2018 25th IEEE International Conference on Image Processing (ICIP)

7-10 Oct. 2018

Filter Results

Displaying Results 1 - 25 of 848
  • [Front cover]

    Publication Year: 2018, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (124 KB)
    Freely Available from IEEE
  • 2018 IEEE International Conference on Image Processing: Proceedings

    Publication Year: 2018, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (124 KB)
    Freely Available from IEEE
  • Copyright ©2018 by The Institute of Electrical and Electronics Engineers, Inc. All rights reserved

    Publication Year: 2018, Page(s):ii - iii
    Request permission for commercial reuse | PDF file iconPDF (147 KB)
    Freely Available from IEEE
  • ICIP 2018 Organizing Committee

    Publication Year: 2018, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (138 KB)
    Freely Available from IEEE
  • Technical Program Committee

    Publication Year: 2018, Page(s):v - xvi
    Request permission for commercial reuse | PDF file iconPDF (192 KB)
    Freely Available from IEEE
  • Message from the General Chairs

    Publication Year: 2018, Page(s):xvii - xix
    Request permission for commercial reuse | PDF file iconPDF (191 KB)
    Freely Available from IEEE
  • Technical Program Chairs' Overview

    Publication Year: 2018, Page(s):xx - xxii
    Request permission for commercial reuse | PDF file iconPDF (156 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2018, Page(s):xxiii - lxxxix
    Request permission for commercial reuse | PDF file iconPDF (336 KB)
    Freely Available from IEEE
  • Margin-Based Sample Filtering for Image Classification Using Convolutional Neural Networks

    Publication Year: 2018, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (878 KB) | HTML iconHTML

    Deep convolutional neural networks have become the state of the art methods for image classification after demonstrating very good performance on very large datasets with general visual content. Amongst the problems for training deep CNN architectures is the heavy computational cost and the large memory requirements. In this work we exploit the fact that many training samples are correctly classif... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Effnet: An Efficient Structure for Convolutional Neural Networks

    Publication Year: 2018, Page(s):6 - 10
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (353 KB) | HTML iconHTML

    With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various approaches which vary from binary networks to revised convolution layers. We offer our contribution to the latter and propose a novel convolution block which sig... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online Filter Clustering and Pruning for Efficient Convnets

    Publication Year: 2018, Page(s):11 - 15
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB) | HTML iconHTML

    Pruning filters is an effective method for accelerating deep neural networks (DNNs), but most existing approaches prune filters on a pre-trained network directly which limits in acceleration. Although each filter has its own effect in DNNs, but if two filters are same with each other, we could prune one safely. In this paper, we add an extra cluster loss term in the loss function which can force f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Can DNNs Learn to Lipread Full Sentences?

    Publication Year: 2018, Page(s):16 - 20
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (296 KB) | HTML iconHTML

    Finding visual features and suitable models for lipreading tasks that are more complex than a well-constrained vocabulary has proven challenging. This paper explores state-of-the-art Deep Neural Network architectures for lipreading based on a Sequence to Sequence Recurrent Neural Network. We report results for both hand-crafted and 2D/3D Convolutional Neural Network visual front-ends, online monot... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cyclic Annealing Training Convolutional Neural Networks for Image Classification with Noisy Labels

    Publication Year: 2018, Page(s):21 - 25
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (591 KB) | HTML iconHTML

    Noisy labels modeling makes a convolutional neural network (CNN) more robust for the image classification problem. However, current noisy labels modeling methods usually require an expectation-maximization (EM) based procedure to optimize the parameters, which is computationally expensive. In this paper, we utilize a fast annealing training method to speed up the CNN training in every M-step. Sinc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Iterative Optimization of Quarter Sampling Masks for Non-Regular Sampling Sensors

    Publication Year: 2018, Page(s):26 - 30
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (855 KB) | HTML iconHTML

    Non-regular sampling can reduce aliasing at the expense of noise. Recently, it has been shown that non-regular sampling can be carried out using a conventional regular imaging sensor when the surface of its individual pixels is partially covered. This technique is called quarter sampling (also 1/4 sampling), since only one quarter of each pixel is sensitive to light. For this purpose, the choice o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Architecture and Noise Analysis for Block-Based Compressive Imaging

    Publication Year: 2018, Page(s):31 - 35
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (896 KB) | HTML iconHTML

    This paper addresses two main issues present in compressive imaging: namely, the issue of long acquisition time by using a single-pixel sensor and that of high computational complexity for high-resolution image recovery. We show that these issues are resolved in a new architecture, which is referred to as block-based compressive imaging. The new architecture consists of a lens, a programmable aper... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-Resolution Lidar Using Random Demodulation

    Publication Year: 2018, Page(s):36 - 40
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (788 KB) | HTML iconHTML

    Recently emerging applications, such as autonomous navigation, mapping, and home entertainment, have increased the demand for inexpensive and high quality depth sensing. In this paper we fundamentally re-examine the problem, considering recent advances in photoelectric devices, increased availability of fast electronics, reduced computation cost, and developments in sensing theory. Our main contri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perceptual Evaluation of Light Field Image

    Publication Year: 2018, Page(s):41 - 45
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (888 KB) | HTML iconHTML

    Recently, light field image has attracted wide attention. However, much less work has been conducted on the perceptual evaluation of light field image. In this work, we create the first windowed 5 degree of freedom light field image database (Win5-LID) based on stereoscopic display, which provides windowed 5 DOF experience and all the depth cues of light field image. The database consists of light... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-Scale Deep Networks for Image Compressed Sensing

    Publication Year: 2018, Page(s):46 - 50
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (752 KB) | HTML iconHTML

    As a successful deep model applied in image compressed sensing, the Compressed Sensing Network (CSNet) has demonstrated superior performance to the previous handcrafted models in both running speed and reconstruction quality. However, CSNet trains different models for different sampling rates that hinders it from practical usage since too many models need to store. In this paper, we propose multi-... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution

    Publication Year: 2018, Page(s):51 - 55
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1139 KB) | HTML iconHTML

    Recent research on image super-resolution (SR) has shown that the use of perceptual losses such as feature-space loss functions and adversarial training can greatly improve the perceptual quality of the resulting SR output. In this paper, we extend the use of these perceptual-focused approaches for image SR to that of video SR. We design a 15-block residual neural network, VSRResNet, which is pre-... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Low-Light Color Image Super-Resolution Using RGB/NIR Sensor

    Publication Year: 2018, Page(s):56 - 60
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (13502 KB) | HTML iconHTML

    We propose a method for super-resolution (SR) of low-resolution (LR) color images taken in low-light scenes. Our method is based on multi-frame SR technique, which fuses multiple LR images taken at different camera positions to synthesize a high-resolution color image. Previous methods have implicitly assumed that LR images could be captured with less noise and blur. However, heavy noise and motio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Coarse-to-Fine Face Hallucination Method by Exploiting Facial Prior Knowledge

    Publication Year: 2018, Page(s):61 - 65
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1416 KB) | HTML iconHTML

    Face hallucination technique generates high-resolution (HR) face images from low-resolution (LR) ones. In this paper, we propose to use a coarse-to-fine method for face hallucination by constructing a two-branch network, which makes full use of the specific prior knowledge of face images and the advantages of generic image super-resolution (SR) methods. Specifically, we jointly build a deep neural... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Super-Resolution Using Convolutional Neural Networks Without Any Checkerboard Artifacts

    Publication Year: 2018, Page(s):66 - 70
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4117 KB) | HTML iconHTML

    It is well-known that a number of excellent super-resolution (SR) methods using convolutional neural networks (CNNs) generate checkerboard artifacts. A condition to avoid the checkerboard artifacts is proposed in this paper. So far, checkerboard artifacts have been mainly studied for linear multirate systems, but the condition to avoid checkerboard artifacts can not be applied to CNNs due to the n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense Bynet: Residual Dense Network for Image Super Resolution

    Publication Year: 2018, Page(s):71 - 75
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2690 KB) | HTML iconHTML

    This paper proposes a method, Dense ByNet, for single image super-resolution based on a convolutional neural network (CNN). The main innovation is a new architecture that combines several CNN design choices. Using a residual network as a basis, it introduces dense connections inside residual blocks, significantly reducing the number of parameters. Second, we apply dilation convolutions to increase... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • UAV Cinematography Constraints Imposed by Visual Target Tracking

    Publication Year: 2018, Page(s):76 - 80
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB) | HTML iconHTML

    Camera-equipped drones have recently revolutionized aerial cinematography, allowing easy acquisition of impressive footage. Although they are currently manually operated, autonomous functionalities based on machine learning and computer vision are becoming popular. However, the emerging area of autonomous UAV filming has to face several challenges, especially when visually tracking fast and unpred... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Evaluation Metric for Object Detection Algorithms in Autonomous Navigation Systems and its Application to a Real-Time Alerting System

    Publication Year: 2018, Page(s):81 - 85
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2996 KB) | HTML iconHTML

    An autonomous navigation system relies on a number of sensors including radar, LIDAR and a visible light camera for its operation. We focus our attention on the visible light camera in this work. Object detection is the key first step to processing the video input from the camera. Specifically, we address the problem of assessing the performance of object detection algorithms in hazardous driving ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.