A SNoW-Based Face Detector Export

@inproceedings{citeulike:3757007, abstract = {A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-dened or incrementally learned feature space and is specically tailored for learning in the presence of a very large number of features. A wide range of face images in dierent poses, with dierent expressions and under dierent lighting conditions are used as a training set to capture the variations of human faces. Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and others. Furthermore, learning and evaluation using the SNoW-based method are signicantly more ecient than with other methods.}, author = {Yang, Ming-Hsuan and Roth, Dan and Ahuja, Narendra}, booktitle = {Advances in Neural Information Processing Systems 12}, citeulike-article-id = {3757007}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.152}, keywords = {face-detection, snow}, pages = {855--861}, posted-at = {2008-12-08 13:48:43}, priority = {0}, title = {A SNoW-Based Face Detector}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.152}, year = {2000} }

TY - CONF ID - citeulike:3757007 L3 - citeulike-article-id:3757007 N2 - A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-dened or incrementally learned feature space and is specically tailored for learning in the presence of a very large number of features. A wide range of face images in dierent poses, with dierent expressions and under dierent lighting conditions are used as a training set to capture the variations of human faces. Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and others. Furthermore, learning and evaluation using the SNoW-based method are signicantly more ecient than with other methods. EP - 861 TI - A SNoW-Based Face Detector T2 - Advances in Neural Information Processing Systems 12 SP - 855 KW - face-detection KW - snow AU - Yang, Ming-Hsuan AU - Roth, Dan AU - Ahuja, Narendra PY - 2000/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.152 ER -