Abstract. In speech recognition, phonemes have demonstrated their efficacy to model the words of a language. While they are well defined for languages, their extension to human act...
Kaustubh Kulkarni, Edmond Boyer, Radu Horaud, Amit...
We present an unsupervised, shape-based method for joint clustering of multiple image segmentations. Given two or more closely-related images, such as nearby frames in a video seq...
This paper presents a novel intrinsic 3D surface distance and its use in a complete probabilistic tracking framework for dynamic 3D data. Registering two frames of a deforming 3D ...
Yun Zeng, Chaohui Wang, Yang Wang, David Gu, Dimit...
The most popular approach to large scale image retrieval is based on the bag-of-visual-word (BoV) representation of images. The spatial information is usually reintroduced as a po...
We propose structured models for image labeling that take into account the dependencies among the image labels explicitly. These models are more expressive than independent label ...
Object recognition has made great strides recently. However, the best methods, such as those based on kernelSVMs are highly computationally intensive. The problem of how to accele...
Blind image deconvolution is an ill-posed problem that requires regularization to solve. However, many common forms of image prior used in this setting have a major drawback in th...
In this paper, we propose a novel method to reduce the magnitude of 4D CT artifacts by stitching two images with a data-driven regularization constrain, which helps preserve the l...
Dongfeng Han, John Bayouth, Qi Song, sudershan Bha...
In this paper, we propose a novel framework to jointly recover the illumination environment and an estimate of the cast shadows in a scene from a single image, given coarse 3D geo...
We present an unsupervised, shape-based method for joint clustering of multiple image segmentations. Given two or more closely-related images, such as nearby frames in a video sequ...
Daniel Glasner, Shiv N. Vitaladevuni and Ronen Bas...