Bases de données
Le LIVIA a mis sur pied deux bases de données qu'il met à la disposition du public.
Behavioural Ambivalence / Hesitancy (BAH)
A dataset for ambivalence/hesitancy recognition in videos for participants recruited in Canada.
Behavioural Ambivalence/Hesitancy is a dataset collected for subject-based multimodal recognition of A/H in videos. It contains videos from 224 participants captured accross 9 provinces in Canada, with different age, and ethnicity. Through our web platform, we recruited participants to answer 7 questions, some of which were designed to elicit A/H while recording themselves via webcam with microphone.
SR-CACO-2 Dataset
The laboratory makes available to the scientific community the SR-CACO-2 dataset, derived from confocal fluorescence microscopy. This unique resource includes more than 2,200 images of the human epithelial Caco-2 cell line, captured at multiple resolutions and with three fluorescent markers. The images, organized into nearly 10,000 patches, provide a solid basis to evaluate and compare machine learning methods for single-image super-resolution (SISR).
The SR-CACO-2 dataset represents a significant scientific challenge, as it highlights the current limitations of state-of-the-art approaches in reconstructing high-resolution textures. It is distributed under a Creative Commons license (CC BY-NC-SA 4.0) and is freely accessible, along with code and pretrained model weights.