3 papers
cs.LG2026
TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
Khalid Oublal, Quentin Bouniot, Qi Gan +2
As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-s…
cs.LG2025
Feature Impact Analysis on Top Long-Jump Performances with Quantile Random Forest and Explainable AI Techniques
Qi Gan, Stephan Clémençon, Mounîm A. El-Yacoubi +3
Biomechanical features have become important indicators for evaluating athletes' techniques. Traditionally, experts propose significant features and evaluate them using physics equ…
cs.CV2025
Polar Coordinate-Based 2D Pose Prior with Neural Distance Field
Qi Gan, Sao Mai Nguyen, Eric Fenaux +2
Human pose capture is essential for sports analysis, enabling precise evaluation of athletes' movements. While deep learning-based human pose estimation (HPE) models from RGB video…