Skip to main content

Large Scale Learning for Media Understanding

The remarkable growth in computational power over the last decade has enabled important advances in machine learning, allowing us to achieve impressive results across all areas of image and video processing. Numerical methods that were once thought to be intractable are now commonly deployed to solve problems as diverse as 3D modeling from 2D data (photo tourism), object recognition (logo detection), human biometrics (face recognition), and video surveillance (automatic threat detection). Despite this tremendous progress, there are many open issues related to understanding visual data – we are still far from matching human visual ability in all of these areas. This special issue will look at emerging questions and algorithms related to complex visual processing tasks where machine learning is applicable.

Edited by: Anderson Rocha and Walter Scheirer

  1. Research

    Hyperspectral image classification via contextual deep learning

    Because the reliability of feature for every pixel determines the accuracy of classification, it is important to design a specialized feature mining algorithm for hyperspectral image classification. We propose...

    Xiaorui Ma, Jie Geng and Hongyu Wang

    EURASIP Journal on Image and Video Processing 2015 2015:20

    Published on: 14 July 2015

  2. Research

    Large-scale geo-facial image analysis

    While face analysis from images is a well-studied area, little work has explored the dependence of facial appearance on the geographic location from which the image was captured. To fill this gap, we construct...

    Mohammad T. Islam, Connor Greenwell, Richard Souvenir and Nathan Jacobs

    EURASIP Journal on Image and Video Processing 2015 2015:17

    Published on: 10 June 2015

  3. Research

    On the optical flow model selection through metaheuristics

    Optical flow methods are accurate algorithms for estimating the displacement and velocity fields of objects in a wide variety of applications, being their performance dependent on the configuration of a set of...

    Danillo R Pereira, José Delpiano and João P Papa

    EURASIP Journal on Image and Video Processing 2015 2015:11

    Published on: 9 May 2015

  4. Research

    A robust SVM classification framework using PSM for multi-class recognition

    Our research focuses on the question of classifiers that are capable of processing images rapidly and accurately without having to rely on a large-scale dataset, thus presenting a robust classification framewo...

    Jinhui Chen, Tetsuya Takiguchi and Yasuo Ariki

    EURASIP Journal on Image and Video Processing 2015 2015:7

    Published on: 11 March 2015