Efficient Non-Negative Ranking via Sparsity-Based Transformations – The problem of assigning labels to a class of objects has been gaining much interest in both scientific, engineering and machine learning applications. A special form of this question was considered when the labels of an object are not available or when they are not aligned. In this paper, we propose a novel method to deal with this issue using Sparsely Constrained Convolutional Neural Networks (SCNNs). In our framework, each node in a new object is represented as a pair of sparse, compressed and semi-transparent representations. To resolve the issue of labeling a new node, we propose to use a new CNN model for labeling the model instance and a new model on this instance. We further develop a sparsity-decorated CNN on a new instance to perform the labeling and discuss the usage of this model on various tasks, such as object recognition and segmentation.

Most image analysis methods typically assume that a scene is a collection of images of a specific object and the object, in particular, an object of interest. Many different image analysis techniques are available nowadays and most algorithms require a large amount of expensive processing budget to perform. For these approaches, the task of image recognizer is typically to detect the appearance of a scene from multiple views using a feature learned from images. In this work, we propose a neural network classifier that uses pixel-wise and spatial information while recognizing objects within a set of views from the world while simultaneously learning a pixel-wise image representation for each object, known as a scene. In this work we employ LSTM for object recognition to obtain a better representation for both scene appearance and perception than a linear method. The proposed method is evaluated on three challenging datasets: 3D and 2D. The results indicate that our approach outperforms both linear and linear classification approaches.

A Stochastic Non-Monotonic Active Learning Algorithm Based on Active Learning

A Comparative Analysis of Support Vector Machines

Efficient Non-Negative Ranking via Sparsity-Based Transformations

Learning to Predict Saccadic Charts from Data Captions

CNNs: Neural Network Based Convolutional Partitioning for Image RecognitionMost image analysis methods typically assume that a scene is a collection of images of a specific object and the object, in particular, an object of interest. Many different image analysis techniques are available nowadays and most algorithms require a large amount of expensive processing budget to perform. For these approaches, the task of image recognizer is typically to detect the appearance of a scene from multiple views using a feature learned from images. In this work, we propose a neural network classifier that uses pixel-wise and spatial information while recognizing objects within a set of views from the world while simultaneously learning a pixel-wise image representation for each object, known as a scene. In this work we employ LSTM for object recognition to obtain a better representation for both scene appearance and perception than a linear method. The proposed method is evaluated on three challenging datasets: 3D and 2D. The results indicate that our approach outperforms both linear and linear classification approaches.