6 papers
Event Detection in Videos: A Framework for the Development of New Methods
Anastasia Zakharova, Thierry Bouwmans, Anthony Cioppa +13
Event detection tasks in videos, the most important aspect of video surveillance, aim to detect events either at the pixel-level, frame-level, or clip-level. Plenty of methods inte…
A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains
Sébastien Piérard, Adrien Deliège, Anaïs Halin +1
Frequently, multiple entities (methods, algorithms, procedures, solutions, etc.) can be developed for a common task and applied across various domains that differ in the distributi…
A Hitchhiker's Guide to Understanding Performances of Two-Class Classifiers
Anaïs Halin, Sébastien Piérard, Anthony Cioppa +1
Properly understanding the performances of classifiers is essential in various scenarios. However, the literature often relies only on one or two standard scores to compare classif…
Foundations of the Theory of Performance-Based Ranking
Sébastien Piérard, Anaïs Halin, Anthony Cioppa +2
Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this…
The Tile: A 2D Map of Ranking Scores for Two-Class Classification
Sébastien Piérard, Anaïs Halin, Anthony Cioppa +2
In the computer vision and machine learning communities, as well as in many other research domains, rigorous evaluation of any new method, including classifiers, is essential. One…
Physically Interpretable Probabilistic Domain Characterization
Anaïs Halin, Sébastien Piérard, Renaud Vandeghen +10
Characterizing domains is essential for models analyzing dynamic environments, as it allows them to adapt to evolving conditions or to hand the task over to backup systems when fac…