The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Zero-shot learning, a special case of unsupervised domain adaptation where the source and target domains have disjoint label spaces, has become increasingly popular in the computer vision community. In this paper, we propose a novel zero-shot learning method based on discriminative sparse non-negative matrix factorization. The proposed approach aims to identify a set of common high-level semantic...
Zero-shot learning (ZSL) models rely on learning a joint embedding space where both textual/semantic description of object classes and visual representation of object images can be projected to for nearest neighbour search. Despite the success of deep neural networks that learn an end-to-end model between text and images in other vision problems such as image captioning, very few deep ZSL model exists...
Motor relearning after stroke is a lengthy process which should be continued after patients get discharged from the clinic. This project aims at developing a system for telerehabilitation which enables stroke patients to exercise at home autonomously or under supervision of a therapist. The system includes haptic therapy devices which are more promising and beneficial for stroke rehabilitation than...
This paper aims to provide a new method of visualizing high-dimensional data classification by employing principal component analysis (PCA) and support vector machine (SVM). In this method, PCA is adopted to reduce the dimension of high-dimensional data, and then SVM is used for the data classification process. At last, the classified result is projected to two-dimension mapping. The method can visualize...
Visually impaired community rely on many artificial aids which allow them to lead an average life in the complex modern society. Identification of currency notes is of utmost importance in this regard and many electronic currency note recognizers have been developed. Nevertheless, a compact, accurate and a cost effective recognizer optimized for local currency notes is highly preferred. In this paper...
In this paper, we will report our virtual evaluation tool which can be used for a simultaneous evaluation of driving acuity and spatial perceptual capacity. This system has been developed in a multidisciplinary team consisting of systemic neuroscientists and computer scientists. Our approach is to develop a portable system which is cost effective to be used in hospitals, driving schools or even police...
We present LISSA — Live Interactive Social Skill Assistance — a web-based system that helps people practice their conversational skills by having short conversations with a human like virtual agent and receiving real-time feedback on their nonverbal behavior. In this paper, we describe the development of an interface for these features and examine the viability of real time feedback using a Wizard...
A bio-inspired model for head pose recognition is described in this paper. The bio-inspired model recognizes the head by using gray scale information as well as the silhouette of the person. A set of descriptors is generated from this analysis by a hierarchical model based on the visual cortex. Then the descriptors are classified by a multilayer perceptron artificial neural network to identify the...
This paper describes the design, development, implementation and user evaluation of an interactive modular tile system, aimed to support balance rehabilitation of patients recovering from a stroke. The REHAP Balance Tiles system is an innovative tool, which has been developed in close collaboration with therapists and patients in stroke units of health rehabilitation institutes in Sydney, Australia...
In this paper, we propose that visualized activities and experiences created in 3D virtual worlds may provide a new type of learning community memory. We explore how such activities and experience can be captured, crystallized, and reused with this technology in three prototypes designed on two platforms. This approach can support learning communities by addressing the common challenge of acquiring...
As more and more images with user free tags are appearing on the Internet, image search reranking has received considerable attention to help users obtain images relevant to the query. In this paper, we propose to rerank the initial image search results using an adaptive online query modeling method based on local features. For a query and its initial rank list, we construct a visual word dictionary...
This research proposes a Brain Computer Interface as an interactive and intelligent Image Search and Retrieval tool that allows users, disabled or otherwise to browse and search for images using brain signals. The proposed BCI system implements decoding the brain state by using a non-invasive electroencephalography (EEG) signals, in combination with machine learning, artificial intelligence and automatic...
Multiple-labeling classification approaches attempt to handle applications that associate more than one label to a given sample. Since we have an increasing number of systems that are guided by such assumption, in this paper we have presented a multiple-labeling approach for the Optimum-Path Forest (OPF) classifier based on the problem transformation method. In order to validate our proposal, a multi-labeled...
In computer vision, semantically accurate segmentation of an object is considered to be a critical problem. The different looking fragments of the same object impose the main challenge of producing a good segmentation. This leads to consider the high-level semantics of an image as well as the low-level visual features which require computationally intensive operations. This demands to optimize the...
ImageNet is a large-scale database of object classes with millions of images. Unfortunately only a small fraction of them is manually annotated with bounding-boxes. This prevents useful developments, such as learning reliable object detectors for thousands of classes. In this paper we propose to automatically populate ImageNet with many more bounding-boxes, by leveraging existing manual annotations...
High-content imaging is an emerging technology for the analysis and quantification of biological phenomena. Thus, classifying a huge number of cells or quantifying markers from large sets of images by experts is a very time-consuming and poorly reproducible task. In order to over-come such limitations, we propose a supervised method for automatic cell classification. Our approach consists of two steps:...
In this paper we demonstrate an effective method for parsing clothing in fashion photographs, an extremely challenging problem due to the large number of possible garment items, variations in configuration, garment appearance, layering, and occlusion. In addition, we provide a large novel dataset and tools for labeling garment items, to enable future research on clothing estimation. Finally, we present...
This paper presents a framework for unsupervised learning of a hierarchical generative image model called ANDOR Template (AOT) for visual objects. The AOT includes: (1) hierarchical composition as “AND” nodes, (2) deformation of parts as continuous “OR” nodes, and (3) multiple ways of composition as discrete “OR” nodes. These AND/OR nodes form the hierarchical visual dictionary. We show that both...
This paper presents an improvement on a biologically inspired network for image classification. Previous models have used a multi-scale and multi-orientation architecture to gain robustness to transformations and to extract complex visual features. Our contribution to this type of architecture resides in the building of complex visual features which are better tuned to images structures. We allow...
The Digital Age has brought with it large-scale digitization of historical records. The modern scholar of history or of other disciplines is often faced today with hundreds of thousands of readily-available and potentially-relevant full or fragmentary documents, but without computer aids that would make it possible to find the sought-after needles in the proverbial haystack of online images. The problems...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.