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.
The level of automated unmanned surface vehicle is always dependent on human interactions. An automated collision avoidance approach is proposed which is based on the visual system in order to improve it. Deep convolutional neural network (CNN) is a popular deep neural network for pattern recognition. Three types of encounter scenes are created and recorded which are used as the CNN training samples...
This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two coupled projections that project the source domain and target domain data into low-dimensional...
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses...
The current paper presents a novel recurrent neural network model, predictive multiple spatio-temporal scales RNN (P-MSTRNN), which can generate as well as recognize dynamic visual patterns in a predictive coding framework. The model is characterized by multiple spatio-temporal scales imposed on neural unit dynamics through which an adequate spatio-temporal hierarchy develops via learning from exemplars...
Visualization helps us to understand single-label and multi-label classification problems. In this paper, we show several standard techniques for simultaneous visualization of samples, features and multi-classes on the basis of linear regression and matrix factorization. The experiment with two real-life multi-label datasets showed that such techniques are effective to know how labels are correlated...
The neocognitron is a deep (multi-layered) convolutional neural network that can be trained to recognize visual patterns robustly. In the intermediate layers of the neocognitron, local features are extracted from input patterns. In the deepest layer, based on the features extracted in the intermediate layers, input patterns are classified into classes. A method called IntVec (interpolating-vector)...
We summarize the history and state of the art in Convolutional Neural Networks (CNNs), which constitute a significant advancement in pattern recognition. As a demonstration of capability, we address the problem of automatic aircraft identification during refueling approach. In this paper we describe the history of CNN development and provide a high level overview of the state of the art and a summary...
In this paper, an asymmetric kernel is proposed for extracting sparse features from two-dimensional visual face images for identity recognition. Essentially, the kernel consists of an inner product of two vectors where one of them has been raised to power terms element-wise. The impact of such a power term is suppression of less influential features where only relevant ones are used for estimation...
Deep convolutional neural networks is a recently developed method that yields very successful results in image classification. Deep neural networks, which have a high number of parameters, require a large amount of data to avoid overfitting during training. For applications in which the available data is not adequate to train a deep neural network from the scratch, deep neural networks trained for...
The increase popularity of using huge image databases in various image retrieval applications construct a need to develop an efficient and robust system provides the output in the form of similar images with respect to the input or query image. Also to carry out its management and retrieval, Content-Based Image Retrieval is an effective method in retrieval system, as well as key technologies. In addition...
In real video surveillance scenarios, visual pedestrian attributes, such as gender, backpack, clothes types, are very important for pedestrian retrieval and person reidentification. Existing methods for attributes recognition have two drawbacks: (a) handcrafted features (e.g. color histograms, local binary patterns) cannot cope well with the difficulty of real video surveillance scenarios; (b) the...
Bayesian pattern recognition is a natural companion for graph-based simultaneous localization and mapping (SLAM) due to its ability to come up with high quality place matches based solely on image data, completely eschewing metric information. Recent SLAM-like approaches such as fast appearance-based mapping (FAB-MAP) [1] are very effective information filters, with the ability to provide place matching...
In this work, we address the problem of building recognition as a mobile application. Our approach exploits a small-sized vocabulary-tree of SIFT descriptors. Each SIFT descriptor in our dataset is saved along with its class label, its nearest neighbor from the vocabulary and the visual words corresponding to its spatial neighbors. To evaluate a new query image, we extract SIFT interest points and...
We demonstrate that visual (geometric) patterns can be robustly recognized by an artificial retina composed of a chaotic sensitive system where the coding of the patterns is by attractor features and an artificial neural network is used to classify the attractors. This opens the door to sensorial systems that mimic the biological ones. The specificity of solutions of chaotic systems to their parameters...
Antinuclear autoantibodies (ANAs) are important markers to diagnose autoimmune diseases, very serious and also invalidating illnesses. The benchmark procedure for ANAs diagnosis is the indirect immunofluorescence (IIF) assay performed on the HEp-2 substrate. Medical doctors first determine the fluorescence intensity exhibited by HEp-2 cells, and then report the staining pattern for positive wells...
Scale invariance is a desirable property for many vision tasks such as image segmentation and classification. One way to achieve such invariance is to collect images containing objects of all scales and then train a classifie r. In practice, however, only a finite number of images at a finite number of scales can be collected, and this poses the problem of scale sampling. In this paper, we focus on...
We use video metadata to perform activity detection from videos in the wild, particularly the TRECVID dataset. Unlike previous activity datasets (KTH, Weiz-mann, UCF sports, etc.), this test set is assembled from videos captured with a wide range of cameras, resulting in videos with different frame rates, audio/video bitrates, and resolutions. Because these measures correlate with the quality of the...
Face detection is a computer technology that determines the locations and sizes of human faces in arbitrary (digital) images. It detects facial features and ignores anything else, such as buildings, trees and other parts of the body. In this paper, we present a face detection system based on the Schneiderman-Kanade method. This system is trained using visual attributes extracted from training samples.
Traditional approaches in object class recognition utilize a large number of labeled visual examples in order to train classifiers to recognize the category of an object in a test image. However, the need for a large number of training data makes the scalability of this approach problematic. In this paper, we explore the recently proposed paradigm of attribute based category recognition for object...
In our real world, there usually exist several different objects in one image, which brings intractable challenges to the traditional pattern recognition methods to classify the images. In this paper, we introduce a Conditional Random Fields (CRFs) model to deal with the Multi-label Image Classification problem. Considering the correlations of the objects, a second-order CRFs is constructed to capture...
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.