Stéphane Dray

The paper analyzes changes in bird interaction networks across North America over six decades, revealing shifts driven by species abundance and human activity.

This paper improves camera trap classification models by incorporating self-attention to leverage information from multiple animal detections, enhancing species classification accuracy in both mono- and multi-species scenarios.

This paper uses correspondence analysis to study interaction networks without trait data, finding that latent traits influence niche breadths and foraging preferences in a bird-plant frugivory network.

This study uses vision-language foundation models to classify animal behaviors in camera trap images without prior training, achieving over 91% accuracy in three ungulate species.

This study evaluates the calibration of deep learning models for camera trap image sequences, showing that temperature scaling improves confidence score interpretability for ecological applications.

The paper examines how elephant carcass abundance affects hyaena and prey population dynamics in Hwange National Park using long-term data and statistical models.