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/

MediaMill - Semantic Video Search Engine

The MediaMill semantic video search engine is bridging the gap between research and applications. It integrates the state-of-the-art techniques developed at the Intelligent Systems Lab Amsterdam of the University of Amsterdam and applies it to realistic problems in video retrieval.

The techniques employed in MediaMill originate from various disciplines such as image and video processing, computer vision, language technology, machine learning and information visualization. To ensure state-of-the-art competitiveness, MediaMill participates in the yearly TRECVID benchmark.

MediaMill has its roots in the ICES-KIS Multimedia Information Analysis project (in conjunction with TNO) and the Innovative Research Program for Image processing (IOP). It blossomed in the BSIK program MultimediaN and the EU FP-6 program VIDI-Video. MediaMill currently plays an important role in the Dutch VENI SEARCHER project, the Dutch/Flemish IM-Pact BeeldCanon project, the Dutch FESCOMMIT program, and the US IARPA SESAME project.

http://www.science.uva.nl/research/mediamill/index.php

ImageTerrier: An extensible platform for scalable high-performance image retrieval

ImageTerrier is a novel easily extensible open-source, scalable, high-performance search engine platform for content-based image retrieval applications. The platform provides a comprehensive test-bed for experimenting with bag-of-visual-words image retrieval techniques. It incorporates a state-of-the-art implementation of the single-pass indexing technique for constructing inverted indexes and is capable of producing highly compressed index data structures. ImageTerrier is written as an extension to the open-source Terrier, "Terabyte Retriever", test-bed platform for textual information retrieval research. The ImageTerrier platform is demonstrated to successfully index and search a corpus of over 10 million images containing just under 10,000,000,000 quantised SIFT visual terms.

http://dl.acm.org/citation.cfm?id=2324844&bnc=1