Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
34
Supplementary material for the paper Are Sparse Representations Really Relevant for Image Classification? ∗
"... This document presents results we obtained but were unable to put in the paper because of space limitations. The different combinations we tried are called by concatenating the names of their parts together. The possible part names are given below in capital letters. For example, OLS-SPARSEGD-ABS-MA ..."
Abstract
- Add to MetaCart
Support Vector Machine for classification. We sometimes use a star (*) as the name of one component that is varied for an evaluation. 1. Filter Bank Learning Setup The filter learning procedure is based on stochastic gradient descent. The objective function of Eq. (3) is minimized by. Table 1 reports
Human Gesture Recognition using Sparse B-spline Polynomial Representations
"... The extraction and quantization of local image and video descriptors for the subsequent creation of visual codebooks is a technique that has proved extremely effective for image and video retrieval applications. In this paper we build on this concept and extract a new set of visual descriptors that ..."
Abstract
- Add to MetaCart
The extraction and quantization of local image and video descriptors for the subsequent creation of visual codebooks is a technique that has proved extremely effective for image and video retrieval applications. In this paper we build on this concept and extract a new set of visual descriptors
Smooth Sparse Coding via Marginal Regression for Learning Sparse Representations- Supplementary material 1. Data set Description
"... The face recognition experiment was conducted on the CMU Multi-PIE dataset. The dataset is challenging due to the large number of subjects and is one of the standard data sets used for face recognition experiments. The data set contains 337 subjects across simultaneous variations in pose, expression ..."
Abstract
- Add to MetaCart
, expression, and illumination. Weignorethe88subjectsthatwereconsidered as outliers in (Yang et al., 2010) and used the rest of the images for our face recognition experiments. We follow (Yang et al., 2010) and use the 7 frontal extreme illuminations from session one as train set and useother 20illuminations
Learning a Discriminative Sparse Tri-value Transform
"... Simple binary patterns have been successfully used for extracting feature representations for visual object classification. In this paper, we present a method to learn a set of discriminative tri-value patterns for projecting high dimensional raw visual inputs into a low dimensional subspace for tas ..."
Abstract
- Add to MetaCart
Simple binary patterns have been successfully used for extracting feature representations for visual object classification. In this paper, we present a method to learn a set of discriminative tri-value patterns for projecting high dimensional raw visual inputs into a low dimensional subspace
RESEARCH ARTICLE Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine ’ Algorithm
"... Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates ..."
Abstract
- Add to MetaCart
rates below 1 % on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the ‘Extreme Learning Machine ’ (ELM) approach, which also enables a very rapid training time ( * 10 minutes). Adding distortions
SHOULDWE DISCARD SPARSE OR INCOMPLETE VIDEOS?
"... In this paper, we determine whether incomplete videos that are often discarded carry useful information for action recognition, and if so, how one can represent such mixed collection of video data (complete versus incomplete, and labeled versus unlabeled) in a unified manner. We propose a novel fram ..."
Abstract
- Add to MetaCart
the input mixed data into a uniform compact representation. (3) Exhaustively scrutinizing 280 configurations, we experimentally show on our two created benchmarks that, even the videos are extremely sparse and incomplete, it is still possible to recover useful information from them, and classify unknown
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 1 Weighted Tanimoto Extreme Learning Machine with Case Study in Drug Discovery
"... Abstract—Machine learning methods are becoming more and more popular in the field of computer-aided drug design. The specific data characteristic, including sparse, binary representa-tion as well as noisy, imbalanced datasets, presents a challenging binary classification problem. Currently, two of t ..."
Abstract
- Add to MetaCart
Abstract—Machine learning methods are becoming more and more popular in the field of computer-aided drug design. The specific data characteristic, including sparse, binary representa-tion as well as noisy, imbalanced datasets, presents a challenging binary classification problem. Currently, two
LEARNING UTTERANCE-LEVEL REPRESENTATIONS FOR SPEECH EMOTION AND AGE/GENDER RECOGNITION USING DEEP NEURAL NETWORKS
"... ABSTRACT Accurately recognizing speaker emotion and age/gender from speech can provide better user experience for many spoken dialogue systems. In this study, we propose to use deep neural networks (DNNs) to encode each utterance into a fixed-length vector by pooling the activations of the last hid ..."
Abstract
- Add to MetaCart
hidden layer over time. The feature encoding process is designed to be jointly trained with the utterance-level classifier for better classification. A kernel extreme learning machine (ELM) is further trained on the encoded vectors for better utterance-level classification. Experiments on a Mandarin
Linear Discriminant Text Classification in High Dimension
"... Linear Discriminant (LD) techniques are typically used in pattern recognition tasks when there are many (n >> 10 4 ) datapoints in low-dimensional (d < 10 2 ) space. In this paper we argue on theoretical grounds that LD is in fact more appropriate when training data is sparse, and the d ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
Linear Discriminant (LD) techniques are typically used in pattern recognition tasks when there are many (n >> 10 4 ) datapoints in low-dimensional (d < 10 2 ) space. In this paper we argue on theoretical grounds that LD is in fact more appropriate when training data is sparse
A Structured Committee for Food Recognition
"... Food recognition is an emerging computer vision topic. The problem is characterized by the absence of rigid struc-ture of the food and by the large intra-class variations. Ex-isting approaches tackle the problem by designing ad-hoc feature representations based on a priori knowledge of the problem. ..."
Abstract
- Add to MetaCart
. Differently from these, we propose a committee-based recognition system that chooses the optimal features out of the existing plethora of available ones (e.g., color, texture, etc.). Each committee member is an Extreme Learn-ing Machine trained to classify food plates on the basis of a single feature type
Results 1 - 10
of
34
