ACCV Special Session: RGB-D (Xbox-Kinect) application competition

http://www.accv2012.org/sub/sub02_05.asp

The goal of this special session is to provide a platform for computer vision researchers to present their recent works, preliminary ideas and/or results related to RGB-D cameras. We provide prize awards for the first prize (USD$800) and first runner-up (USD$200) to encourage high quality submission to this special session. The competition is a peer evaluated competition. Each participant will be asked to give a poster presentation and/or demo during the special session event in the ACCV2012. The attendants of ACCV 2012 will vote for the winner of this competition.

We encourage re-submission of high quality works accepted/presented from other conferences/journals. Papers submitted to the ACCV main conferences are also welcome to submit their works to this special session. The proposals accepted to this special session are not considered as regular papers in ACCV.

What to submit:

Each team should submit a 1-2 page proposal via the special session registration website. The format of proposal is the same as the ACCV paper submission format. The submitted proposals will be included in the ACCV proceedings as a record of this special session competition.

Important Date:

August 24, 2012 Submissions Deadline

September 30, 2012 Notification of acceptance

November 6, 2012 Special Session event in ACCV

November 7-9, 2012 ACCV Main Conference

Online submission site:

https://cmt.research.microsoft.com/ACCVSS2012/

Content-Based Analysis Improves Audiovisual Archive Retrieval

Original Article: http://www.ceessnoek.info/

The paper “Content-Based Analysis Improves Audiovisual Archive Retrieval” by Bouke Huurnink, Cees Snoek, Maarten de Rijke, and Arnold Smeulders, which appears in the August issue of IEEE Transactions on Multimedia, is now available. Content-based video retrieval is maturing to the point where it can be used in real-world retrieval practices. One such practice is the audiovisual archive, whose users increasingly require fine-grained access to broadcast television content. In this paper, we take into account the information needs and retrieval data already present in the audiovisual archive, and demonstrate that retrieval performance can be significantly improved when content-based methods are applied to search. To the best of our knowledge, this is the first time that the practice of an audiovisual archive has been taken into account for quantitative retrieval evaluation. To arrive at our main result, we propose an evaluation methodology tailored to the specific needs and circumstances of the audiovisual archive, which are typically missed by existing evaluation initiatives. We utilize logged searches, content purchases, session information, and simulators to create realistic query sets and relevance judgments. To reflect the retrieval practice of both the archive and the video retrieval community as closely as possible, our experiments with three video search engines incorporate archive-created catalog entries as well as state-of-the-art multimedia content analysis results. A detailed query-level analysis indicates that individual content-based retrieval methods such as transcript-based retrieval and concept-based retrieval yield approximately equal performance gains. When combined, we find that content-based video retrieval incorporated into the archive’s practice results in significant performance increases for shot retrieval and for retrieving entire television programs. The time has come for audiovisual archives to start accommodating content-based video retrieval methods into their daily practice.

Article from http://www.ceessnoek.info/

Fusing Concept Detection and Geo Context for Visual Search

Article from http://www.ceessnoek.info/index.php/fusing-concept-detection-and-geo-context-for-visual-search/

The ICMR2012 paper Fusing Concept Detection and Geo Context for Visual Search by Xirong Li, Cees Snoek, Marcel Worring and Arnold Smeulders is now available. Given the proliferation of geo-tagged images, the question of how to exploit geo tags and the underlying geo context for visual search is emerging. Based on the observation that the importance of geo context varies over concepts, we propose a concept-based image search engine which fuses visual concept detection and geo context in a concept-dependent manner. Compared to individual content-based and geo-based concept detectors and their uniform combination, concept-dependent fusion shows improvements. Moreover, since the proposed search engine is trained on social-tagged images alone without the need of human interaction, it is flexible to cope with many concepts. Search experiments on 101 popular visual concepts justify the viability of the proposed solution. In particular, for 79 out of the 101 concepts, the learned weights yield improvements over the uniform weights, with a relative gain of at least 5% in terms of average precision.

http://www.ceessnoek.info/index.php/fusing-concept-detection-and-geo-context-for-visual-search/

OCiRis Project

http://chatzichristofis.info/?page_id=451

OCiRis is a new open source (student project) application for OCR on Android. Use your mobile phone to convert the printed text into an electronic and searchable format.

[Download Files][Download APK]

User Instructions

• Open the application “Character Recognition”.
• Aim the word with the camera. Be careful to align with the red line.

• Touch the screen, then you do not need to focus to the word as the screen is frozen.

• Drag your finger on the screen to mark the word.

• If the word is not right after the character recognition go to step 2.
• If the word is right press the button “google it!!!”

How to install the application to your Android device

1. Put the [Application] into your SD card.
2. Download ASTRO File Manager to your device. You can find it on Play Store.
3. Open ASTRO File Manager and choose “MANAGE MY FLES”
4. Choose the .apk file from your SD card and press install.
5. Now OCiRis is running to your phone!

How to run the application from eclipse

1. Download eclipse indigo (http://www.eclipse.org/downloads/).
2. Download the latest JDK (http://www.oracle.com/technetwork/java/javase/downloads/index.html) and SDK (http://developer.android.com/sdk/index.html) and make the proper settings on eclipse (http://developer.android.com/sdk/installing/index.html , http://developer.android.com/sdk/eclipse-adt.html and http://developer.android.com/sdk/installing/adding-packages.html )
3. Create a Android Virtual Device (http://developer.android.com/training/basics/firstapp/running-app.html )
4. Install C/C++ Development Tools in eclipse (http://archive.eclipse.org/technology/phoenix/demos/install-cdt/callisto-cdt.html ).
5. Import into your workspace the OCiRis.zip , the tess-two.zip and the OpenCV.zip from the folder “Eclipse exports”.
6. Close Eclipse and re-open it to save the changes from workspace.
7. Now you can see and work on our code.

Licenses

• OpenCV Licence, Intel License Agreement, For Open Source Computer Vision Library, Copyright (C) 2000-2006, Intel Corporation, all rights reserved. Third party copyrights are property of their respective owners.
• Eclipse Platform, Version: 3.7.2.v20120207-1839-9gF7UHPDFxGjd-P qDr2jX_4yKaumkoHTz04_q-q, Build id: M20120208-0800, (c) Copyright Eclipse contributors and others 2000, 2012. All rights reserved. Visit http://www.eclipse.org/platform
• Ndk android, The documentation content on this site is made available to you as part of the Android Open Source Project. This documentation, including any code shown in it, is licensed under the Apache 2.0 license, the preferred license for all parts of the of the Android Open Source Project.
• Sdk : Android Development Toolkit, Version: 18.0.0.v201203301601-306762, (c) Copyright 2007-2011 The Android Open Source Project. All rights reserved. Visit http://developer.android.com/sdk/eclipse-adt.html
• Oracle Binary Code License Agreement for Java SE
• Tesseract is released under the Apache License, Version 2.0.

About
Samaras Christos, samaraschris@hotmail.gr
Born: 7 of April 1990 in Thessaloniki, Greece. Currently studying electrical and computer engineering at Democritus University of Thrace. My studies begun in the year 2008-2009. Furthermore, I own the proficiency level certificate in English provided by the Michigan University as long and the B1 level certificate of German provided by Goethe institute .
Bampis Loukas, loukbabi@gmail.com
Born in 23 of August in Thessaloniki, Greece. Currently studying electrical and computer engineering at Democritus University of Thrace. My studies begun in the year 2008. Also, I own the lower level certificate in English provided by Cambridge.
Tsiouris Konstantinos, tsiourisk@gmail.com
Born: June 13, 1990 in Ioannina, Greece.
Currently studying in Democritus University of Thrace for electrical and computer engineer degree, since 2008. I own the Certificate of Proficiency in English provided by the Michigan University, U.S.
For any further information please contact us through e-mail on the addresses listed above.

2011 Impact Factor Values

According to the ISI Web of Knowledge, the top 10 journals in the field of “COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE” are:

1.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
2.SIAM Journal on Imaging Sciences
3.MEDICAL IMAGE ANALYSIS
4.International Journal of Neural Systems
5.IEEE TRANSACTIONS ON FUZZY SYSTEMS
6.INTERNATIONAL JOURNAL OF COMPUTER VISION
7.INTEGRATED COMPUTER-AIDED ENGINEERING
8.IEEE Computational Intelligence Magazine
9.IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
10.IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS

The top 10 journals in the field of “COMPUTER SCIENCE, INFORMATION SYSTEMS” are:

1.IEEE Communications Surveys and Tutorials
2.Journal of Chemical Information and Modeling
3.MIS QUARTERLY
4.Enterprise Information Systems
5.JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
6.Journal of Cheminformatics
7.IEEE TRANSACTIONS ON INFORMATION THEORY
8.ANNUAL REVIEW OF INFORMATION SCIENCE AND TECHNOLOGY
9.INFORMATION SCIENCES
10.IEEE WIRELESS COMMUNICATIONS

The top 6 journals with the word “Multimedia” in their title are:

1. IEEE TRANSACTIONS ON MULTIMEDIA
2. ACM Transactions on Multimedia Computing Communications and Applications
3. MULTIMEDIA SYSTEMS
4. MULTIMEDIA TOOLS AND APPLICATIONS
5. New Review of Hypermedia and Multimedia
6. IEEE MULTIMEDIA

And finally, the top 11 journals with the word “Image” in their title are:

1.MEDICAL IMAGE ANALYSIS
2.IEEE TRANSACTIONS ON IMAGE PROCESSING
3.JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION
4.COMPUTER VISION AND IMAGE UNDERSTANDING
5.JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
6.Journal of Real-Time Image Processing
7.Journal of Signal Processing Systems for Signal Image and Video Technology
8.IET Image Processing
9.Signal Image and Video Processing
10.EURASIP Journal on Image and Video Processing

For more details regarding the impact factor values please refer to ISI  Web of Knowledge