springeropen.

com
Call for
Papers
EURASIP Journal on
Image and Video Processing
Special Issue on
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 recogni-
tion (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. This spans a number of important problems at multiple stages of the
image analysis pipeline. For instance: at the lowest level, denoising techniques in the area of compu-
tational photography learn image priors to recover a hypothesized clean image; at the highest level,
object detectors learn deformable parts to indentify relevant visual categories in the presence of
millions of unknown and irrelevant inputs. And in-between there is a host of problems that can be
approached by reasoning about potential features and exploiting learned context. Thus, this special
issue will consider articles with some aspect in large-scale learning, deep learning, feature learning,
and information fusion emerging approaches making a strong impact on challenging problems
where more good work is needed.
New original contributions for the related topics of interest below will be solicited from the
computer vision, machine learning, biometrics and image and video forensics communities.
springeropen.com EURASIP Journal on Image and Video Processing
A05752
Submission schedule
Manuscript due:
December 20th, 2014
Submission Instructions
Before submission authors should carefully read over the Instructions for Authors, which
are located at jivp.eurasipjournals.com/authors/instructions. Prospective authors should
submit an electronic copy of their complete manuscript through the SpringerOpen submis-
sion system at jivp.eurasipjournals.com/manuscript according to the submission schedule.
They should choose the correct Special Issue in the sections box upon submitting. In
addition, they should specify the manuscript as a submission to the Special Issue on Large
Scale Learning for Media Understanding in the cover letter. All submissions will undergo
initial screening by the guest editors for ft to the theme of the special issue and prospects for
successfully negotiating the review process.
Lead guest editor
Prof. Anderson Rocha, Institute of Computing, University of Campinas, Brazil
anderson.rocha@ic.unicamp.br
Guest editor
Dr. Walter J. Scheirer, Harvard University
wscheirer@fas.harvard.edu
Topics are expected to contain material related to statistical learning and related approaches .
Potential topics include:
Visual Representations (what to learn)
Recognition (how to learn)
Evaluation (methodology)

Applications (purpose of learning)

Benchmarking on Large-scale problems/
algorithms (pros and cons)

Benchmarks of existing algorithms

Novel data sets and evaluation regimes

Biomedical imaging and visualization

Biometrics

Document processing and analysis

Image and video forensics

Robotics

Remote sensing and geophysical imaging

Virtual and augmented reality

Visual data mining

Deep learning

Feature extraction and matching

Feature learning

Image and video segmentation

Shape representation

Information and multimodal Fusion Image
and video analysis

Image and video annotation/classifcation

Image and video retrieval

Large-scale learning and Big Data