Thursday, April 25, 2013

Computer Vision platform using Python.

SimpleCV is an open source framework for building computer vision applications. With it, you get access to several high-powered computer vision libraries such as OpenCV – without having to first learn about bit depths, file formats, color spaces, buffer management, eigenvalues, or matrix versus bitmap storage. This is computer vision made easy.

Tuesday, April 23, 2013

Open Source Software Competition

ACM Multimedia 2013
October 21-25, 2013, Barcelona, Catalunya, Spain
Open Source Software Competition Program
Important Dates
    Submission deadline: May 13, 2013 at 11:59pm PST (UTC-8)
    Notification of acceptance: June 30, 2013
    Camera-ready submission deadline: July 30, 2013
The ACM Multimedia Open Source Software Competition celebrates the invaluable contribution of researchers and software developers who advance the field by providing the community with implementations of codecs, middleware, frameworks, toolkits, libraries, applications, and other multimedia software. This year will be the sixth year in running the competition as part of the ACM Multimedia program.
To qualify, software must be provided with source code and licensed in such a manner that it can be used free of charge in academic and research settings. For the competition, the software will be built from the sources. All source code, license, installation instructions and other documentation must be available on a public web page. Dependencies on non-open source third-party software are discouraged (with the exception of operating systems and commonly found commercial packages available free of charge). To encourage more diverse participation, previous years' non-winning entries are welcome to re-submit for the 2013 competition. Student-led efforts are particularly encouraged.
Authors are highly encouraged to prepare as much documentation as possible, including examples of how the provided software might be used, download statistics or other public usage information, etc. Entries will be peer-reviewed to select entries for inclusion in the conference program as well as an overall winning entry, to be recognized formally at ACM Multimedia 2013.  The criteria for judging all submissions include broad applicability and potential impact, novelty, technical depth, demo suitability, and other miscellaneous factors (e.g., maturity, popularity, student-led, no dependence on closed source, etc.).
Authors of the winning entry, and possibly additional selected entries, will be invited to demonstrate their software as part of the conference program.  In addition, accepted overview papers will be included in the conference proceedings.
Open Source Software Competition Guidelines
Authors interested in submitting an entry to the ACM Multimedia Open Source Software Competition should follow the instructions at

Multimedia Grand Challenge Solutions

What problems do Yahoo!, Microsoft, Huawei, Technicolor, NHK and Videolectures see in the future of multimedia? Try to address them by working with some of the largest multimedia collections available, including: hundred’s of thousands of training images per class for classification (Yahoo!), 1,000 video clips of raw broadcast video footage for beauty detection (NHK), 3D data of multi-view video streams, multiple humans and actions (Huawei/3DLife), 10.6 GB of training data for image retrieval (Microsoft), 17 hours of lecture videos and >1000 slides (MediaMixer/VideoLectures.NET) and TV archives (Technicolor).
The Multimedia Grand Challenge is a set of problems and issues from these industry leaders, geared to engage the multimedia research community in solving relevant, interesting  and challenging questions about industry's current and future needs and applications for multimedia.
The Grand Challenge was first presented as part of ACM Multimedia 2009 and has established itself as a prestigious competition in the multimedia community. This year's conference will continue the tradition, with both ongoing and brand new challenges.

The 2013 Multimedia Grand Challenges are:
        * NHK – Where is beauty? Grand Challenge
        * Technicolor - Rich Multimedia Retrieval from Input Videos Grand Challenge
        * Yahoo! – Large-scale Flickr-tag Image Classification Grand Challenge
        * Huawei/3DLife - 3D Human Reconstruction and Action Recognition Grand Challenge
        * MediaMixer/VideoLectures.NET - Semantic VideoLectures.NET Segmentation Service Grand Challenge
        * MSR-Bing Grand Challenge on Image Retrieval
Submissions should:
* Significantly address one of the challenges posted on the Grand Challenge web site.
* Depict working, presentable systems or demos, using the Grand Challenge dataset where provided.
* Describe why the system presents a novel and interesting solution.
The finalists will be selected by a committee consisting of academia and industry representatives, based on novelty, presentation and scientific interest of the approaches and, for the evaluation-based challenges,  on the performance against the task.
Preference is given to results that are reproducible by the research community, e.g. where the data and the source code is made available publicly.
The finalists will be  published in the proceedings and presented in a special event during the MM  2013 conference in  Barcelona. Based on the  presentation, winners  will be selected for Grand  Challenge awards. At  the conference, authors of accepted submissions will introduce the idea to the  audience, give a quick demo, and take difficult questions from the judges. Based on the presentation and the submission, a team of judges will select the top contributors.

DEADLINE: July 1st, 2013.
For more information and submission guidelines visit:

Saturday, April 20, 2013

Friday, April 19, 2013

Web based LIRE demo now online

Article from

A new web based LIRE demo is online. Within this demo you are able to search in an index of 300.000 images from the MIRFLICKR data set. Currently online queries from within the index are allowed, so no custom query images can be uploaded. The backend is plain LIRE, so there’s no search server and alike, and it’s the current SVN version. Search is done based on hashing, so the results are approximate, but they are immediately there. Also it’s just a selection of global features, but it’s enough to get the idea. The image below shows the result of two example searches.

LIRE web demo screen shots


Tuesday, April 16, 2013

Pyramid Histogram of Oriented Gradients (PHOG) implemented in LIRE

Article from:

Yesterday I checked in the latest LIRE revision featuring the PHOG descriptor. I basically goes along image edge lines (using the Canny Edge Detector) and makes a fuzzy histogram of gradient directions. Furthermore it does that on different pyramid levels, meaning that the image is split up like a quad-tree and all sub-images get their histogram. All histograms of levels & sub-images are concatenated and used for retrieval. First tests on the SIMPLIcity data set have shown that the current configuration of PHOG included in LIRE outperforms the EdgeHistogram descriptor.

You can find the latest version of LIRE in the SVN & in the nightly builds.


  • A. Bosch, A. Zisserman & X. Munoz. 2007. Representing shape with a spatial pyramid kernel. In Proceedings of CIVR ’07 — [DOI] [PDF]

NAO Writer – NAO Robot Writes Any Word (Video)

Article from:

nao robot

Franck Calzada is a real robot wizard, especially with the NAO humanoid robot from Aldebaran Robotics. He keeps on surprising me, always pleasantly, with new functionality, features, and extensions of other available routines.

This time he has his NAO executing an enhanced version of the word recognition handwriting functionality that I saw Taylor Veltrop demonstrate at the Paris Hackathon last year. Building on the original concept, Franck added speech to text word recognition, and the reverse, enabling the robot to grok and print almost any word. He's also improved the robot performance making it look much more professional.

The only minor fault I could find with Franck's implementation is the stroke order. NAO prints the characters in a very odd sequence, very different from actual handwriting - at least the handwriting of most people I know.

Tuesday, April 9, 2013

CUDA™ based implementation of CEDD


My colleague Loukas Babis has just released a CUDAbased implementation of CEDD descriptor.

Download the CUDA based implementation of CEDD

In order to execute this application, the latest version on the NVidia CUDA driver must be installed. A message stating “There is no device supporting CUDA” will appear during execution if CUDA’s GPU is not enabled or the respective driver is not up-to-date.  The cuda drivers can be found here.

Make sure to place the "cudart32_42_9.dll" file together with the application in the same directory and execute the latter using the Windows Command Prompt. Executing the application without any arguments will extract the CEDD descriptors for all images (bmp format) that are contained in the same directory as the application. Including the folder’s full path as an argument in the Command Prompt, allows the user to extract the descriptors of images stored in directories other than the one the application is in. Please note that the application only works with bmp formatted images.

Preliminary results


If you have any questions about the CUDA based implementation please don’t hesitate to send an email to Loukas Babis <>. More details, comparisons and other details will be added soon. Please note that CUDA based implementation produce a lossless representation of the descriptor.

Read more about CEDD descriptor [HERE]

Saturday, April 6, 2013

Video Browser Showdown 2014 CFP

The Video Browser Showdown (VBS) is an annual live video browsing competition where international researchers, working in the field of interactive video search, evaluate and demonstrate the efficiency of their tools.

The aim of the Video Browser Showdown is to evaluate video browsing tools for their efficiency at “Known Item Search” (KIS) tasks with a well-defined data set in direct comparison with other tools. For each KIS task the searchers need to interactively find a short video clip in a one-hour video file within a specific time limit.


The next Video Browser Showdown will take place in Dublin, Ireland on January 7, 2014, in conjunction with the 20th International Conference on MultiMedia Modeling (MMM 2014).

How to Participate?

Submit a demo paper of 2-3 pages in Springer LNCS style to the VBS track of MMM 2014.
Submission deadline: September 16, 2013
More information here…