This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches...
This paper proposes a new generic object recognition system based on multi-scale affineinvariant image regions. Image segments are obtained by a watershed transform of the princip...
Wei Zhang, Hongli Deng, Thomas G. Dietterich, Eric...
Abstract. This paper presents a new Bayesian approach to hyperspectral image segmentation that boosts the performance of the discriminative classifiers. This is achieved by combin...
Abstract. We address the problem of large scale place-of-interest recognition in cell phone images of urban scenarios. Here, we go beyond what has been shown in earlier approaches ...
Abstract. The importance of spatial configuration information for object class recognition is widely recognized. Single isolated local appearance codes are often ambiguous. On the...