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.
Feature selection is essential to rule learning in the context of functional verification. In practice today, features are selected manually and the selection requires domain knowledge. In contrast, this work proposes using automatic feature extraction from design documents as a viable approach to support rule learning. To demonstrate its effectiveness, document-extracted features are employed to...
In this paper we investigate the influence of outliers in the training set on the probabilistic classifier quality. By the example of naive Bayes classifier we show how the qualitative characteristics depend on the percentage of outliers' ratio. This dependence is built on three basic metrics of the classifier quality: precision, recall and F1 score. At the end we propose method for reducing the outliers...
The joint Bayesian method is an effective method for face verification. However, it is insufficient distinguishability for this method to calculate the similarity between different samples. To address this problem, in this paper, we proposed an improved similarity metric based on joint Bayesian for face verification. The proposed method defines two novel similarities for two samples based on joint...
Answer triggering task as new subtle challenge to Question Answering (QA), requires QA systems to have the ability to detect whether there exists at least one valid answer in the set of candidate sentences for the question; and if yes, select one of the valid answer sentences from the candidate sentence set. This paper presents a novel approach that addresses answer triggering task in answer sentence...
Person re-identification is one of the hot topics in computer vision. How to design a robust feature representation to identify pedestrians is a key problem for person re-identification. In this paper, a feature representation based on Multi-Statistics Cascade on Pyramid (MSCP) is proposed for person re-identification. The MSCP feature is composed of deep PCA network feature and hand-crafted features...
Automatically recognising facial emotions has drawn increasing attention in computer vision. Facial landmark based methods are one of the most widely used approaches to perform this task. However, these approaches do not provide good performance. Thus, researchers usually tend to combine more information such as textural and audio information to increase the recognition rate. In this paper we propose...
A hash algorithm converts data into compact strings. In the multimedia domain, effective hashing is the key to large-scale similarity search in high-dimensional feature space. A limit of existing hashing techniques is that they typically use single features. In order to improve search performance, it is necessary to utilize multiple features. Due to the compactness requirement, concatenation of hash...
This paper presents fine-tuned CNN features for person re-identification. Recently, features extracted from top layers of pre-trained Convolutional Neural Network (CNN) on a large annotated dataset, e.g., ImageNet, have been proven to be strong off-the-shelf descriptors for various recognition tasks. However, large disparity among the pre-trained task, i.e., ImageNet classification, and the target...
Video summarization is useful to find a concise representation of the original video, nevertheless its evaluation is somewhat challenging. This paper proposes a simple and efficient method for precisely evaluating the video summaries produced by the existing techniques. This method includes two steps. The first step is to establish a set of matched frames between automatic summary (AT) and the ground...
Recognizing offline handwritten Telugu characters from digitized document images is very challenging. In this paper, we propose a novel approach of hybrid feature extraction and hierarchical classification to recognize the glyphs of offline handwritten Telugu characters. In the proposed method, hybrid features are extracted from the glyphs and the glyphs are recognized using a hierarchical classification...
With the exponential rise in the number of Internet users, Social Networking platforms have become one of the major means of communication all over the globe. Many major players in this field exist including the likes of Facebook, Twitter, Google+ etc. Impressed by the number of users an individual can reach using the existing Social Networking platforms, most organizations and celebrities make use...
In graph based extractive summarization the extraction of sentences can be determined by the importance of the words it contains and the association between the sentences. This method considers the word separately. It does not provide association link handling between the words. This paper addresses to what extent the integration of coreference resolution into the summarization process can improve...
This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps. We propose an architecture which, instead, combines features extracted at different levels of a Convolutional Neural...
In this paper we propose a hierarchical activity clustering methodology which incorporates the use of topological persistence analysis. Our clustering methodology captures the hierarchies present in the data and is therefore able to show the dependencies that exist between these activities. We make use of an aggregate persistence diagram to select robust graphical structures present within the dataset...
In surveillance videos, the pictures of a same person often present significant variation which makes person re-identification difficult. Though the globe appearances may present great difference, some local patches still have great similarities, and human eyes can be used to distinguish the identity of each person via these local patches. Inspired from it, patch matching is introduced in person re-identification...
Although the design of low-level local spatiotemporal features has recently led to significant improvement of performance in many action recognition applications, much less attention has been given to the equally important problem how to organize such low-level features extracted from the videos into a higher-level representation suitable to represent and discriminate between many different action...
For images taken from very different viewpoints, we propose a new feature matching algorithm that provides accurate matches while preserving high matchability. Our method first synthesizes images by simulating the viewpoint changes. It then learns variation of local feature descriptors induced by the viewpoint changes. Finally, we robustly match feature descriptors by measuring the similarity using...
One of the main problems of recognizing faces in videos is to achieve accurate algorithms which can be used in real-time applications. Recently, Fisher Vector representation of local descriptors (e.g., SIFT) has gained widespread popularity, achieving good recognition rates. In this work, we propose to use Fisher Vector encoding of binary features for video face recognition, in order to speed up the...
We propose a novel method for extracting features from images of people using co-occurrence attributes, which are then used for person re-identification. Existing methods extract features based on simple attributes such as gender, age, hair style, or clothing. Our method instead extracts more informative features using co-occurrence attributes, which are combinations of physical and adhered human...
The problem of re-identify persons across single disjoint camera-pairs has received great attention from the community. Despite this, when the re-identification process has to be carried out on a large camera network a different approach has to be considered. In particular, existing approaches have neglected the importance of the network topology (i.e., the structure of the monitored environment)...
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.