2017 IEEE Third International Conference on Multimedia Big Data (BigMM)

19-21 April 2017

Filter Results

Displaying Results 1 - 25 of 91
  • [Front cover]

    Publication Year: 2017, Page(s): c1
    Request permission for reuse | PDF file iconPDF (4659 KB)
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2017, Page(s): i
    Request permission for reuse | PDF file iconPDF (40 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2017, Page(s): iii
    Request permission for reuse | PDF file iconPDF (109 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2017, Page(s): iv
    Request permission for reuse | PDF file iconPDF (202 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2017, Page(s):v - xi
    Request permission for reuse | PDF file iconPDF (145 KB)
    Freely Available from IEEE
  • Preface

    Publication Year: 2017, Page(s): xii
    Request permission for reuse | PDF file iconPDF (86 KB)
    Freely Available from IEEE
  • Message from the General Co-Chairs

    Publication Year: 2017, Page(s): xiii
    Request permission for reuse | PDF file iconPDF (97 KB)
    Freely Available from IEEE
  • Message from the Program Committee Chairs

    Publication Year: 2017, Page(s): xiv
    Request permission for reuse | PDF file iconPDF (76 KB)
    Freely Available from IEEE
  • Conference Organization

    Publication Year: 2017, Page(s):xv - xvii
    Request permission for reuse | PDF file iconPDF (191 KB)
    Freely Available from IEEE
  • Program Committee

    Publication Year: 2017, Page(s):xviii - xix
    Request permission for reuse | PDF file iconPDF (104 KB)
    Freely Available from IEEE
  • Conference Program

    Publication Year: 2017, Page(s): xx
    Request permission for reuse | PDF file iconPDF (143 KB)
    Freely Available from IEEE
  • Keynote Talks

    Publication Year: 2017, Page(s): xxi
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (205 KB)

    Provides an abstract for each of the keynote presentations and may include a brief professional biography of each View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical Unigram Analysis for Source Code Repository

    Publication Year: 2017, Page(s):1 - 8
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (319 KB) | HTML iconHTML

    Unigram is a fundamental element of n-gram in natural language processing. However, unigrams collected from a natural language corpus are unsuitable for solving problems in the domain of computer programming languages. In this paper, we analyze the properties of unigrams collected from an ultra-large source code repository. Specifically, we have collected 1.01 billion unigrams from 0.7 million ope... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mining Urban WiFi QoS Factors: A Data Driven Approach

    Publication Year: 2017, Page(s):9 - 16
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (605 KB) | HTML iconHTML

    WiFi networks play a significant role in providing today's wireless connectivity, therefore, understanding and improving WiFi network performance is important for today's mobile applications and services. Previous studies conducted to investigate WiFi network performance have generally been performed using specific types of WiFi networks in relatively small areas and have been limited by either th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Large-Scale Endoscopic Image and Video Linking with Gradient-Based Signatures

    Publication Year: 2017, Page(s):17 - 21
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (375 KB) | HTML iconHTML

    Given a large-scale video archive of surgical interventions and a medical image showing a specific moment of an operation, how to find the most image-related videos efficiently without the utilization of additional semantic characteristics? In this paper, we investigate a novel content-based approach of linking medical images with relevant video segments arising from endoscopic procedures. We prop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Twitter Photo Geo-Localization Using Both Textual and Visual Features

    Publication Year: 2017, Page(s):22 - 25
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (545 KB) | HTML iconHTML

    In this paper, we propose a method to add geotags to Twitter photos which have no geotags. Our objective is localizing a Twitter photo using both textual features and visual features. For localization from texts, we use GeoNLP which estimates location from location names and location-dependent named entity. For localization from visual features, we use image search for a geotagged photo database. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Walking on the Image Trail: Uncovering the Past and Predicting the Future

    Publication Year: 2017, Page(s):26 - 32
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1139 KB) | HTML iconHTML

    Predicting the temporal evolution of images is an interesting problem that has applications in surveillance, content recommendation and behavioral analysis. Given a single image or a stream of images with timestamps, the goal of this work is to predict possible images that could appear at different time instances in the future. We propose a data-driven Riemannian shape theoretic approach for this ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Salient Object Detection with Complex Scene Based on Cognitive Neuroscience

    Publication Year: 2017, Page(s):33 - 37
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (885 KB) | HTML iconHTML

    Detecting salient objects with complex backgrounds is still a challenging problem. Under the background having similar colors with complex patterns of salient objects, existing methods' performance is not satisfied, especially for multiple salient objects detection. In this paper, we propose a framework based on cognitive neuroscience to tackle with these challenges. According to cognitive neurosc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How to Promote TV Series? Evaluating Actors' Behavior on Social Media

    Publication Year: 2017, Page(s):38 - 45
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (305 KB) | HTML iconHTML

    While social networks have become primary promotion platforms for TV series, it's crucial to provide reliable measurements of promotion effectiveness for actors, which can guide them to select better promotion strategies when they post microblogs. In this article, influence indexes are proposed to measure the influence of microblogs, and some measurements on actors' microblogs also indicate and re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrated Recommendation for Public Cultural Service

    Publication Year: 2017, Page(s):46 - 49
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (257 KB) | HTML iconHTML

    Recent years recommender systems have been used in the public cultural services to provide personalized services. The single recommendation methods only cover the limited areas of interest of users. To address this issue, this paper proposes an integrated recommender system for cross-domain heterogeneous recommendations of the public cultural resources. The proposed system works on the recommendat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • T-LRA: Trend-Based Learning Rate Annealing for Deep Neural Networks

    Publication Year: 2017, Page(s):50 - 57
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (385 KB) | HTML iconHTML

    As deep learning has been widespread in a wide range of applications, its training speed and convergence have become crucial. Among different hyperparameters existed in the gradient descent algorithm, the learning rate has an essential role in the learning procedure. This paper presents a new statistical algorithm for adapting the learning rate during the training process. The proposed T-LRA (tren... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Flood Forecasting Model Based on Deep Learning Algorithm via Integrating Stacked Autoencoders with BP Neural Network

    Publication Year: 2017, Page(s):58 - 61
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (383 KB) | HTML iconHTML

    Artificial neural network (ANN) has been widely applied in flood forecasting and got good results. However, it can still not go beyond one or two hidden layers for the problematic non-convex optimization. This paper proposes a deep learning approach by integrating stacked autoencoders (SAE) and back propagation neural networks (BPNN) for the prediction of stream flow, which simultaneously takes ad... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Patch Based Semi-supervsied Linear Regression for Single Sample Face Recognition

    Publication Year: 2017, Page(s):62 - 65
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (185 KB) | HTML iconHTML

    In this paper, we propose a patch based semi-supervised linear regression (PSLR) approach to address single sample per person (SSPP) problem in face recognition, which takes full use of the unlabeled probe samples to learn facial variation information. We partition each face image into several overlapped patches, where each patch corresponds to a mapping matrix of regression model. Then, mapping m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fooling Neural Networks in Face Attractiveness Evaluation: Adversarial Examples with High Attractiveness Score But Low Subjective Score

    Publication Year: 2017, Page(s):66 - 69
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (832 KB) | HTML iconHTML

    People are fond of taking and sharing photos in their social life, and a large part of it is face images, especially selfies. A lot of researchers are interested in analyzing attractiveness of face images. Benefited from deep neural networks (DNNs) and training data, researchers have been developing deep learning models that can evaluate facial attractiveness of photos. However, recent development... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient Optimization of Convolutional Neural Networks Using Particle Swarm Optimization

    Publication Year: 2017, Page(s):70 - 73
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (795 KB) | HTML iconHTML

    This work presents methods to automatically find optimal parameter settings for convolutional neural networks (CNNs) by using an evolutionary algorithm called particle swarm optimization (PSO). Even though the parameter space is extremely large (> 1020), we experimentally show that a better parameter setting can be found for Alexnet configuration for five different image datasets. We... View full abstract»

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