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.
This paper considers the problem of material recognition. Motivated by observation of close interconnections between material and object recognition, we study how to select and integrate multiple features obtained by different models of Convolutional Neural Networks (CNNs) trained in a transfer learning setting. To be specific, we first compute activations of features using representations on images...
Defending key network infrastructure, such as Internet backbone links or the communication channels of critical infrastructure, is paramount, yet challenging. The inherently complex nature and quantity of network data impedes detecting attacks in real world settings. In this paper, we utilize features of network flows, characterized by their entropy, together with an extended version of the original...
The huge amount of time required to construct a set of labeled images to train a classifier has led researchers to develop algorithms which can identify the most informative training images, such that labelling those will be sufficient to achieve a considerable classification accuracy. In this paper we focus on choosing a subset of the most informative and diverse images based on which the classification...
Detecting pedestrians in groups and cluttered scenes is one of the most important technology in computer vision. We observe that contour is often an important factor to distinguish pedestrian from others. The particular contour structure of pedestrian head, upper body and lower body becomes the key in pedestrian detection. Inspired by the connection of these three components of pedestrian, a pedestrian...
The lasting popularity of many social Q&A websites, such as Yahoo! Answers and ResearchGate, has become valuable knowledge repositories for people to search for answers to questions in various aspects in life. Finding the most relevant questions is often a non-trivial task, and a fine-grained classification system of questions will be an important aid. Existing work mainly focused on classifying...
In machine learning, an information-theory optimal way to filter the best input features, without reference to any specific machine learning models, consists of maximizing the mutual information between the selected features and the model output, a choice which will minimize the uncertainty in the output to be predicted, given the feature values.
Segmentation process of an Image, represents meaningful way for further analysis and use in medical imaging, remote sensing and military objects detection. Due to poor resolution, segmentation become complex especially is an image is blurred or mixed pixels. Active contour technique is popular to get smooth curve around the boundary of 2D images but due to image gradient this techniques is unable...
Gait recognition is an emerging biometric technology which aims to identify people purely through the analysis of the way they walk. The technology has attracted interest as a method of identification because it is non-invasiveness since it does not require the subject's cooperation. However, "covariates" which include clothing, carrying conditions, and other intra-class variations affect...
The analysis of electroencephalogram (EEG) signal is a low-cost and effective technique to examine electrical activity of the brain and diagnose brain diseases in the Brain Computer Interface (BCI) applications. Classification of EEG signals is an important task in BCI applications. This paper investigates two common methods of feature extraction on EEG signals, autoregressive (AR) model and approximate...
In this research a novel discriminative reordering model for statistical machine translation is proposed. Source dependency tree is used to define the orientation classes of the reordering model. We use maximum entropy principle to train the model. In addition to the common features used in the discriminative reordering models, two new and effective features are introduced. They are phrase number...
A new probability-based parsing model DPSK (Dependency Parsing with Structure Knowledge) is presented for dependency parsing. Similar to a bottom-up chart parsing algorithm, DPSK select the best dependency arc between two words in a sentence according to the probability. The arc probability depends on two kinds of information: (1) Features extracting from two words of the arc. (2) Features extracting...
In this work, we propose an approach that relies on cues from depth perception from RGB-D images, where features related to human body motion (3D skeleton features) are used on multiple learning classifiers in order to recognize human activities on a benchmark dataset. A Dynamic Bayesian Mixture Model (DBMM) is designed to combine multiple classifier likelihoods into a single form, assigning weights...
This paper proposes a novel saliency object detection method by using the mid-level and high-level visual cues. In the mid-level objectness evaluation, we generate three complementary saliency maps, such as the multi-scale segmentation cue, the background cue and the spatial color distribution cue. The first cue is used to highlight the objects via the local region segment. The second cue uses the...
A new and effective salient region detection method based on local and global saliency information is proposed. To keep the completeness of salient regions, the input image is segmented into several regions firstly. Then for each region, local saliency and global saliency are generated respectively. The local saliency is computed by multi-scale neighborhood contrast, and the global saliency is measured...
Content authentication of text document has become a major concern in the current digital era. In this paper, a zero-watermark algorithm is proposed for Chinese text documents content authentication. Firstly, the frequencies of different part-of-speech (POS) tags are obtained through natural language processing technology. And they are used to calculate the expect value and entropy, which can be as...
Online trading takes place in a very complex environment full of uncertainty in which deceitful service providers or sellers may strategically change their behaviors to maximize their profits. The proliferation of deception cases makes it essential and challenging to model the dynamics of a service provider and predict the trustworthiness of the service provider in transactions. Recently, probabilistic...
Canonical views are referred to the classical three-quarter views of a 3D object, always preferred by human beings, because they are stable and able to produce more meaningful and understandable images for the viewer. Unlike existing methods to measure features in the 3D space for view selection, this paper proposes to measure features on the viewing plane, taking into account the influence of feature...
Texture classification became one of the problems which has been paid much attention on by image processing scientists since late 80s. Consequently, since now many different methods have been proposed to solve this problem. In most of these methods the researchers attempted to describe feature's set which provide good dimensionality and severability between textures. In RTV method, a new feature's...
Retrieval of files without the support of file system structures is arguably essential for digital forensics. Files are typically stored as sequences of data blocks, which have to be reconstructed in the retrieval process. This is commonly performed, among other approaches, through file carving, in general detecting the original block sequences by means of signatures of known headers and footers of...
Presently, the mainstream approach to appearance-based localization with local features uses a quantized representation. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity and information content properties. Having demonstrated the advantages of the non-quantized representation, the paper proposes a localization method based on it, and...
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.