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.
While metric learning is important for Person reidentification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training. However, this limits their scalabilities to realistic applications, in which a large amount...
Person re-identification (Re-ID) is an important problem in video surveillance, aiming to match pedestrian images across camera views. Currently, most works focus on RGB-based Re-ID. However, in some applications, RGB images are not suitable, e.g. in a dark environment or at night. Infrared (IR) imaging becomes necessary in many visual systems. To that end, matching RGB images with infrared images...
Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previous state-of-the-art methods using hand-crafted potentials in conventional graphical model which can only define a limited range of relations. Thus, the complex structural dependencies among individuals involved in a collective...
Composite function minimization captures a wide spectrum of applications in both computer vision and machine learning. It includes bound constrained optimization and cardinality regularized optimization as special cases. This paper proposes and analyzes a new Matrix Splitting Method (MSM) for minimizing composite functions. It can be viewed as a generalization of the classical Gauss-Seidel method...
Automatic classification of Human Epithelial Type-2 (HEp-2) specimen patterns is an important yet challenging problem in medical image analysis. Most prior works have primarily focused on cells images classification problem which is one of the early essential steps in the system pipeline, while less attention has been paid to the classification of whole-specimen ones. In this work, a specimen pattern...
In this paper, we propose a facial skin beautification framework to remove facial spots based on layer dictionary learning and sparse representation. More precisely, we first decompose the face image into three layers: lighting layer, detail layer and color layer. The corresponding detail layer dictionary are learned by using 60 thousands beauty images collected from the Internet. Thereafter, the...
The main theme of this paper is to develop a systematic framework to learn a Mahalanobis distance metric based on matrix sketching. Within this framework, we present a novel sketch metric learning algorithm which sequentially sketches the received samples from training dataset and formulates a new kind of constraint for metric learning. This is in contrast to the traditional constraints that are only...
Most existing person re-identification (re-id) models focus on matching still person images across disjoint camera views. Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the occlusion, pose and camera-view change, and lighting variation problems. In comparison, video-based re-id methods can utilize extra space-time information, which contains...
We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for recognising a target object class from the background given very limited training target samples. Unlike existing transfer learning techniques, our method does not assume that auxiliary data are labelled, nor the relationships between...
As an emerging field of speech recognition, dialect identification plays an important role for promoting applications of speech recognition technology. Since the communications among Mainland China, Hong Kong and Taiwan are becoming frequently, it is particularly necessary to identify their dialects. This paper makes contributions to this issue in the following three-folds: 1) we build a speech corpus...
A good face recognition algorithm should be robust against variations caused by occlusion, expression or aging changes etc. However, the performance of holistic feature based methods would drop dramatically as holistic features are easily distorted by those variations. SIFT, a classical sparse local feature descriptor, was proposed for object matching between different views and scales and has its...
It has been known that it is hard to capture the high-frequency components (shadows and specularities) during the modeling of illumination effects. In this paper, we propose a reflectance model to simulate the interaction of light and the facial surface under the assumption that face is strictly axial symmetry. This model works well not only in fitting the intensities of pixel but also in processing...
Multi-view clustering has become a popular clustering technique in recent years due to its ability to analyze data collected from multiple sources or represented by multiple views. In this paper, we propose a novel multi-view clustering approach termed weighted multi-view online competitive clustering (WMLCC). We simultaneously exploit the variable weighting strategy and the online competitive learning...
Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features. We propose a novel feature extraction model called Feature Fusion Net (FFN) for pedestrian image representation. In FFN, back...
In real world person re-identification (re-id), images of people captured at very different resolutions from different locations need be matched. Existing re-id models typically normalise all person images to the same size. However, a low-resolution (LR) image contains much less information about a person, and direct image scaling and simple size normalisation as done in conventional re-id methods...
We address a new partial person re-identification (re-id) problem, where only a partial observation of a person is available for matching across different non-overlapping camera views. This differs significantly from the conventional person re-id setting where it is assumed that the full body of a person is detected and aligned. To solve this more challenging and realistic re-id problem without the...
Automatic classification of Human Epithelial Type-2 (HEp-2) cells staining patterns is a challenging and important problem in the field of medical image analysis. This paper proposed an efficient framework to address the HEp-2 cell image classification problem based on wavelet scattering network and Random Forest. The wavelet scattering network computes rotation-invariant wavelet coefficients as representations...
Person re-identification aims to match people across non-overlapping camera views. For this purpose, most works exploit appearance cues, assuming that the color of clothes is discriminative in short term. However, when people appear in extreme illumination or change clothes, appearance-based methods tend to fail. Fortunately, depth images provide more invariant body shape and skeleton information...
In this paper, we focus on heterogeneous feature learning for RGB-D activity recognition. Considering that features from different channels could share some similar hidden structures, we propose a joint learning model to simultaneously explore the shared and feature-specific components as an instance of heterogenous multi-task learning. The proposed model in an unified framework is capable of: 1)...
Person re-identification is an important problem of matching persons across non-overlapping camera views. However, the re-identification is still far from achieving reliable matching. First, many existing approaches are wholebody- based matching, and how body parts could affect and assist the matching is still not clearly known. Second, the learned similarity measurement/metric is equally used for...
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.