Despite progress in image retrieval by using low-level features, such as colors, textures and shapes, the performance is still unsatisfied as there are existing gaps between low-level features and high-level semantic concepts (semantic gaps). In this research, we propose a novel image retrieval system based on bag-of-features (BoF) model by integrating scale invariant feature transform (SIFT) a...

In this paper we describe a new formulation for the 3D salient local features based on the voxel grid inspired by the Scale Invariant Feature Transform (SIFT). We use it to identify the salient keypoints (invariant points) on a 3D voxelized model and calculate invariant 3D local feature descriptors at these keypoints. We then use the bag of words approach on the 3D local features to represent t...

An image retrieval system is a computer system for browsing, searching and retrieving images from a large database of digital images. Given a textual query in traditional text based image retrieval (TBIR),relevant images are to be re ranked using visual features after the initial text based image search. In this paper, we propose a new bag based re ranking framework for large scale TBIR. We com...

Digital libraries relating to particular subject domains have invested a great deal of human e ort in developing metadata in the form of subject area thesauri. This e ort has emerged more recently in arti cial intelligence as ontologies or knowledge bases which organize particular subject areas. The purpose of subject area thesauri is to provide organization of the subject into logical, semanti...

This paper presents a 3D shape retrieval algorithm based on the Bag of Words (BoW) paradigm. For a given 3D shape, the proposed approach considers a set of feature points uniformly sampled on the surface and associated with local Fourier descriptors; this descriptor is computed in the neighborhood of each feature point by projecting the geometry onto the eigenvectors of the Laplace-Beltrami ope...

The Problem: Traditional information retrieval systems based on the “bag-of-words” paradigm cannot capture the semantic content of documents. While these systems are relatively robust and have high recall, they suffer from very poor precision. On the other hand, it is impossible with current technology to build a practical information access system that fully analyzes and understands unrestrict...

Community question answering platforms need to automatically rank answers and questions with respect to a given question. In this paper, we present the approaches for the Answer Selection and Question Retrieval tasks of SemEval-2016 (task 3). We develop a bag-of-vectors approach with various vectorand text-based features, and different neural network approaches including CNNs and LSTMs to captu...

I evaluate an approach to compare images using a structured feature representation based on graph entropy. The effect, a pairwise similarity measure among images, may be used for retrieval and classification of images. I begin the paper by detailing how to select and extract features from an image in order to build a weighted graph while still taking into account the spatial organization of the...

Content-based image retrieval (CBIR) has been applied to a variety of medical applications, e.g., pathology research and clinical decision support, and bag-of-features (BOF) model is one of the most widely used techniques. In this study, we address the problem of vocabulary pruning to reduce the influence from the redundant and noisy visual words. The conditional probability of each word upon t...

In this paper, we address the tissue region retrieval problem in prostate histopathology: we search for tissue regions visually similar to a query region from a database of prostate tissue slide images. To achieve this goal, a gland-based method to compute the similarity between two tissue regions is adopted, in which we first need to segment glands and extract their features. The region simila...