We present a simple supervised text classification system that combines sparse and dense vector representations of words, and the generalized representations of words via clusters. The sparse vectors are generated from word n-gram sequences (13). The dense vector representations of words (embeddings) are learned by training a neural network to predict neighboring words in a large unlabeled data...

Spoken language recognition requires a series of signal processing steps and learning algorithms to model distinguishing characteristics of different languages. In this paper, we present a sparse discriminative feature learning framework for language recognition. We use sparse coding, an unsupervised method, to compute efficient representations for spectral features from a speech utterance whil...

One popular approach for human action recognition is to extract features from videos as representations, subsequently followed by a classification procedure of the representations. In this paper, we investigate and compare hand-crafted and random feature representation for human action recognition on YouTube dataset. The former is built on 3D HoG/HoF and SIFT descriptors while the latter bases ...

A key recent advance in face recognition models a test face image as a sparse linear combination of a set of training face images. The resulting sparse representations have been shown to possess robustness against a variety of distortions like random pixel corruption, occlusion and disguise. This approach however makes the restrictive (in many scenarios) assumption that test faces must be perfe...

The manual delineation of Multiple Sclerosis (MS) lesions is a challenging task pertaining to the requirement of neurological experts and high intraand inter-observer variability. It is also time consuming because large number of Magnetic Resonance (MR) image slices are needed to obtain 3-D information. Over the last years, various models combined with supervised and unsupervised classification...

Machine learning concerns forming representations of input observations to facilitate tasks such as classification. A recent insight in deep learning [1] is to use a deep architecture that stacks multiple levels of nonlinear operations in an inference hierarchy to extract different layers of abstractions. Deep learning is a promising direction and has attained state-of-the-art performance in so...

Sparse representations allow modeling data using a few basis elements of an over-complete dictionary and have been used in many image processing applications. We propose to use the sparse representation and dictionary learning paradigm to automatically segment Multiple Sclerosis (MS) lesions from longitudinal MR data. The dictionaries are learned for the lesion and healthy brain tissue classes,...

Group sparsity has drawn much attention in machine learning. However, existing work can handle only datasets with certain group structures, where each sample has a certain membership with one or more groups. This paper investigates the learning of sparse representations from datasets with uncertain group structures, where each sample has an uncertain membership with all groups in terms of a pro...