While discriminative training (e.g., CRF, structural SVM) holds much promise for machine translation, image segmentation, and clustering, the complex inference these applications ...
— Object recognition is a challenging problem for artificial systems. This is especially true for objects that are placed in cluttered and uncontrolled environments. To challenge...
Most standard learning algorithms, such as Logistic Regression (LR) and the Support Vector Machine (SVM), are designed to deal with i.i.d. (independent and identically distributed...
Chi-Hoon Lee, Matthew R. G. Brown, Russell Greiner...
This paper presents a statistical model for textures that uses a non-negative decomposition on a set of local atoms learned from an exemplar. This model is described by the varianc...
High-level, or holistic, scene understanding involves
reasoning about objects, regions, and the 3D relationships
between them. This requires a representation above the
level of ...