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.
Scene recognition is an important and challenging task in computer vision. We propose an end-to-end pipeline by combing convolutional neural networks (CNNs) with explicit attention model to determine several meaningful regions of original images for scene recognition. In the proposed pipeline, the spatial transformer network is leveraged as the attention module, which can automatically learn the scales...
People drive on the road and eat in the kitchen. Can the road imply driving or the kitchen imply eating? This paper addresses such a problem by studying the relations between actions and scenes. To get effective scene representation, we use a deep convolutional neural networks (CNN) model trained from a scene-centric database to predict scene responses for videos. We employ two encoding schemes based...
Pedestrian detection is one of the challenging research topics in computer vision and efficient feature representation of a pedestrian attracts more and more attention. Traditional features such as Histogram of Oriented Gradients (HOG) were widely used in pedestrian detection, but because of their poor texture description ability, these feature based methods cannot achieve satisfactory pedestrian...
In this paper, we present an object recognition and pose estimation framework consisting of a novel global object descriptor, so called Viewpoint oriented Color-Shape Histogram (VCSH), which combines object's color and shape information. During the phase of object modeling and feature extraction, the whole object's color point cloud model is built by registration from multi-view color point clouds...
Recognizing objectionable content draws more and more attention nowadays given the rapid proliferation of images and videos on the Internet. Although there are some investigations about violence video detection and pornographic information filtering, very few existing methods touch on the problem of violence detection in still images. However, given its potential use in violence webpage filtering,...
Robust scene recognition serves as an essential task for robots to work within a complex dynamic environment. Considering vision device's limited adaptability in the dark environment, a 3D-laser-based scene recognition approach that extracts and matches SIFT features from Bearing Angle images is proposed, which makes it possible to make full use of both global metric information and local scale-invariant...
Locality preserving projection (LPP) is a promising manifold learning approach for dimensionality reduction. However, it often encounters small sample size (3S) problem in face recognition tasks. To overcome this limitation, this paper proposes a discrete sine transform (DST) feature extraction approach and develops a DST-feature based LPP algorithm for face recognition. The proposed method has been...
In this paper, we propose a passive image tampering detection method based on modeling edge information. We model the edge image of image chroma component as a finite-state Markov chain and extract low dimensional feature vector from its stationary distribution for tampering detection. The support vector machine (SVM) is utilized as classifier to evaluate the effectiveness of the proposed algorithm...
Clustering Web search result is a promising way to help alleviate the information overload for Web users. In this paper, we focus on clustering snippets returned by Google Scholar. We propose a novel similarity function based on mining domain knowledge and an outlier-conscious clustering algorithm. Experimental results showed improved effectiveness of the proposed approach compared with existing methods.
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.