In this paper, we present a new mechanism to extract discriminative acoustic features for speech recognition using continuous output coding (COC) based feature transformation. Our proposed method first expands the short-time spectral features into a higher dimensional feature space to improve its discriminative capability. The expansion is performed by employing the polynomial expansion. The hi...

This paper describes a segmental feature extraction and speech coding method in an acousticarticulatory domain using nomograms that represent a mapping between formant frequencies and articulatory parameters. The vocal tract model is a modified Fant model, in which we newly introduced a parameter for successively adjusting vocal tract lengths. We investigated first the relationship between form...

Simultanagnosia is a disorder characterized by an inability to see more than one object at a time. We report a simultanagnosic patient (ED) with bilateral posterior infarctions who produced frequent illusory conjunctions on tasks involving form and surface features (e.g., a red T) and form alone. ED also produced "blend" errors in which features of one familiar perceptual unit appeared to migra...

This report describes an experimental still image coder that grew out of a project in the graduate course “Advanced Video Coding” in spring 2000. The project has investigated the idea to use local orientation histograms in fractal coding. Instead of performing a correlation-like grey-level matching of image regions, the block search is made by matching feature histograms of the block contents. ...

We consider the problem of object recognition with a large number of classes. In order to overcome the low amount of labeled examples available in this setting, we introduce a new feature learning and extraction procedure based on a factor model we call spike-and-slab sparse coding (S3C). Prior work on S3C has not prioritized the ability to exploit parallel architectures and scale S3C to the en...

The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported for object recognition tasks. In this paper, we investigate if and how feature learning can be used for material recognition. We propose two strategies to in...

The potential value of hashing techniques has led to it becoming one of the most active research areas in computer vision and multimedia. However, most existing hashing methods for image search and retrieval are based on global representations, e.g., GIST [3], which lack the analysis of the intrinsic geometric property of local features and heavily limit the effectiveness of the hash code. In t...

Recently, the computer vision and machine learning community has been in favor of feature extraction pipelines that rely on a coding step followed by a linear classifier, due to their overall simplicity, well understood properties of linear classifiers, and their computational efficiency. In this paper we propose a novel view of this pipeline based on kernel methods and Nyström sampling. In par...

Abstract We consider the problem of using a factor model we call spike-and-slab sparse coding (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure and employ a variational EM training algorithm. Prior work on approximate ...

Model-based coding is a new image sequence compression technique for very low bit rate coding. Most researchers have paid more attention to facial image analysis and synthesis because facial images are very important in multimedia communication applications, such as video phone, video conferencing, remote learning etc. This coding method represents the image content in a structural way. This is...