This paper builds on a novel framework of hybrid matching constraints for estimation of structure and recovery of camera focal length and motion, combining the advantages of both ...
One of disadvantages of Hidden Markov Models (HMMs) is its low resistance to unexpected noises among observation sequences. Unexpected noises in a sequence usually "break&quo...
Albert Hung-Ren Ko, Alceu de Souza Britto Jr., Rob...
In this paper, a new algorithm is developed for recovering the large disocclusion regions in depth image based rendering (DIBR) systems on 3DTV. For the DIBR systems, undesirable ...
Image segmentation combining boundary and region information has been the subject of numerous research works in the past. This combination is usually subject to arbitrary weightin...
This paper addresses the problem of 3D face recognition using spherical sparse representations. We first propose a fully automated registration process that permits to align the 3...
Effrosini Kokiopoulou, Ivana Tosic, Pascal Frossar...
Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...
Cylindrical panoramic mosaics can be created by aligning and stitching images from a series, captured by a camera rotating around its optical center. The transformation between tw...
We propose a new loss function for discriminative learning of Markov random fields, which is an intermediate loss function between the sequential loss and the pointwise loss. We s...
Current sign language recognition systems are still designed for signer-dependent operation only and thus suffer from the problem of interpersonal variability in production. Appli...
This paper presents a novel Gaussianized vector representation for scene images by an unsupervised approach. First, each image is encoded as an ensemble of orderless bag of featur...
Hao Tang, Mark Hasegawa-Johnson, Thomas S. Huang, ...