Estimating semantic correspondence between pairs of images can be challenging as a result of intra-class variation, background clutter, and repetitive patterns. This paper proposes a convolutional neural network (CNN) that attempts to learn rich semantic representations that contain the global semantic context to enable robust semantic correspondence estimation against intra-class variation and repetitive patterns. We introduce a global context fused feature representation that efficiently emplo...
Owing to the low number of submodules (SMs) in modular multilevel converters (MMCs), especially in medium-voltage applications, the output current and voltage generated by conventional nearest-level control (NLC) methods contain evident distortions. Previously, various hybrid and level-increased NLC methods have been proposed to improve the output voltage quality, but such measures wither increased the complexity or did not regulate all the control objectives simultaneously. To further enhance t...
Last. Nikola Kasabov(AUT: Auckland University of Technology)H-Index: 65
view all 4 authors...
Specular highlights often exist in real-world images due to the material property of objects and the capturing environments. High light in real-life scenes can reduce image quality and cause loss of image information, to overcome this, we propose an effective specular reflection image enhancement algorithm. First, the scene depth map of specular reflection image was obtained by the color attenuation prior method; then, two adaptive adjustment factors were developed to optimize the transmission m...
Last. Yigang Wang(HDU: Hangzhou Dianzi University)H-Index: 6
view all 4 authors...
Nonnegative Matrix Factorization (NMF) is a popular technique for machine learning. Its power is that it can decompose a nonnegative matrix into two nonnegative factors whose product well approximates the nonnegative matrix. However, the nonnegative constraint of the data matrix limits its application. Additionally, the representations learned by NMF fail to respect the intrinsic geometric structure of the data. In this paper, we propose a novel unsupervised matrix factorization method, called R...
In the context of mathematical morphology, component-graphs are complex but powerful structures for multi-band image modeling, processing, and analysis. In this work, we propose a novel multi-band object detection method relying on the component-graphs and statistical hypothesis tests. Our analysis shows that component-graphs are better at capturing image structures compared to the classical component-trees, with significantly higher detection capacity. Besides, we introduce two filtering algori...
Last. Xiaofeng Yang(BJTU: Beijing Jiaotong University)H-Index: 88
view all 5 authors...
Featured with the simple structure, V-clamp multilevel converter (VMC) shows good prospect in the high-voltage and high-power applications. But VMC is endangered by the deviation of dc-link capacitors voltage, especially under the high modulation index (MI) and high power factor (PF) condition. Thus, a voltage balancing strategy for three-phase seven-level VMC is proposed in this paper. This strategy re-designs the carriers and reference to achieve capacitors voltage balancing with reduced switc...
Last. Ulises Cortés(BSC: Barcelona Supercomputing Center)H-Index: 28
view all 5 authors...
Convolutional Neural Networks (ConvNets) at present achieve remarkable performance in image classification tasks. However, current ConvNets cannot guarantee the capabilities of the mammalian visual systems such as invariance to contrast and illumination changes. Some ideas to overcome the illumination and contrast variations usually have to be tuned manually and tend to fail when tested with other types of data degradation. In this context, we present a new bio-inspired entry layer, M6, which de...
Microwave atmospheric pressure plasma jets continue to evolve with the growth of atmospheric plasma’s applications in sterilization, material modification, and cancer treatment. In this article, continuous and modulated microwave plasma filaments were produced by a hand-held microwave plasma jet, and then they were compared in plasma length, electron temperature, and emission spectrum. The electron temperature was measured by the emission spectroscopy diagnostic method, and the regularities of t...
Emerging wireless networks possess the potential to achieve levels of connectivity and Quality-of-Service (QoS) that are orders of magnitude higher than today’s networks. Realizing the potential of these networks will require flexible, low cost, and accurate Digital Signal Processing (DSP). Supervised Learning (SL) models employing unknown parameter estimation and classification techniques have experienced widespread use in physical (PHY) layer wireless communication systems since they can achie...
Road vehicles have incorporated several functionalities over the last decade, with an increasing incorporation of electronic embedded systems. Most of those functionalities are controlled, managed, and supervised by distributed software, within many interconnected Electronic Control Units (ECUs). Within such context, new methodologies for tests of the distributed software functions must be developed to ensure proper performance at the integration level, complying with the requirement specificati...
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies. To learn more, you can find in our Privacy Policy.