11 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…
Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models
Maxim Henry, Adrien Deliège, Sébastien Piérard +1
Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often…
What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely
Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck
Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, prec…
Multi-domain performance analysis with scores tailored to user preferences
Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck
The performance of algorithms, methods, and models tends to depend heavily on the distribution of cases on which they are applied, this distribution being specific to the applicati…
Gaze-Based Indicators of Driver Cognitive Distraction: Effects of Different Traffic Conditions and Adaptive Cruise Control Use
Anaïs Halin, Adrien Deliège, Christel Devue +1
In this simulator study, we investigate how gaze parameters reflect driver cognitive distraction under varying traffic conditions and adaptive cruise control (ACC) use. Participant…
LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation
Maxim Henry, Adrien Deliège, Adrien Deliège +2
Convolutional Neural Networks (CNN) are widely used in many computer vision tasks. Yet, their increasing size and complexity pose significant challenges for efficient deployment on…