Postdocs/PhDs in Multimodal Biometrics and Multimedia Retrieval

Juergen Luettin luettin at idiap.ch
Tue Oct 26 12:50:23 EDT 1999


                   POSTDOC and PHD POSITIONS

                             in

          MULTIMODAL BIOMETRICS and MULTIMEDIA RETRIEVAL

                             at

                     IDIAP, Switzerland


Applications are invited for several Post-Doctoral positions and PhD
research studentships in the Computer Vision Group at IDIAP to work
in one of the following research areas (with possible research topics):

Video Indexing/Retrieval
- adaptation of video content analysis methods
- combination and integration of audio, video, and text information
- high level video structure modelling
- video abstraction/summary generation, browsing, GUI, MPEG7

Audio Indexing/Retrieval
- adaptation of speech recognition systems to video (acoustic
  models, lexicon, language models, topic)
- audio segmentation (speech, music, audio events)
- speaker change detection
- document indexing and retrieval, MPEG7

Text Segmentation and Recognition in Videos
- detection, segmentation and recognition of text embedded in video
- investigation of image properties (texture, colour, shape)
- use of temporal information
- integration of detection/segmentation algorithms with text recognition

  engine

Face Analysis
- face detection (in complex backgrounds, under variant pose, occlusion)

- face recognition (identification/verification, robustness issues,
  confidence estimation, evidence integration)

Speaker Verification
- client model adaptation
- decision strategy
- robustness to microphone/channel characteristics
- discriminant analysis

Classifier Combination
- classifier confidence estimation
- classifier combination techniques
- evidence integration
- application to multimodal biometrics, video retrieval

The successful candidates will participate in the following important
and highly competitive European and national projects:

o BANCA: Biometric Access Control for Networked and e-Commerce
  EU project, lead by Matra Nortel Communication
  http://www.idiap.ch/vision/banca.html

o ASSAVID: Automatic Segmentation and Semantic Annotation of Sports
Videos
  EU project, lead by Sony UK
  http://www.idiap.ch/vision/assavid.html

o VOCR: Text Segmentation and Recognition for Video Retrieval
  Swiss National Science Foundation project
  http://www.idiap.ch/vision/vocr.html

Several tasks will be performed in close collaboration with other
project partners including universities, industries, and end-users.

REQUIREMENTS

Postdoctoral candidates should possess a relevant PhD degree and
doctoral students an M.S. degree (or equivalent) in Computer Science
or a related area and should have a strong background in mathematics,
signal processing, and pattern recognition.

ABOUT IDIAP

IDIAP is a semi-private research institute, that conducts basic and
applied research in artificial intelligence. The main research
activities are in machine learning, speech processing, and computer
vision. Research in the rapidly growing computer vision group focuses
on topics in multimedia processing including multimodal biometrics,
multimodal speech recognition, and document analysis and recognition
(See http://www.idiap/vision).  Doctoral students at IDIAP are usually
registered at a Swiss university or Federal Institute of Technology,
often EPFL, that awards the PhD degree.

LOCATION

IDIAP is located in the town of Martigny in Valais, a scenic region in
the south of Switzerland, surrounded by some of the highest mountains
in Europe which offer some of the best skiing, hiking, and climbing.
It is within close proximity to Lausanne, and lake Geneva, and centrally

located for travel to other parts of Europe.

HOW TO APPLY

Prospective candidates should send a detailed CV, including 2 names
and addresses of referees, research interest, and earliest possible
starting date, preferably by email to

Dr. Juergen Luettin
Head, Computer Vision Group
IDIAP, CP 592, 1920 Martigny, Switzerland
Email: Luettin at idiap.ch
Tel: +41 27 721 77 27
Fax: +41 27 721 77 12







More information about the Connectionists mailing list