We have provided this page because it has information that may be of interest to our users. NIST does not necessarily endorse the views expressed or the facts presented on this page. Please address comments to craig.watson@nist.gov

ANNOUNCEMENT AND CALL FOR PARTICIPATION
Second Workshop on

Empirical Evaluation Methods in Computer Vision

 
 
1 July 2000, In Conjuntion with ECCV 2000
(click here for postscript version of call for papers for the workshop)

MOTIVATION

In order for computer vision to mature from both scientific and industrial points of view, we must have objective methods for evaluating algorithms. Towards this end, we are organizing the the Second Workshop of Empirical Evaluation of Methods in Computer Vision. As with the first workshop, one of the goals of the workshop is to bring together researchers in the computer vision community to present papers and discuss methods for empirical evaluation of vision algorithms. We hope to foster interaction and discussion on this subject, and to learn from related fields that have successfully used empirical evaluation methods.  Read a report about the first evaluation workshop at CVPR'98.
 

PROGRAM

The workshop program will include tutorials, invited speakers, and presentations of contributed papers. The emphasis for the invited speakers will be on methods for statistically analyzing performance results; i.e., when is the difference in performance between two algorithms statistically significant.

Contributed papers will be reviewed based on content relevant to the theme of the workshop, with an emphasis on sound empirical methods and results. Relevant topics include, but are not limited to:

 

SCHEDULE
1 JULY 2000

8:50 Welcome H. Christensen and P. J. Phillips
9:00 Invited talk - "Vision of Performance Characterisation for Computer Vision"
K. Bowyer
10:00 "A Comparative Analysis of Cross-Correlation Matching Algorithms using a
Pyramidal Resolution Approach"
N. Roma, J Santos-Victor, and J. Tome
10:30 Coffee break
11:00 "Design of Training/Test Data Sets for Empirical Performance Evaluation"
X. Jiang, C. Irniger, and H. Bunke
11:30 "Analyzing the Performance of Bayesian Networks for Automatic
Determination of Main Subjects in Photographic Images"
A. Singhal, S. Etz, and J. Lou
12:00 Lunch
13:30 "Task-Based Evaluation of Image Diffusion Filtering Algorithms"
I. Bajla, I. Hollander, and V. Witkovsky
14:00 "Analysis of PCA-based Face Recognition Algorithms: Eigenvector
Selection and Distance Measures"
W. Yambor, B. Draper, and J. R. Beveridge
14:30 Invited talk - W. Foerstner - TBA
15:30 Coffee break
16:00 "Duality of Identification and Verification in Empirical Evaluation"
P. J. Phillips
16:30 Panel Discussion - Promotion of Empirical Evaluation
17:30 End of workshop

Related Resources:

We have provided links to these sites because they have information that may be of interest to our users. NIST does not necessarily endorse the views expressed or the facts presented on these sites. Further, NIST does not endorse any commercial products that may be advertised or available on these sites. Please address comments to craig.watson@nist.gov

Special issue of CVIU on Empirical Evaluation of Computer Vision Algorithms

Click here for call for papers.

Related webpages

Click here for European Computer Vision Net Benchmarking web page.

Click here for Workshop on Performance Characterisation and Benchmarking of Vision Systems web page.

Click here for link to Workshop on Evaluation and Validation of CV Algorithms

U of Toronto's "Delve" - "Data for Evaluating Learning in Valid Experiments"