Bag-of-words document representations are often used in text, image and video processing. While it is relatively easy to determine a suitable word dictionary for text documents, there is no simple mapping from raw images or videos to dictionary terms. The classical approach builds a dictionary using vector quantization over a large set of useful visual descriptors extracted from a training set,...

We describe a submission to the ICML 2013 Bird Challenge, in which we explore the use of sparse representations as an advance on the standard technique of cross-correlation template matching in time-frequency representations. The Matching Pursuit algorithm is used to represent the signal as a sparse set of activations of templates derived from the challenge training audio. Given an audio record...

Manifold learning is a novel approach in non-linear dimensionality reduction that has shown great potential in numerous applications and has gained ground compared to linear techniques. In addition, sparse representations have been recently applied on computer vision problems with success, demonstrating promising results with respect to robustness in challenging scenarios. A key concept shared ...

Sparsity often leads to efficient and interpretable representations for data. In this paper, we introduce an architecture to infer the appropriate sparsity pattern for the word embeddings while learning the sentence composition in a deep network. The proposed approach produces competitive results in sentiment and topic classification tasks with high degree of sparsity. It is computationally che...

With the rapid development of surveillance technology, there are often several cameras in one scenario. The multi-camera usage to perform gait recognition becomes a challenge problem. This paper studies multi-camera gait recognition via structure sparsity. For the multicamera structure in the training set, we propose a structure sparsity algorithm to learn informative and discriminative sparse ...

Nine quasar absorption spectra at 21-cm and ultraviolet (UV) rest-frame wavelengths are used to estimate possible variations in x ≡αgpμ, where α is the fine structure constant, gp the proton g-factor and μ ≡ me/mp is the electron-to-proton mass ratio. We find 〈 x/x〉 total = (0.63 ± 0.99) × 10−5 over a redshift range 0.23 zabs 2.35 which corresponds to look-back times of 2.7–10.5 billion years. ...

In this paper, we propose an efficient ADMM-based algorithm for graph regularized sparse coding that explicitly takes into account the local manifold structure of the data. Specifically, the graph Laplacian representing the manifold structure is used as a regularizer, encouraging the resulting sparse codes to vary smoothly along the geodesics of the data manifold. By preserving locality, the ob...

It is well assessed that sparse representations improve the overall accuracy and the systems performances of many image classification problems. This paper deals with the problem of finding sparse and discriminative representations of images in multi-class settings. We propose a new regularized functional, which is a modification of the standard dictionary learning problem, designed to learn on...

Abstract— Bag-of-visual-words or bag-of-visterms (bov) is a common technique used to index Multimedia information with the purposes of retrieval and classification. In this work we address the problem of constructing efficient bov representations of complex shapes as are the Maya syllabic hieroglyphs. Based on retrieval experiments, we assess and evaluate the performance of several variants of ...