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.
Semi-supervised learning (SSL) relies on a few labeled samples to explore data's intrinsic structure through pairwise smooth transduction. The performance of SSL mainly depends on two folds: (1) the accuracy of labeled queries, (2) the integrity of manifolds in data distribution. Both of these qualities would be poor in real applications as data often consist of several irrelevant clusters and discrete...
In this paper, we propose a super resolution method based on linear regression in different middle-frequency texture categories. We benefit from the hypothesis that the mapping from middle-frequency manifold to high-frequency manifold is similar locally, and use simple linear regression method to learn mapping functions in different area of middle-frequency manifold. Different from previous works,...
This paper presents a method for recognizing aerial image categories based on matching graphlets(i.e., small connected subgraphs) extracted from aerial images. By constructing a Region Adjacency Graph (RAG) to encode the geometric property and the color distribution of each aerial image, we cast aerial image category recognition as RAG-to-RAG matching. Based on graph theory, RAG-to-RAG matching is...
The representative samples can be pictured as the skeleton of a point cloud. We learn a discrete distribution defined over all samples, so that these skeleton points have large probabilities and the outliers have probabilities close to zero. The basic assumption is that any observation is generated from a nearby skeleton point. The learning objective is to minimize the communication cost from a random...
Visual saliency plays an important role in the human visual system HVS since it is indispensable for object detection and recognition. A bottom-up saliency model was proposed, following the manifold characteristic of HVS, previously developed for understanding HVS mechanism. The saliency of a given location of visual field is defined as the power of features responses after the dimensionality reduction...
In this paper, we introduce a torus manifold-based temporal super resolution method for gait recognition from low frame-rate videos with view transitions. Given a low frame-rate gait sequence with view transition from an unknown person, we estimate three unknowns: view, phase, and style. We estimate view by walking trajectory and camera information, phase by dynamic programming using multiview exemplar...
Domain adaptation algorithms that handle shifts in the distribution between training and testing data are receiving much attention in computer vision. Recently, a Grassmann manifold-based domain adaptation algorithm that models the domain shift using intermediate subspaces along the geodesic connecting the source and target domains was presented in [6]. We build upon this work and propose replacing...
In this paper, we present a theoretical analysis on learning anchors for local coordinate coding (LCC), which is a method to model functions for data lying on non-linear manifolds. In our analysis several local coding schemes, i.e., orthogonal coordinate coding (OC-C), local Gaussian coding (LGC), local Student coding (LSC), are theoretically compared, in terms of the upper-bound locality error on...
We describe a mechanism based upon activity manifolds that map image data from more than one view to spatial pose. We learn the manifolds from training data which are motion capture data about real human subjects exercising the target actions. The nature of the training data allows the learned manifolds to conform naturally to multiple constraints, including (1) the body-part articulation constraint;...
This paper proposes a novel nonlinear manifold learning method for addressing the ill-posed problem of occluded human action analysis. As we know, a person can perform a broad variety of movements. To capture the multiplicity of a human action, this paper creates a low-dimensional manifold for capturing the intra-path and inter-path contexts of an event. Then, an action path matching scheme can be...
This paper addresses issues of online learning and occlusion handling in video object tracking. Although manifold tracking is promising, large pose changes and long-term partial occlusions of video objects remain challenging. We propose a novel manifold tracking scheme that tackles such problems, with the following main novelties: (a) Online estimation of object appearances on Grassmann manifolds;...
Due to the high degree of freedom found in hand motion, it is difficult to model articulated hand configurations. In addition, observed hand shapes vary according to the hand rotation, even when using the same hand configuration. This paper presents a new manifold embedding method for modeling low dimensional hand configurations and hand rotation using a 4D torus manifold, in which the product of...
In this paper, we propose a new form of regularization that is able to utilize the label information of a data set for learning kernels. We first present the definition of extended ideal kernel for both labeled and unlabeled data of multiple classes. Based on this extended ideal kernel, we propose an ideal regularization which is a linear function of the kernel matrix to be learned. The ideal regularization...
In contrast with Isomap, which learns the low-dimension embedding, and solves problem under the classic Multi-dimension Scaling (MDS) framework, we propose a dimensionality reduction technique, called Orthogonal Isometric Projection (OIP), in this paper. We consider an explicit orthogonal linear projection by capturing the geodesic distance, which is able to handle new data straightforward, and leads...
This paper proposes a new manifold entropy function based on local tangent space (LTS). With this entropy function, we further propose a framework for image retrieval. The retrieval is treated as searching for ordered cycles by categories in image datasets. The optimal cycles can be found by minimizing our manifold entropy of images.
We present a novel method for shape analysis which represents shapes as probability density functions and then uses the intrinsic geometry of this space to match similar shapes. In our approach, shape densities are estimated by representing the square-root of the density in a wavelet basis. Under this model, each density (of a corresponding shape) is then mapped to a point on a unit hypersphere. For...
Extracting low-dimensional structures from high-dimensional space through spectral analysis has been prevalent in the fields of machine learning and computer vision. However, most manifold learning methods assume that there is a dominant low-dimensional manifold, while other variations are usually considered as noise or even ignored. This paper proposes a novel submanifold decomposition (SMD) algorithm,...
In this paper, we propose a method to recognize food images which include multiple food items considering co-occurrence statistics of food items. The proposed method employs a manifold ranking method which has been applied to image retrieval successfully in the literature. In the experiments, we prepared co-occurrence matrices of 100 food items using various kinds of data sources including Web texts,...
In this paper, we propose a novel method called THUNTER to transfer the heterogenous unlabeled data from the source domain to the target domain for clustering. Suppose the target data are a set of images, then the so-called heterogeneous unlabeled data can be a large set of text data or acoustic data. Our method aims to address how to transfer these large amount of heterogeneous data to the relatively...
This paper proposes an activity-specific 3D human pose tracking system from multiple camera views. Dimensionality reduction is used to represent a single activity in a hierarchy of low dimensional spaces. This hierarchy provides increasing independence between limbs by decoupling them, allowing higher flexibility and adaptability that result in improved accuracy. For every subspace, a deterministic...
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.