":"2368","DOI":"10.1109\/TPAMI.2011.131","volume":"33","author":"C Liu","year":"2011","unstructured":"Liu C, Yuen J, Torralba A (2011) Nonparametric Scene Parsing via Label Transfer. IEEE Trans Pattern Anal Mach Intell (PAMI) 33(12):2368\u20132382","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"issue":"9","key":"2420_CR21","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1109\/TPAMI.2003.1227984","volume":"25","author":"J Li","year":"2003","unstructured":"Li J, Wang JZ (2003) Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans Pattern Anal Mach Intell (PAMI) 25(9):1075\u20131088","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"2420_CR22","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. ICCV:1150\u20131157","DOI":"10.1109\/ICCV.1999.790410"},{"key":"2420_CR23","doi-asserted-by":"crossref","unstructured":"Lu T, Jin Y, Su F, Shivakumara P, Tan CL Content-oriented multimedia document understanding through cross-media correlation. Multimedia Tools and Applications, to appear","DOI":"10.1007\/s11042-014-2044-9"},{"issue":"3","key":"2420_CR24","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/TSMCB.2005.846677","volume":"35","author":"J Luo","year":"2005","unstructured":"Luo J, Boutell MR, Gray RT, Brown CM (2005) Image transform bootstrapping and its applications to semantic scene classification. IEEE Trans Syst Man Cybern Part B (TSMC) 35(3): 563\u2013570","journal-title":"IEEE Trans Syst Man Cybern Part B (TSMC)"},{"issue":"9","key":"2420_CR25","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.1109\/TPAMI.2011.268","volume":"34","author":"A Marco","year":"2012","unstructured":"Marco A, Lihi Z-M, Pietro P (2012) Unsupervised learning of categorical segments in image collections. IEEE Trans Pattern Anal Mach Intell (PAMI) 34(9):1842\u20131855","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"2420_CR26","doi-asserted-by":"crossref","unstructured":"Malisiewicz T, Efros AA (2008) Recognition by association via learning per-exemplar distances. CVPR","DOI":"10.1109\/CVPR.2008.4587462"},{"key":"2420_CR27","unstructured":"Ma X, Lu T, Xu F, Su F (2012) Anomaly detection with spatio-temporal context using depth images. ICPR, pp 2590\u20132593"},{"issue":"1","key":"2420_CR28","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1023\/B:VISI.0000027790.02288.f2","volume":"60","author":"K Mikolajczyk","year":"2004","unstructured":"Mikolajczyk K, Schmid C (2004) Scale Affine Invariant Interest Point Detectors. Int J Comput Vis (IJCV) 60(1):63\u201386","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2420_CR29","unstructured":"Niu Z, Hua G, Gao X, Tian Q (2012) Context aware topic model for scene recognition. CVPR, pp 2743\u20132750"},{"issue":"3","key":"2420_CR30","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 (IJCV) 42(3):145\u2013175","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2420_CR31","doi-asserted-by":"crossref","unstructured":"Rabinovich A, Vedaldi A, Galleguillos C, Wiewiora E, Belongie S Objects in Context. ICCV 2007:1-8","DOI":"10.1109\/ICCV.2007.4408986"},{"issue":"1-3","key":"2420_CR32","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"BC Russell","year":"2008","unstructured":"Russell BC, Torralba A, Murphy KP, Freeman WT (2008) LabelMe: a database and web-based tool for image annotation. Int J Comput Vis (IJCV) 77(1-3):157\u2013173","journal-title":"Int J Comput Vis (IJCV)"},{"issue":"8","key":"2420_CR33","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell (PAMI) 22(8):888\u2013905","journal-title":"IEEE Trans Pattern Anal Mach Intell (PAMI)"},{"key":"2420_CR34","doi-asserted-by":"crossref","unstructured":"Shotton J, Johnson M, Cipolla R Semantic texton forests for image categorization and segmentation. CVPR 2008","DOI":"10.1109\/CVPR.2008.4587503"},{"issue":"1","key":"2420_CR35","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","volume":"81","author":"J Shotton","year":"2009","unstructured":"Shotton J, Winn JM, Rother C, Criminisi A (2009) TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context. Int J Comput Vis (IJCV) 81(1):2\u201323","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2420_CR36","unstructured":"Sivic J, Russell BC, Efros AA, Zisserman A, Freeman WT Discovering Object Categories in Image Collections. ICCV 2005:65-76."},{"issue":"1-3","key":"2420_CR37","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/s11263-007-0069-5","volume":"77","author":"EB Sudderth","year":"2008","unstructured":"Sudderth EB, Torralba A, Freeman WT, Willsky AS (2008) Describing Visual Scenes Using Transformed Objects and Parts. Int J Comput Vis (IJCV) 77(1-3):291\u2013330","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2420_CR38","doi-asserted-by":"crossref","unstructured":"Su F, Yang L, Lu T, Wang G (2011) Environmental sound classification for scene recognition using local discriminant bases and HMM. ACM Multimedia, pp 1389\u20131392","DOI":"10.1145\/2072298.2072022"},{"issue":"5","key":"2420_CR39","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1109\/TSMCB.2007.902249","volume":"37","author":"W Tao","year":"2007","unstructured":"Tao W, Jin H, Zhang Y (2007) Color image segmentation based on mean shift and normalized cuts. IEEE Trans Syst Man, Cybern Part B (TSMC) 37(5):1382\u20131389","journal-title":"IEEE Trans Syst Man, Cybern Part B (TSMC)"},{"key":"2420_CR40","doi-asserted-by":"crossref","unstructured":"Tighe J, Lazebnik S (2010) SuperParsing: Scalable Nonparametric Image Parsing with Superpixels. ECCV, pp 352\u2013365","DOI":"10.1007\/978-3-642-15555-0_26"},{"key":"2420_CR41","unstructured":"Torralba A, Murphy KP, Freeman WT Contextual models for object detection using boosted random fields. NIPS 2004"},{"key":"2420_CR42","unstructured":"Jakob JV, Bill T (2007) Region classification with markov field aspect models. CVPR"},{"key":"2420_CR43","doi-asserted-by":"crossref","unstructured":"Vezhnevets A, Ferrari V, Buhmann JM (2011) Weakly supervised semantic segmentation with a multi-image model. ICCV, pp 643\u2013650","DOI":"10.1109\/ICCV.2011.6126299"},{"key":"2420_CR44","doi-asserted-by":"crossref","unstructured":"Vezhnevets A, Ferrari V, Buhmann JM (2012) Weakly supervised structured output learning for semantic segmentation. CVPR, pp 845\u2013852","DOI":"10.1109\/CVPR.2012.6247757"},{"key":"2420_CR45","doi-asserted-by":"crossref","unstructured":"Wang L, Wu Y, Lu T, Chen K (2011) Multiclass object detection by combining local appearances and context. ACM Multimedia, pp 1161\u20131164","DOI":"10.1145\/2072298.2071964"},{"key":"2420_CR46","first-page":"661","volume":"6","author":"JM Winn","year":"2005","unstructured":"Winn JM, Bishop CM (2005) Variational message passing. J Mach Learn Res (JMLR) 6:661\u2013694","journal-title":"J Mach Learn Res (JMLR)"},{"issue":"2","key":"2420_CR47","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","volume":"73","author":"J Zhang","year":"2007","unstructured":"Zhang J, Marszalek M, Lazebnik S, Schmid C (2007) Local features and kernels for classification of texture and object categories: a comprehensive study. Int J Comput Vis (IJCV) 73(2):213\u2013238","journal-title":"Int J Comput Vis (IJCV)"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2420-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-2420-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2420-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,19]],"date-time":"2019-08-19T00:54:21Z","timestamp":1566176061000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-2420-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12,27]]},"references-count":47,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["2420"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-2420-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12,27]]}}}