Related papers: ELSR: Extreme Low-Power Super Resolution Network F…
Recent developments and widespread in wireless sensor network have led to many routing protocols, many of these protocols consider the efficiency of energy as the ultimate factor to maximize the WSN lifetime. The quality of Service (QoS)…
Extreme learning machine (ELM), proposed by Huang et al., has been shown a promising learning algorithm for single-hidden layer feedforward neural networks (SLFNs). Nevertheless, because of the random choice of input weights and biases, the…
Recent single-image super-resolution (SISR) networks, which can adapt their network parameters to specific input images, have shown promising results by exploiting the information available within the input data as well as large external…
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results…
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient…
The recent development of light-weighted neural networks has promoted the applications of deep learning under resource constraints and mobile applications. Many of these applications need to perform a real-time and efficient prediction for…
Wearable devices are revolutionizing personal technology, but their usability is often hindered by frequent charging due to high power consumption. This paper introduces Distributed Neural Networks (DistNN), a framework that distributes…
How would a cellular network designed for maximal energy efficiency look like? To answer this fundamental question, tools from stochastic geometry are used in this paper to model future cellular networks and obtain a new lower bound on the…
The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area,…
RAW images have shown superior performance than sRGB images in many image processing tasks, especially for low-light image enhancement. However, most existing methods for RAW-based low-light enhancement usually sequentially process…
The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain,…
In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses challenges due to high computational and storage resource requirements. To address this issue, a…
Least squares kernel based methods have been widely used in regression problems due to the simple implementation and good generalization performance. Among them, least squares support vector regression (LS-SVR) and extreme learning machine…
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at…
With the rapid advancement of remote sensing technology, super-resolution image reconstruction is of great research and practical significance. Existing deep learning methods have made progress but still face limitations in handling complex…
Recent advances in deep neural networks have achieved unprecedented success in visual speech recognition. However, there remains substantial disparity between current methods and their deployment in resource-constrained devices. In this…
This paper studies the problem of real-world video super-resolution (VSR) for animation videos, and reveals three key improvements for practical animation VSR. First, recent real-world super-resolution approaches typically rely on…
Image super-resolution generation aims to generate a high-resolution image from its low-resolution image. However, more complex neural networks bring high computational costs and memory storage. It is still an active area for offering the…
Real-world video deblurring in real time still remains a challenging task due to the complexity of spatially and temporally varying blur itself and the requirement of low computational cost. To improve the network efficiency, we adopt…
Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with advances in deep neural networks (DNNs), have opened up new opportunities for enabling sustainable smart applications. Nevertheless, implementing…