The First IEEE International Workshop on Computer Vision for Converging Perspectives



(in conjunction with ICCV 2013)


Important Dates:


Paper Submission Due

Sep 11, 2013


Acceptance Notification

Oct 7, 2013


Final Manuscript

Oct 13, 2013


Workshop on

Dec 8, 2013




We now live in a world that can be thought of a massive heterogeneous visual sensor network with devices ranging from first-person vision systems to unmanned aerial imaging platforms capable of sensing the world around us from wildly different perspectives. The images captured from these different perspectives are complementary, and so fusing them is a logical approach for improving vision-based object and event understanding. For example, while a wearable camera mounted on a subject can capture an event closely and in great detail, an aerial imaging system observing the event from above can provide the geospatial context necessary to interpret the event. The key to integrating these different perspectives—to get them to converge—is, of course, location.


We feel that due to the growing availability of geo-referenced images and videos, the time is right to investigate the research challenges and opportunities involved with jointly analyzing images and videos captured from different devices and from wildly varying perspectives but of the same location. Combining this heterogeneous visual data could lead to improved data organization strategies, event understanding systems, and transformative solutions for computer vision challenges. The focus of this workshop therefore is to explore techniques that can exploit the rich data provided by converging perspectives, such as first-person cameras, street view sensors, mobile phones, and aerial images.

Call for Papers:

The aim of this workshop on Computer Vision for Converging Perspectives is to bring together interested researchers from academia, government, and industry working in the field of computer vision, machine learning, pattern recognition, and remote sensing to address the challenges involved in developing vision systems capable of assimilating image and video data from heterogeneous, multiscale and multi-perspective visual sensing platforms for actionable intelligence and scientific discoveries. The workshop will provide an interactive forum to engage in discussions, shape potential research directions, and disseminate recent research results. This workshop invites contributions in the form of original papers to the following areas:

-Complex event understanding through visual data fusion

-Advanced image indexing and retrieval

-Spatio-temporal integration of visual observations

-First-person vision meets aerial vision

-Data fusion for scene classification

-Heterogeneous and multi-perspective imaging architectures

-Geospatial context for social media analysis

-Big data challenges in heterogeneous imaging networks

-Knowledge transfer between personal photos/videos and streetview images

-Registration of social network data with streetview images

-Integrating remote and proximate sensing land use/cover map classification and validation

Further, to stimulate the research in this emerging area, we provide an extensive dataset of geo-coincident imagery for the workshop participants to explore.


Submission and Reiview Policy:

We solicit high quality research papers (max 8 pages) and visionary position papers (max 8 pages). By submitting to this workshop, the author acknowledges that the manuscript has not been previously published or accepted for publication in substantially similar form in an archival peer-reviewed forum. All accepted papers will be allocated up to 8 pages in the proceedings and will be charged a flat fee of US$200. Each paper will be reviewed by at least three reviewers from the program committee. Papers with more than 8 pages will be rejected. A complete paper should be submitted using the below templates, which are blind-submission review-formatted templates. Please refer to the below files for formatting

LaTeX/Word Templates (tar): iccv2013AuthorKit.tgz

LaTeX/Word Templates (zip):


At least one author of the paper should register for the workshop through the ICCV'13 conference website and present their paper at the workshop.



For visa details to attend this workshop please refer to the ICCV'13 conference website: (



Workshop Chairs

Anil Cheriyadat

(Oak Ridge National Laboratory)

Shawn Newsam

(Univ. California, Merced)

Mei Han


Keynote Speakers:

Luc Vincent

Director Engineering,

Google Street View


Prof. Robert Pless

Computer Science & Eng

Washington University


Prof. A. van den Hengel

Director, ACVT

University of Adelaide, Australia


Best Paper Award:

The best paper award sponsored by Google. The best paper will be judged by the program committee.


Geo-Coincident Imagery Dataset Download

Program Committee

Art Pope (Google)

Amitha Perera (Kitware)

Cem Unsalan (U.Yeditepe Turkey)
David Crandall (Indiana Univ.)
James Hays (Brown U.)
Jana Kosecka (GMU)

Jiangye Yuan (ORNL)
Kim Boyer (RPI)
Matthew Klaric (U. of Missouri)
Nathan Jacobs (U. of Kentucky)
Selim Aksoy (Bilkent Univ.)
Silvio Savarese (U. Michigan)
Sudeep Sarkar (U. South Florida)
Tony Han (U. Missouri-Columbia)
Yanxi Liu (Penn State)

Ruisheng Wang (U. Calgary)

Jan Wegner (ETH)