IC3D 2012 - International Conference on 3D Imaging 2012

Royal Opera House, Liège, Belgium
3-5 noon December 2012
Technically co-sponsored by the IEEE Signal Processing Society

Call for Papers
IC3D 2012 - International Conference on 3D Imaging 2012
Royal Opera House, Liège, Belgium
3-5 noon December 2012
Technically co-sponsored by the IEEE Signal Processing Society

IC3D provides in-depth coverage of all the aspects of 3D.IC3D addresses all the modalities/types of 3D, including stereoscopic, multiview (or multiscopic), lightfield (or plenoptic or integral), volumetric, holographic, and range (or depth), as well as free-viewpoint imaging/TV and wide-angle or omnidirectional imaging.IC3D considers, for each of these 3D modalities, all possible operations in each conceivable, end-to-end 3D processing chain, e.g. from the capture of real 3D images or the generation of synthetic 3D images, through pre-processing, scene modeling, compression, coding, transmission, storage, and post-processing, to visualization, printing, and other forms of exploitation.IC3D explores the many applications of each of these 3D modalities, mainly ranging from cinema and broadcast, through industry, engineering, design, science, medicine, defense, and R&D, to communication, education, and entertainment.IC3D covers all the bases for all the above topics, including the principles, theories, sciences, physics, optics, electronics, algorithms, processing, technologies, and human factors.All of the above defines what we mean by “3D imaging”.

Topics of interest
They include:
All conventional and exotic 3D modalities
All operations, applications, and bases for each 3D modality
Human 3D perception, including Vision Science
Capture and generation of 3D data
Transformation of captured and generated 3D data
Modeling of 3D scenes from captured 3D data
3D stereography
Transmission and/or storage of 3D content
3D visualization and immersion
3D input devices
3D printing
Processing of 3D data and images
3D audio
Applications of 3D

http://www.3dstereomedia.eu/en/scientific-conference

PhD position: machine learning, data mining, information retrieval

Open PhD position at the newly founded Knowledge Mining and Assessment Group (Prof. Ulf Brefeld, http://www.uni-bonn.de/~brefeld/) at Technical University of Darmstadt, Germany.

The position's focus will be on machine learning, data mining, and information retrieval, particularly on unsupervised information extraction and aggregation. Duties and responsibilities include teaching as well as academic research. The group closely collaborates with the German Institute for International Educational Research (DIPF) in Frankfurt/Main (http://www.dipf.de) and is part of the research initiative for Knowledge Discovery in the Web (http://www.werc.tu-darmstadt.de/). 

Requirements: 

The candidate should have or expect to obtain a MSc or equivalent in computer science, mathematics, or physics. 

Desirable skills:

* profound knowledge of kernel machines, structured input-output spaces, graphical models, and probabilistic inference

* strong mathematical skills

* practical experience with automatic web crawlers 

* expertise in natural language processing and information extraction

* practical experience of processing data at internet scales using Hadoop/MapReduce

* strong programming skills

* good written and spoken communication skills in German or English.

The position is a fixed-term contract with an option to extend it, provided certain conditions are met. We offer the possibility of further scientific qualification towards a doctoral degree. The salary is based on TV-TU Darmstadt (standard for employees at TU Darmstadt). A part-time working arrangement is possible.

The Department of Computer Science of TU Darmstadt is regularly ranked among the best in Germany. We invite applications from women and people with disabilities. More informations (in German): http://www.intern.tu-darmstadt.de/dez_vii/stellen/stellen_details_80832.de.jsp

Inquiries should be directed to stegmann@tk.informatik.tu-darmstadt.de. Applications (reference number 351) should be addressed to the Dean of the Department of Computer Science, Hochschulstr. 10, 64289 Darmstadt, Germany. Deadline: September 23.

ANN: Visual obs. & anal. of animal and insect behavior (VAIB12)

Visual observation and analysis of animal and insect behavior (VAIB'12)

A 1 day workshop to be held November 11, 2012 at the 2012 International Conference on Pattern Recognition Tsukuba, Japan
http://homepages.inf.ed.ac.uk/rbf/vaib12.html

There has been an enormous amount of research on analysis of video data of humans, but relatively little on visual analysis of other organisms. The goal of this workshop is to stimulate and bring together the current research in this area, and provide a forum for researchers to share expertise.

The following papers are planned for the program.

    ================
    Insects
    ================

Mapping All Social Interactions in a Honeybee Hive
C. L. Luengo Hendriks, ZQ. Yu, A. Lecocq, B. Locke, O. Terenius

Bumblebees Detection and Tracking
B. D. Miranda-Maya, J. Salas-Rodriguez, P. Vera-Alfaro

Counting the Number of Bumblebees Entering and Leaving a Beehive
J. Salas-Rodriguez, P. Vera-Alfaro, B. D. Miranda-Maya

Local Appearance Feature Based Classification of the Theraphosidae Family
Ã. Utasi

3D Tracking of Building Process in Macrotermes
K. Petersen, N. Napp, J. Chin-Lee, J. Werfel, R. Nagpal

    ================
    Flying Animals
    ================

Vision System for Wingbeat Analysis of Bats in the Wild
M. Breslav, N. Fuller, M. Betke

Analysing the hovering flight of the hummingbird using statistics of the optical flow field
F. Martínez Carrillo, A. Manzanera, E. Romero

Error Analysis and Design Considerations for Stereo Vision Systems Used to Analyze Animal Behavior
G. Towne, D. H. Theriault, Z. Wu, N. Fuller, T. H. Kunz, M. Betke

    ================
    Ground Animals
    ================

Multiple Animal Species Detection Using Robust Principal Component Analysis and Large Displacement Optical Flow
P. Khorrami, JP. Wang, T. Huang

Rat behavior: human versus automatically generated annotation
E. A. van Dam

HMM Based Behavior Recognition of Laboratory Animals
S. Sandikci, P. Duygulu

Automated tracking of motor behavior as a means to assess severity of symptoms in the 6-OHDA marmoset model of Parkinson's disease
T. Palmer, M. Santana, Fuentes, Petersson

Learning animal social behavior from trajectory features
E. Eyjolfsdottir, X. P. Burgos-Artizzu, S. Branson, K. Branson, D. J. Anderson, P. Perona

    ================
    Fish and other marine animals
    ================

Three-dimensional behavior measurements of small aquatic lives using a single camera
K. Kawasue, S. Nagatomo, Y. Oya

Using non-local background modeling to quantify the schooling behaviour of sticklebacks
S. Tavare R. Ardekani, A. K. Greenwood, C. L. Peichel

Using Sparse Representation for Fish Recognition and Verification in Real World Observation
Yi-Haur, F.-P. Lin

Long-term underwater camera surveillance for monitoring and analysis of fish populations
B. J. Boom, P. X. Huang, C. Spampinato, S. Palazzo, J. He, C. Beyan, E. Beauxis-Aussalet, J. van Ossenbruggen, G. Nadarajan, Y.-H. Chen-Burger, D. Giordano, L. Hardman, F.-P. Lin, R. B. Fisher

Marker-Based Tracking of Subsurface Locomotion in Noisy Environments
M. M. Serrano, S. Sharpe, D. I. Goldman, P. A. Vela

More information can be found at: http://homepages.inf.ed.ac.uk/rbf/vaib12.html
For registration, see the main ICPR web site: http://www.icpr2012.org

Research Assistant / PhD Student

Open research position in the context of recently funded project focused on video mining, dynamic feature selection, and multimodal sequence representation.

Contact: Maia Zaharieva

 

The Interactive Media Systems Group of the Institute of Software Technology and Interactive Systems at the Vienna University of Technology is seeking to recruit a Research Assistant in the field of multimedia retrieval for a fixed period of 3 years.

Description of the post
You will work on project funded by the Vienna Science and Technology Fund (WWTF) and focused on video mining in media repositories. The main objective of the project is the detection of unusual and, thus, potentially interesting sequences in large video collections. Core components include dynamic feature selection, multimodal sequence representation, and data mining and clustering.

You will be expected to collaborate on publications with other members of the project team with the aim of publishing in top tier international journals and conferences in the field of multimedia retrieval. You will have the opportunity to get involved in teaching at the undergraduate and graduate level. We offer a great working atmosphere as well as remuneration according to the collective bargaining agreement §48 VwGr. B1 (praedoc). Additionally, you may participate in the Vienna University of Technology’s human resources development scheme.

The Vienna University of Technology is an equal opportunity employer actively committed to ensuring diversity in all campus employment.

Minimum requirement profile

• Outstanding Master or Diploma thesis in Computer Science or related disciplines
• German and English
• Experience in media analysis and retrieval

Additional qualification profile

• Project experience
• Experience in data clustering

Your application should include the following documents:

• Letter of intent
• Scientific CV
• Certificates
• List of publications (if available)
• References (if available)

http://www.ims.tuwien.ac.at/task_detail.php?ims_id=245

Eye Tribe

Read More

The Eye Tribe creates software that allows users to interact with their mobile device just by looking at it. Activate the screen, scroll websites automatically as you read and play games using your eyes!

The image captured by the front-facing camera of the smartphone or tablet is analyzed using computer-vision algorithms. Eye Tribe software can determine the location of the eyes and estimate where you're looking on the screen with an accuracy good enough to know which icon you're looking at.

The version showcased in the videos uses the "EyeDock", an add-on with an inexpensive webcam and an infrared LED. These are standard components and can be integrated into a mobile device using the front-facing camera and a built-in LED.

The first device with the software is expected to hit the market in 2013.

Photo Search by Face Positions and Facial Attributes on Touch Devices

With the explosive growth of camera devices, people can freely take photos to capture moments of life, especially the ones accompanied with friends and family. Therefore, a better solution to organize the increasing number of personal or group photos is highly required.

In this project, we propose a novel way to search for face images according facial attributes and face similarity of the target persons. To better match the face layout in mind, our system allows the user to graphically specify the face positions and sizes on a query “canvas,” where each attribute or identity is defined as an “icon” for easier representation.

Moreover, we provide aesthetics filtering to enhance visual experience by removing candidates of poor photographic qualities. The scenario has been realized on a touch device with an intuitive user interface. With the proposed block-based indexing approach, we can achieve near real-time retrieval (0.1 second on average) in a large-scale dataset (more than 200k faces in Flickr images).

 

http://www.csie.ntu.edu.tw/~winston/projects/face/