2017 IEEE International Symposium on Multimedia (ISM)

11-13 Dec. 2017

Filter Results

Displaying Results 1 - 25 of 121
  • [Front cover]

    Publication Year: 2017, Page(s): c1
    Request permission for commercial reuse | |PDF file iconPDF (1676 KB)
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2017, Page(s): i
    Request permission for commercial reuse | |PDF file iconPDF (96 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2017, Page(s): iii
    Request permission for commercial reuse | |PDF file iconPDF (133 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2017, Page(s): iv
    Request permission for commercial reuse | |PDF file iconPDF (114 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2017, Page(s):v - xiii
    Request permission for commercial reuse | |PDF file iconPDF (152 KB)
    Freely Available from IEEE
  • Message from the General Co-Chairs

    Publication Year: 2017, Page(s):xiv - xv
    Request permission for commercial reuse | |PDF file iconPDF (83 KB)
    Freely Available from IEEE
  • Message from the Program Co-Chairs

    Publication Year: 2017, Page(s):xvi - xvii
    Request permission for commercial reuse | |PDF file iconPDF (84 KB)
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2017, Page(s):xviii - xix
    Request permission for commercial reuse | |PDF file iconPDF (98 KB)
    Freely Available from IEEE
  • Program Committee

    Publication Year: 2017, Page(s):xx - xxiii
    Request permission for commercial reuse | |PDF file iconPDF (107 KB)
    Freely Available from IEEE
  • Reviewers

    Publication Year: 2017, Page(s): xxiv
    Request permission for commercial reuse | |PDF file iconPDF (61 KB)
    Freely Available from IEEE
  • Boundary-Preserving Depth Upsampling Without Texture Copying Artifacts and Holes

    Publication Year: 2017, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (982 KB) | HTML iconHTML

    In this paper, we propose boundary-preserving depth upsampling without texture copying artifacts and holes. Since high-resolution (HR) color images contain many edges and textures, they inevitably cause artifacts such as texture copying when they are used in depth upsampling. Thus, we perform rolling guidance filtering on HR color images before depth upsampling to preserve object boundaries in dep... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-generation-robust Coding with JPEG XS

    Publication Year: 2017, Page(s):6 - 13
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (828 KB) | HTML iconHTML

    The JPEG committee (formally, ISO SC29 WG1) is currently standardizing a lightweight mezzanine codec for video over IP transport under the name JPEG XS. A particular challenging design constraint of this codec is multi-generation robustness, that is the necessity to minimize the error built-up under multiple re-compression cycles. In this paper, we discuss the sources of such errors, how they are ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Occlusion Robust Light Field Depth Estimation Using Segmentation Guided Bilateral Filtering

    Publication Year: 2017, Page(s):14 - 18
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (867 KB) | HTML iconHTML

    Although light field data provides abundant cues for depth estimation, light field depth estimation suffers from occlusion and uncertain edges. In this paper, we propose occlusion robust light field depth estimation using segmentation guided bilateral filtering. First, we calculate refocused images from light field data using digital refocusing. Second, we perform support vector machines (SVM) cla... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Priced-Based Fair Bandwidth Allocation for Networked Multimedia

    Publication Year: 2017, Page(s):19 - 24
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (356 KB) | HTML iconHTML

    The high demand of bandwidth from multimedia applications, specially video applications which consume the great majority of the Internet bandwidth, has caused a challenge for service providers and network operators. On the one hand, the allocation of bandwidth in a fair manner for multimedia users is necessary, so that the total utility of all users is maximized for higher quality of experience. O... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance Evaluation of Walking Imagery Training Based on Virtual Environment in Brain-Computer Interfaces

    Publication Year: 2017, Page(s):25 - 30
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (483 KB) | HTML iconHTML

    Motor imagery (MI) based on brain computer interfaces (BCIs) have been widely applied for upper limb motor rehabilitation. Due to the fact that a large number of disabled people need to restore or improve walking ability, it is also important to investigate the use of MI-based BCIs for lower limb motor rehabilitation. The brain activity of lower limb MI is more difficult to detect because of low r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Based Localization Based on Feature Scale Consistency in BOF Vector

    Publication Year: 2017, Page(s):31 - 37
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (832 KB) | HTML iconHTML

    Image search engines commonly employ the Bag Of Features (BOF) method to represent each database image with a feature vector and retrieve the best candidate using a measure of similarity to a query image vector. The BOF vector, which specifies the occurrence frequency of features, is used with Soft Assignment (SA) to find the most similar candidates which are further analyzed using geometric infor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Adaptation Approach for Viewport-adaptive 360-degree Video Streaming

    Publication Year: 2017, Page(s):38 - 44
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (680 KB) | HTML iconHTML

    In this paper, we propose a new adaptation approach for viewport-adaptive streaming of 360-degree videos over the Internet. The proposed approach is able to systematically decide quality levels of tiles according to user head movements and network conditions by taking into account not only prediction errors but also user head movements in each adaptation interval. Experimental results show that th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of Optimal Encoding Ladders for Tiled 360° VR Video in Adaptive Streaming Systems

    Publication Year: 2017, Page(s):45 - 52
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (718 KB) | HTML iconHTML

    Given the significant industrial growth of demand for virtual reality (VR), 360o video streaming is one of the most important VR applications that require cost-optimal solutions to achieve widespread proliferation of VR technology. Because of its inherent variability of data-intensive content types and its tiled-based encoding and streaming, 360o video requires new encoding l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perceptual Analysis of Perspective Projection for Viewport Rendering in 360° Images

    Publication Year: 2017, Page(s):53 - 60
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1612 KB) | HTML iconHTML

    Omnidirectional, also referred to as 360o, visual content provides an immersive experience since it allows users to view a visual scene from different directions. The overall content typically covers a full sphere, and omnidirectional videos or images are processed to obtain a projection on a 2D plane of a fraction of the sphere (aka viewport), which is shown to the user. Therefore, use... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convolutional DLSTM for Crowd Scene Understanding

    Publication Year: 2017, Page(s):61 - 68
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (518 KB) | HTML iconHTML

    With the growth of crowd phenomena in the real world, crowd scene understanding is becoming an important task in anomaly detection and public security. Visual ambiguities and occlusions, high density, low mobility and scene semantics, however, make this problem a great challenge. In this paper, we propose an end-to-end deep architecture, Convolutional DLSTM (ConvDLSTM), for crowd scene understandi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recurrent Visual Relationship Recognition with Triplet Unit

    Publication Year: 2017, Page(s):69 - 76
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (689 KB) | HTML iconHTML

    The task of visual relationship recognition (VRR) is recognizing multiple objects and their relationships in an image. A fundamental difficulty of this task is class-number scalability, since the number of possible relationships we need to consider causes combinatorial explosion. Another difficulty of this task is modeling how to avoid outputting semantically redundant relationships. To overcome t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Pre-Saliency Map Based Blind Image Quality Assessment via Convolutional Neural Networks

    Publication Year: 2017, Page(s):77 - 82
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (652 KB) | HTML iconHTML

    In recent years, various approaches have been investigated towards blind image quality assessment (IQA) with high accuracy and low complexity. In this paper we develop a pre-saliency map based blind IQA method, which takes advantage of saliency information in prior of quality prediction for performance enhancement by two steps. 1) We split the image into patches and design a convolution neural net... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human Action Classification Using Temporal Slicing for Deep Convolutional Neural Networks

    Publication Year: 2017, Page(s):83 - 90
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (515 KB) | HTML iconHTML

    Artificial Neural Networks are a widely used computing system implemented for a wide variety of tasks and problems. A common application of such networks is classification problems. However, a significant amount of this research focuses on one and two-dimensional information, such as vectorized data and images. There is limited research performed on three-dimensional media such as video clips. Thi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rate-Accuracy Optimization of Deep Convolutional Neural Network Models

    Publication Year: 2017, Page(s):91 - 98
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (223 KB) | HTML iconHTML

    Recently, deep learning has enjoyed a great deal of success for computer vision problems due to its capability to model highly complex tasks, such as image classification, object detection, face recognition, among many others. Although these neural networks are nowadays very powerful, there is a huge amount of parameters (i.e. the model) that need to be learned and require considerable storage spa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Classification of Microstructures in Thermal Barrier Coating Images

    Publication Year: 2017, Page(s):99 - 106
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2084 KB) | HTML iconHTML

    Thermal plasma spraying is an important manufacturing technique that creates a thermal barrier coating to protect the surface underneath from wear, erosion, oxidation and corrosion. In this paper, we develop a new microstructure classification and quantification (MCQ) module that could fully automatically classify and quantify two types of microstructures, globular and interlamellar, in the top co... View full abstract»

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