{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T04:14:08Z","timestamp":1649218448630},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2011,2,5]],"date-time":"2011-02-05T00:00:00Z","timestamp":1296864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2012,9]]},"DOI":"10.1007\/s11263-011-0423-5","type":"journal-article","created":{"date-parts":[[2011,2,4]],"date-time":"2011-02-04T17:22:41Z","timestamp":1296840161000},"page":"302-318","source":"Crossref","is-referenced-by-count":1,"title":["Fast Structured Prediction Using Large Margin Sigmoid Belief Networks"],"prefix":"10.1007","volume":"99","author":[{"given":"Xu","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajesh P. N.","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,2,5]]},"reference":[{"issue":"3\u20134","key":"423_CR1","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.specom.2003.11.002","volume":"42","author":"S. Abdou","year":"2004","unstructured":"Abdou, S., & Scordilis, M. S. (2004). Beam search pruning in speech recognition using a posterior probability-based confidence measure. Speech Communication, 42(3\u20134), 409\u2013428.","journal-title":"Speech Communication"},{"key":"423_CR2","first-page":"463","volume":"3","author":"P. L. Bartlett","year":"2002","unstructured":"Bartlett, P. L., & Mendelson, S. (2002). Rademacher and Gaussian complexities: risk bounds and structural results. Journal of Machine Learning Research, 3, 463\u2013482.","journal-title":"Journal of Machine Learning Research"},{"key":"423_CR3","volume-title":"Advances in neural information processing systems","author":"Y. Bengio","year":"2007","unstructured":"Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007). Greedy layer-wise training of deep networks. In Advances in neural information processing systems. Cambridge: MIT Press."},{"key":"423_CR4","first-page":"161","volume-title":"Advances in neural information processing systems","author":"L. Bottou","year":"2008","unstructured":"Bottou, L., & Bousquet, O. (2008). The tradeoffs of large scale learning. In J. Platt, D. Koller, Y. Singer, & S. Roweis (Eds.), Advances in neural information processing systems (Vol. 20, pp. 161\u2013168)."},{"key":"423_CR5","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1016\/j.patcog.2004.03.009","volume":"37","author":"M. R. Boutell","year":"2004","unstructured":"Boutell, M. R., Luo, J., Shen, X., & Brown, C. M. (2004). Learning multi-label scene classification. Pattern Recognition, 37, 1757\u20131771.","journal-title":"Pattern Recognition"},{"issue":"3","key":"423_CR6","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TPAMI.2007.61","volume":"29","author":"G. Carneiro","year":"2007","unstructured":"Carneiro, G., Chan, A., Moreno, P., & Vasconcelos, N. (2007). Supervised learning of semantic classes for image annotation and retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(3), 394\u2013410.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"423_CR7","first-page":"1775","volume":"9","author":"M. Collins","year":"2008","unstructured":"Collins, M., Globerson, A., Koo, T., Carreras, X., & Bartlett, P. L. (2008). Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks. Journal of Machine Learning Research, 9, 1775\u20131822.","journal-title":"Journal of Machine Learning Research"},{"key":"423_CR8","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1145\/765568.765570","volume":"50","author":"A. Darwiche","year":"2003","unstructured":"Darwiche, A. (2003). A differential approach to inference in Bayesian networks. Journal of the ACM, 50, 123\u2013132.","journal-title":"Journal of the ACM"},{"issue":"3","key":"423_CR9","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s10994-009-5106-x","volume":"75","author":"H. Daum\u00e9 III","year":"2009","unstructured":"Daum\u00e9 III, H., Langford, J., & Marcu, D. (2009). Search-based structured prediction. Machine Learning Journal, 75(3), 297\u2013325.","journal-title":"Machine Learning Journal"},{"key":"423_CR10","first-page":"176","volume-title":"Annual conference on uncertainty in artificial intelligence","author":"A. Doucet","year":"2000","unstructured":"Doucet, A., de Freitas, N., Murphy, K. P., & Russell, S. J. (2000). Rao-Blackwellised particle filtering for dynamic Bayesian networks. In Annual conference on uncertainty in artificial intelligence (pp. 176\u2013183)."},{"key":"423_CR11","series-title":"Lecture notes in computer science","first-page":"349","volume-title":"European conference on computer vision","author":"P. Duygulu","year":"2006","unstructured":"Duygulu, P., Barnard, K., de Freitas, J., & Forsyth, D. (2006). Object recognition as machine translation: learning a lexicon for a fixed image vocabulary. In A. Heyden, G. Sparr, M. Nielsen, & P.\u00a0Johansen (Eds.), Lecture notes in computer science: Vol. 2353. European conference on computer vision (pp. 349\u2013354). Berlin: Springer."},{"key":"423_CR12","unstructured":"Fan, R. E., & Lin, C. J. (2007). A study on threshold selection for multi-label classification (Tech. rep.). National Taiwan University."},{"key":"423_CR13","volume-title":"Computer vision and pattern recognition","author":"S. Feng","year":"2004","unstructured":"Feng, S., Manmatha R., & Lavrenko, V. (2004). Multiple Bernoulli relevance models for image and video annotation. In Computer vision and pattern recognition."},{"key":"423_CR14","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1145\/1390156.1390195","volume-title":"International conference on machine learning","author":"T. Finley","year":"2008","unstructured":"Finley, T., & Joachims, T. (2008). Training structural SVMs when exact inference is intractable. In International conference on machine learning (pp. 304\u2013311). New York: ACM."},{"key":"423_CR15","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/ICCV.2009.5459266","volume-title":"International conference on computer vision","author":"M. Guillaumin","year":"2009","unstructured":"Guillaumin, M., Mensink, T., Verbeek, J., & Schmid, C. (2009). Tagprop: discriminative metric learning in nearest neighbor models for image auto-annotation. In International conference on computer vision (pp. 309\u2013316)."},{"key":"423_CR16","volume-title":"Annual conference on uncertainty in artificial intelligence","author":"Y. Guo","year":"2005","unstructured":"Guo, Y., Wilkinson, D., & Schuurmans, D. (2005). Maximum margin Bayesian networks. In Annual conference on uncertainty in artificial intelligence."},{"key":"423_CR17","first-page":"448","volume-title":"Computer vision and pattern recognition","author":"G. E. Hinton","year":"1983","unstructured":"Hinton, G. E., & Sejnowski, T. J. (1983). Optimal perceptual inference. In Computer vision and pattern recognition (pp. 448\u2013453)."},{"key":"423_CR18","first-page":"271","volume-title":"ACM conference on information and knowledge management","author":"G. Hoefel","year":"2008","unstructured":"Hoefel, G., & Elkan, C. (2008). Learning a two-stage SVM\/CRF sequence classifier. In ACM conference on information and knowledge management (pp. 271\u2013278). New York, NY, USA."},{"key":"423_CR19","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1145\/1390156.1390208","volume-title":"International conference on machine learning","author":"C. J. Hsieh","year":"2008","unstructured":"Hsieh, C. J., Chang, K. W., Lin, C. J., Keerthi, S. S., & Sundararajan,\u00a0S. (2008). A dual coordinate descent method for large-scale linear SVM. In International conference on machine learning (pp. 408\u2013415). New York: ACM."},{"issue":"1","key":"423_CR20","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10994-009-5108-8","volume":"77","author":"T. Joachims","year":"2009","unstructured":"Joachims, T., Finley, T., & Yu, C. N. J. (2009). Cutting-plane training of structural SVMs. Machine Learning, 77(1), 27\u201359.","journal-title":"Machine Learning"},{"key":"423_CR21","unstructured":"Kassel, R. H. (1995). A comparison of approaches to on-line handwritten character recognition. PhD thesis, Cambridge, MA, USA."},{"key":"423_CR22","first-page":"185","volume-title":"European conference on computer vision","author":"V. Kolmogorov","year":"2002","unstructured":"Kolmogorov, V., & Zabih, R. (2002). What energy functions can be minimized via graph cuts? In European conference on computer vision (pp. 185\u2013208)."},{"key":"423_CR23","volume-title":"Advances in neural information processing systems","author":"A. Kulesza","year":"2007","unstructured":"Kulesza, A., & Pereira, F. (2007). Structured learning with approximate inference. In Advances in neural information processing systems."},{"key":"423_CR24","volume-title":"International conference on machine learning","author":"J. Lafferty","year":"2001","unstructured":"Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: probabilistic models for segmenting and labeling sequence data. In International conference on machine learning."},{"key":"423_CR25","volume-title":"Advances in neural information processing systems","author":"V. Lavrenko","year":"2003","unstructured":"Lavrenko, V., Manmatha, R., & Jeon, J. (2003). A model for learning the semantics of pictures. In Advances in neural information processing systems. Cambridge: MIT Press."},{"key":"423_CR26","volume-title":"Computer vision and pattern recognition","author":"S. Lazebnik","year":"2006","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."},{"key":"423_CR27","volume-title":"Predicting structured data","author":"Y. LeCun","year":"2006","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., Huang, F. J., Bakir, G., Hofman, T., Sch\u00f6lkopf, B., Smola, A., & Taskar, B. (Eds.) (2006). A tutorial on energy-based learning. In Predicting structured data. Cambridge: MIT Press."},{"key":"423_CR28","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.patcog.2008.04.012","volume":"42","author":"J. Liu","year":"2009","unstructured":"Liu, J., Li, M., Liu, Q., Lu, H., & Ma, S. (2009). Image annotation via graph learning. Pattern Recognition, 42, 218\u2013228.","journal-title":"Pattern Recognition"},{"key":"423_CR29","first-page":"383","volume-title":"Annual conference on uncertainty in artificial intelligence","author":"D. Lowd","year":"2008","unstructured":"Lowd, D., & Domingos, P. (2008). Learning arithmetic circuits. In Annual conference on uncertainty in artificial intelligence (pp. 383\u2013392). Corvallis: AUAI Press."},{"key":"423_CR30","first-page":"316","volume-title":"European conference on computer vision","author":"A. Makadia","year":"2008","unstructured":"Makadia, A., Pavlovic, V., & Kumar, S. (2008). A new baseline for image annotation. In European conference on computer vision (pp.\u00a0316\u2013329). Berlin: Springer."},{"key":"423_CR31","first-page":"591","volume-title":"Proc. 17th international conf. on machine learning","author":"A. McCallum","year":"2000","unstructured":"McCallum, A., Freitag, D., & Pereira, F. (2000). Maximum entropy Markov models for information extraction and segmentation. In Proc. 17th international conf. on machine learning (pp. 591\u2013598). San Francisco: Morgan Kaufmann."},{"key":"423_CR32","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/978-3-540-27814-6_9","volume-title":"The international conference on image and video retrieval","author":"D. Metzler","year":"2004","unstructured":"Metzler, D., & Manmatha, R. (2004). An inference network approach to image retrieval. In The international conference on image and video retrieval (pp. 42\u201350). Berlin: Springer."},{"key":"423_CR33","first-page":"1156","volume-title":"International joint conference on artificial intelligence","author":"X. Miao","year":"2009","unstructured":"Miao, X., & Rao, R. P. (2009). Large margin Boltzmann machines. In International joint conference on artificial intelligence (pp.\u00a01156\u20131162)."},{"issue":"1","key":"423_CR34","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/0004-3702(92)90065-6","volume":"56","author":"R. M. Neal","year":"1992","unstructured":"Neal, R. M. (1992). Connectionist learning of belief networks. Artificial Intelligence, 56(1), 71\u2013113.","journal-title":"Artificial Intelligence"},{"key":"423_CR35","volume-title":"Conditional graphical models","author":"F. Perez-Cruz","year":"2007","unstructured":"Perez-Cruz, F., Ghahramani, Z., & Pontil, M. (2007). Conditional graphical models. Cambridge: MIT Press."},{"key":"423_CR36","first-page":"1097","volume-title":"Advances in neural information processing systems","author":"A. Quattoni","year":"2004","unstructured":"Quattoni, A., Collins, M., & Darrell, T. (2004). Conditional random fields for object recognition. In Advances in neural information processing systems (pp. 1097\u20131104). Cambridge: MIT Press."},{"key":"423_CR37","first-page":"318","volume-title":"Annual conference on uncertainty in artificial intelligence","author":"D. Rosenberg","year":"2007","unstructured":"Rosenberg, D., Klein, D., & Taskar, B. (2007). Mixture-of-parents maximum entropy Markov models. In Annual conference on uncertainty in artificial intelligence (pp. 318\u2013325). Corvallis: AUAI Press."},{"issue":"1","key":"423_CR38","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"B. Russell","year":"2008","unstructured":"Russell, B., Torralba, A., Murphy, K., & Freeman, W. (2008). Labelme: a database and web-based tool for image annotation. International Journal of Computer Vision, 77(1), 157\u2013173.","journal-title":"International Journal of Computer Vision"},{"key":"423_CR39","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1145\/1273496.1273598","volume-title":"International conference on machine learning","author":"S. Shalev-Shwartz","year":"2007","unstructured":"Shalev-Shwartz, S., Singer, Y., & Srebro, N. (2007). Pegasos: primal estimated sub-gradient solver for SVM. In International conference on machine learning (pp. 807\u2013814). New York: ACM."},{"key":"423_CR40","volume-title":"Advances in neural information processing systems","author":"S. Shalev-Shwartz","year":"2008","unstructured":"Shalev-Shwartz, S., Srebro, N., & Sridharan, K. (2008). Fast rates for regularized objectives. In Advances in neural information processing systems."},{"key":"423_CR41","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1613\/jair.154","volume":"4","author":"P. Tadepalli","year":"1996","unstructured":"Tadepalli, P., & Natarajan, B. K. (1996). A formal framework for speedup learning from problems and solutions. The Journal of Artificial Intelligence Research, 4, 445\u2013475.","journal-title":"The Journal of Artificial Intelligence Research"},{"key":"423_CR42","volume-title":"Advances in neural information processing systems","author":"B. Taskar","year":"2004","unstructured":"Taskar, B., Guestrin, C., & Koller, D. (2004). Max-margin Markov networks. In Advances in neural information processing systems, Vancouver, Canada."},{"key":"423_CR43","volume-title":"International conference on machine learning","author":"I. Tsochantaridis","year":"2004","unstructured":"Tsochantaridis, I., Hofmann, T., Joachims, T., & Altun, Y. (2004). Support vector machine learning for interdependent and structured output spaces. In International conference on machine learning."},{"key":"423_CR44","first-page":"667","volume-title":"Data mining and knowledge discovery handbook","author":"G. Tsoumakas","year":"2010","unstructured":"Tsoumakas, G., Katakis, I., & Vlahavas, I. P. (2010). Mining multi-label data. In Data mining and knowledge discovery handbook, pp. 667\u2013685."},{"key":"423_CR45","volume-title":"AISTATS","author":"M. J. Wainwright","year":"2003","unstructured":"Wainwright, M. J., Jaakkola, T., & Willsky, A. S. (2003). Tree-reweighted belief propagation algorithms and approximate Ml estimation via pseudo-moment matching. In AISTATS."},{"key":"423_CR46","doi-asserted-by":"crossref","first-page":"2313","DOI":"10.1109\/TIT.2005.850091","volume":"51","author":"M. J. Wainwright","year":"2005","unstructured":"Wainwright, M. J., Jaakkola, T., & Willsky, A. S. (2005a). A new class of upper bounds on the log partition function. IEEE Transactions on Information Theory, 51, 2313\u20132335.","journal-title":"IEEE Transactions on Information Theory"},{"key":"423_CR47","doi-asserted-by":"crossref","first-page":"3697","DOI":"10.1109\/TIT.2005.856938","volume":"51","author":"M. J. Wainwright","year":"2005","unstructured":"Wainwright, M. J., Jaakola, T., & Willsky, A. S. (2005b). MAP estimation via agreement on trees: message passing and linear programming. IEEE Transactions on Information Theory, 51, 3697\u20133717.","journal-title":"IEEE Transactions on Information Theory"},{"key":"423_CR48","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/11526346_54","volume-title":"The international conference on image and video retrieval","author":"A. Yavlinsky","year":"2005","unstructured":"Yavlinsky, A., Schofield, E., & R\u00fcger, S. (2005). Automated image annotation using global features and robust nonparametric density estimation. In The international conference on image and video retrieval (pp. 507\u2013517). Berlin: Springer."},{"key":"423_CR49","doi-asserted-by":"crossref","first-page":"2282","DOI":"10.1109\/TIT.2005.850085","volume":"51","author":"J. S. Yedidia","year":"2005","unstructured":"Yedidia, J. S., Freeman, W. T., & Weiss, Y. (2005). Constructing free energy approximations and generalized belief propagation algorithms. IEEE Transactions on Information Theory, 51, 2282\u20132312.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"423_CR50","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1214\/aos\/1079120130","volume":"32","author":"T. Zhang","year":"2001","unstructured":"Zhang, T. (2001). Statistical behavior and consistency of classification methods based on convex risk minimization. Annals of Statistics, 32(1), 56\u201385.","journal-title":"Annals of Statistics"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-011-0423-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-011-0423-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-011-0423-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T15:07:30Z","timestamp":1637248050000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-011-0423-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,2,5]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,9]]}},"alternative-id":["423"],"URL":"https:\/\/doi.org\/10.1007\/s11263-011-0423-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,2,5]]}}}