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 present a highly hardware friendly STDP (Spike Timing Dependent Plasticity) learning rule for training Spiking Convolutional Cores in Unsupervised mode and training Fully Connected Classifiers in Supervised Mode. Examples are given for a 2-layer Spiking Neural System which learns in real time features from visual scenes obtained with spiking DVS (Dynamic Vision Sensor) Cameras.
Due to increasing demand of low power computing, and diminishing returns from technology scaling, industry and academia are turning with renewed interest toward energy-efficient programmable accelerators. This paper proposes an Integrated Programmable-Array accelerator (IPA) architecture based on an innovative execution model, targeted to accelerate both data and control-flow parts of deeply embedded...
This paper proposes a modified spatially-constrained similarity measure (mSCSM) method for endosomal structure detection and localization under the bag-of-words (BoW) framework. To our best knowledge, the proposed mSCSM is the first method for fully automatic detection and localization of complex subcellular compartments like endosomes. Essentially, a new similarity score and a novel two-stage output...
Chinese traditional visual culture symbols (CT-VCSs) is formed in the tradition and has the characteristic of Chinese unique ideological and cultural connotation. It is a visual cultural heritage of Chinese culture. So the research on CT-VCSs has important practical significance. In this paper, it is mainly about the recognition and classification of CT-VCSs based on machine learning. We make use...
Sparse Bayesian Learning (SBL) is a widely used framework which helps us to deal with two basic problems of machine learning, to avoid overfitting of the model and to incorporate prior knowledge into it. In this work, multiple linear regression models under the SBL framework are used for the problem of multiclass classification when multiple subjects are available. As a case study, we apply our method...
How the brain maintains the stability of visual perception across saccade is a central question in systems neuroscience; accurately characterizing visual responses in the perisaccadic period is an important step towards understanding how the visual world is represented during saccades. Here, we develop a probabilistic model in the Generalized Linear Model framework to characterize and predict the...
This paper gives a research work in solving visual SLAM via a target-oriented tracking approach. The target-oriented tracking in this context refers to those object tracking approaches such as the well-known MeanShift but the approaches based on state-space or prediction are not included. The target-oriented tracking generally locks a dynamic or specific object which is not always available in a natural...
Visual Question Answering is a complex problem that fuses natural language and image processing to answer a question based on information from the image. The basic architecture for accomplishing this is using a CNN to extract features from the image and an RNN for the language processing, then combine the two in an MLP to produce an answer. These architectures perform well at identifying content,...
The manual process for privacy setting could be very time-consuming and challenging for common users. By assuming that there are hidden correlations between the visual properties of images (i.e., visual features) or object classes and the privacy settings for image sharing, an effective algorithm is developed in this paper to achieve automatic prediction of image privacy, so that the best-matching...
Hashing methods have proven to be useful for a variety of tasks and have attracted extensive attention in recent years. Various hashing approaches have been proposed to capture similarities between textual, visual, and cross-media information. However, most of the existing works use a bag-of-words methods to represent textual information. Since words with different forms may have similar meaning,...
We describe our experiences in the classroom using the internet to collaboratively verify a significant safety and security property across the entire Linux kernel. With 66,609 instances to check across three versions of Linux, the naive approach of simply dividing up the code and assigning it to students does not scale, and does little to educate. However, by teaching and applying analytical reasoning,...
Kernel function implicitly maps data from its original space to a higher dimensional feature space. Kernel based machine learning algorithms are typically applied to data that is not linearly separable in its original space. Although kernel methods are among the most elegant part of machine learning, it is challenging for users to define or select a proper kernel function with optimized parameter...
Hand-engineered local image features have been proven to be intended representation for a variety of high-level visual recognition tasks. But as the visual recognition tasks such as scene classification and object detection become more challenging, the semantic gap between low-level feature and the concept descriptor of the scene images increases. In this paper, we present novel semantic multinomial...
Interpolation tool plays a vital role in estimating missing values. This classical problem aims to preserve the structural information-edges and textures, in the resultant image. In this process of developing a continuous function, distractions such as blur, noise or other artifacts should not be entertained. This paper provides an overview of commonly used interpolation algorithms. Comparative discussions...
In content-based image retrieval systems, visual content of the image is the criterion for measuring image similarity. We propose a method to solve the problem of loss of spatial information of objects when local descriptors from an image with multiple objects are aggregated to form a global representation. In our approach, after saliency-based spatial partitioning, local feature descriptors from...
Compressed domain human action recognition algorithms are extremely efficient, because they only require a partial decoding of the video bit stream. However, the question what exactly makes these algorithms decide for a particular action is still a mystery. In this paper, we present a general method, Layer-wise Relevance Propagation (LRP), to understand and interpret action recognition algorithms...
Correlation filter-based tracking methods have accomplished competitive performance on accuracy and robustness, but there is still a huge potential in choosing suitable features. Recently, Convolutional Kernel Networks (CKN), which provide a fast and simple procedure to approximate kernel descriptors, have been proposed and achieved state-of-the-art performance in many vision tasks. In this paper,...
One of the fundamental functionalities for autonomous navigation of Unmanned Aerial Vehicles (UAVs) is the hovering capability. State-of-the-art techniques for implementing hovering on standard-size UAVs process camera stream to determine position and orientation (visual odometry). Similar techniques are considered unaffordable in the context of nano-scale UAVs (i.e. few centimeters of diameter),...
This paper proposes a novel audio-visual tracking approach that exploits constructively audio and visual modalities in order to estimate trajectories of multiple people in a joint state space. The tracking problem is modeled using a sequential Bayesian filtering framework. Within this framework, we propose to represent the posterior density with a Gaussian Mixture Model (GMM). To ensure that a GMM...
Visual object tracking is a fundamental task in many high-level computer vision applications. Most existing algorithms have to build complex models with expensive computation to achieve accurate object tracking, which brings significant difficulty in real-time tracking. In order to address this problem, motivated by recent success of high-speed correlation filter (CF) models, a novel real-time object...
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.