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.
We consider the problem of finding consistent matches across multiple images. Current state-of-the-art solutions use constraints on cycles of matches together with convex optimization, leading to computationally intensive iterative algorithms. In this paper, we instead propose a clustering-based formulation: we first rigorously show its equivalence with traditional approaches, and then propose QuickMatch,...
In this paper, we first provide a new perspective to divide existing high performance object detection methods into direct and indirect regressions. Direct regression performs boundary regression by predicting the offsets from a given point, while indirect regression predicts the offsets from some bounding box proposals. In the context of multioriented scene text detection, we analyze the drawbacks...
Stereo matching is important in the area of computer vision and photogrammetry. We present a stereo matching algorithm to refine depth map by using stereo image pair. The reference image is segmented by using hill-climbing algorithm and Scale Invariant Feature Transform (SIFT) feature descriptor with Sum of Absolute Difference (SAD) local stereo matching is performed. Next, we extract a set of disparity...
It is a simple task for humans to visually identify objects. However, computer-based image recognition remains challenging. In this paper we describe an approach for image recognition with specific focus on automated recognition of plants and flowers. The approach taken utilizes deep learning capabilities and unlike other approaches that focus on static images for feature classification, we utilize...
Person re-identification in public areas (such as airports, train stations and shopping malls) has recently received increased attention within computer vision research due, in part, to the demand for enhanced levels of security. Re-identifying subjects within non-overlapped camera networks can be considered as a challenging task. Illumination changes in different scenes, variations in camera resolutions,...
In complex scenes, foreground saliency can hardly be detected completely, which may further result in the ambiguous cues of objects for other computer vision tasks. In this letter, an extended locality-constrained linear self-coding (eLLsC) scheme is proposed to assist to solve the saliency detection problem under the complex scenes. The locality of both spatial relation and feature distance is preserved...
Loop closure detection is an important part of visual simultaneous location and mapping (SLAM) system. Most of traditional loop closure detection approaches using hand-crafted features often lack robustness with respect to object occlusions and illumination changes, especially for the complicated indoor environment. Recently, convolutional neural network (CNN) makes a huge impact on many computer...
We present a novel method called Contextual Pyramid CNN (CP-CNN) for generating high-quality crowd density and count estimation by explicitly incorporating global and local contextual information of crowd images. The proposed CP-CNN consists of four modules: Global Context Estimator (GCE), Local Context Estimator (LCE), Density Map Estimator (DME) and a Fusion-CNN (F-CNN). GCE is a VGG-16 based CNN...
Feature selection is playing an increasingly significant role with respect to many computer vision applications spanning from object recognition to visual object tracking. However, most of the recent solutions in feature selection are not robust across different and heterogeneous set of data. In this paper, we address this issue proposing a robust probabilistic latent graph-based feature selection...
This paper is the first to address the problem of unsupervised action localization in videos. Given unlabeled data without bounding box annotations, we propose a novel approach that: 1) Discovers action class labels and 2) Spatio-temporally localizes actions in videos. It begins by computing local video features to apply spectral clustering on a set of unlabeled training videos. For each cluster of...
As the deep learning exhibits strong advantages in the feature extraction, it has been widely used in the field of computer vision and among others, and gradually replaced traditional machine learning algorithms. This paper first reviews the main ideas of deep learning, and displays several related frequently-used algorithms for computer vision. Afterwards, the current research status of computer...
Faster R-CNN (R corresponds to “Region”) which combined the RPN network and the Fast R-CNN network is one of the best ways to object detection of R-CNN series based on deep learning. The proposal obtained by RPN is directly connected to the ROI Pooling layer, which is a framework for CNN to achieve end-to-end object detection. The feasibility of Faster R-CNN implementation of ResNet101 network and...
In this paper we propose a new solution to the text detection problem via border learning. Specifically, we make four major contributions: 1) We analyze the insufficiencies of the classic non-text and text settings for text detection. 2) We introduce the border class to the text detection problem for the first time, and validate that the decoding process is largely simplified with the help of text...
The problem of transferring a deep convolutional network trained for object recognition to the task of scene image classification is considered. An embedded implementation of the recently proposed mixture of factor analyzers Fisher vector (MFA-FV) is proposed. This enables the design of a network architecture, the MFAFVNet, that can be trained in an end to end manner. The new architecture involves...
We present a novel deep learning architecture for fusing static multi-exposure images. Current multi-exposure fusion (MEF) approaches use hand-crafted features to fuse input sequence. However, the weak hand-crafted representations are not robust to varying input conditions. Moreover, they perform poorly for extreme exposure image pairs. Thus, it is highly desirable to have a method that is robust...
In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks. We propose a unified network that simultaneously localizes and recognizes text with a single forward pass, avoiding intermediate processes, such as image cropping, feature re-calculation, word separation, and character grouping. In contrast to existing...
Automatic kinship verification from facial information is a relatively new and open research problem in computer vision. This paper explores the possibility of learning an efficient facial representation for video-based kinship verification by exploiting the visual transformation between facial appearance of kin pairs. To this end, a Siamese-like coupled convolutional encoder-decoder network is proposed...
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attentionbased...
We propose a no-reference image quality assessment (NR-IQA) approach that learns from rankings (RankIQA). To address the problem of limited IQA dataset size, we train a Siamese Network to rank images in terms of image quality by using synthetically generated distortions for which relative image quality is known. These ranked image sets can be automatically generated without laborious human labeling...
In this work we propose a novel framework named Dual-Net aiming at learning more accurate representation for image recognition. Here two parallel neural networks are coordinated to learn complementary features and thus a wider network is constructed. Specifically, we logically divide an end-to-end deep convolutional neural network into two functional parts, i.e., feature extractor and image classifier...
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.