3D reconstruction from an unordered set of images may fail due to incorrect epipolar geometries (EG) between image pairs arising from ambiguous feature correspondences. Previous m...
We present a discriminative latent topic model for scene recognition. The capacity of our model is originated from the modeling of two types of visual contexts, i.e., the category...
We address the problem of segmenting and recognizing objects in real world images, focusing on challenging articulated categories such as humans and other animals. For this purpos...
Pablo Arbelaez, Bharath Hariharan, Chunhui Gu, Sau...
Abstract We tackle the problem of detecting occluded regions in a video stream. Under assumptions of Lambertian reflection and static illumination, the task can be posed as a vari...
This paper presents a two-step approach to compress spontaneous spoken utterances. In the first step, we use a sequence labeling method to determine if a word in the utterance ca...