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.
Multi-instance multi-label (MIML) learning has many interesting applications in computer visions, including multi-object recognition and automatic image tagging. In these applications, additional information such as bounding-boxes, image captions and descriptions is often available during training phrase, which is referred as privileged information (PI). However, as existing works on learning using...
The CNN-RNN design pattern is increasingly widely applied in a variety of image annotation tasks including multi-label classification and captioning. Existing models use the weakly semantic CNN hidden layer or its transform as the image embedding that provides the interface between the CNN and RNN. This leaves the RNN overstretched with two jobs: predicting the visual concepts and modelling their...
Linking two data sources is a basic building block in numerous computer vision problems. Canonical Correlation Analysis (CCA) achieves this by utilizing a linear optimizer in order to maximize the correlation between the two views. Recent work makes use of non-linear models, including deep learning techniques, that optimize the CCA loss in some feature space. In this paper, we introduce a novel, bi-directional...
This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale. The deep network to control actions is pre-trained using various training sequences...
We propose an extremely simple but effective regularization technique of convolutional neural networks (CNNs), referred to as BranchOut, for online ensemble tracking. Our algorithm employs a CNN for target representation, which has a common convolutional layers but has multiple branches of fully connected layers. For better regularization, a subset of branches in the CNN are selected randomly for...
This paper proposes a hybrid negative correlation learning in which each individual neural network in an neural network ensemble would either learn a data point by negative correlation learning or learn to be different to the neural network ensemble. The implementation is through randomly splitting the training set into two subsets for each individual neural network in learning. On one subset of the...
This paper aims to test the hypothesis that audiovisual perceptual feedback based training can improve the sound localization accuracy and the navigational skills in a virtual auditory display where 3D sounds are created using non-individualized HRTFs. In our experiment, we tested the spatial auditory localization performance of nine sighted subjects prior and consequently a series of training procedures...
Many approaches to recognising emotions from metrical data such as EEG signals rely on identifying a very small number of classes and to train a classifier. The interpretation of these classes varies from a single emotion such as stress [24] to features of emotional model such as valence-arousal [4]. There are two major issues here. First classification approach limits the analysis of the data within...
In this work we derive a novel clustering scheme for hyperspectral pixels according to the material they sense. We utilize statistical correlations that pixels sensing the same material exhibit. Specifically, kernel learning is combined with a norm-one regularized canonical correlations framework that can perform data clustering on nonlinearly dependent data. To tackle the derived minimization formulation...
At present, it is a great challenge that solving high-dimension and text sparsity problems in short text classification. To resolve these problems, this paper proposes a method which takes the correlation between lexical items and tags before completing Latent Dirichlet Allocation(LDA) topic model. Meanwhile, this paper adjusts parameters of Support Vector Machine(SVM) to find the optimal values by...
This paper discusses a methodology to construct a synthetic dataset using realistic geophysical data and the L-MEB model to compute synthetic brightness temperatures (Tb's) and to train a Neural Network (NN) for global retrievals of soil moisture (SM). The trained NNs are applied to real Tb's measured by the Soil Moisture and Ocean Salinity (SMOS) satellite (L-MEB NN). The objective is twofold. First,...
In this paper, we focus on promoting multi-label learning task with ensemble learning. Compared to traditional single algorithm methods, it has been recognized that ensemble methods could achieve much better performance than each constituent learned model, especially under the conditional independence of different classifiers. Existing multi-label ensemble algorithms mainly focus on creating diverse...
Information fusion aims to exploit truthful knowledge from various sources in a reliable and accurate way. Fusion of information can be conducted at three abstraction levels including feature level, score level and decision level. The feature fusion approaches have the advantages of preserving effective discriminative structure underlying various features. In this paper, we propose an effective feature...
This study aims to improve students' argumentative capability and enable them to produce better argumentative essays. The "digital argument-map writing system" was designed for this study to help students build a complete structure of argumentation step by step so they can produce better argumentative essays with the structure as a thinking frame. We conducted an experiment to the students...
Learning evaluation in larger online university courses has become a challenge, especially in those cases when learning focuses on the development of professional skills. The objective of this article is to analyze how "authentic Assessment" applied by students correlate with the judgment of the teaching team, in the framework of a course for business and administration students. The results...
Involving users in iterative development processes is to be shown to increase the quality of health care devices and to prevent refusal. Successful use can only be achieved provided that the devices are accepted by its users. In this study potentials of user satisfaction surveys in the development of stroke rehabilitation devices are presented. The two arm-training devices Reha-Slide (RS) and Bi-Manu-Track...
Feature fusion plays an important role in target recognition, especially when single sensor's recognition capability is limited under severe situations. In view of shortcomings of Multi-set Canonical Correlation Analysis (MCCA) and its supervised modified methods in using category information in fusion projection rule learning, a generalized discriminative learning version of MCCA, termed as GDMCCA,...
We propose a novel online Attentional Recurrent Neural Network (ARNN) model for visual tracking, which exploits the feature maps of Convolutional Neural Network (CNN) inside a bounding box to identify whether this target is the one appeared in previous frames. Attention mechanism is adopted for both different parts of targets and different scales of object features. The former attention model is able...
Multi-view correlation learning has attracted great attention with the proliferation of heterogeneous data. Typical methods, such as Canonical Correlation Analysis (CCA) and its variants, usually maximize one-to-one corresponding correlation of inter-view data, while most of them neglect discriminative multi-label information and local structure of each view data. In this paper, we propose multi-label...
Nowadays cross-media retrieval is an useful technology that helps people find expected information from the huge amount of multimodal data more efficiently. A common cross-media retrieval framework is first to map features of different modalities into an isomorphic semantic space so that the similarity between heterogeneous data can be measured. For most of semantic space based methods, the mapping...
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.