Software and datasets released by the PHuSe Lab.
See our GitHub repository for additional project resources that you can download, use and improve. Please attribute this data to its creators in your publications and consider sharing your improved data with us and others online.
Package pyVHR (short for Python framework for Virtual Heart Rate) is a comprehensive framework for studying methods of pulse rate estimation relying on video, also known as remote photoplethysmography (rPPG).
Research: Contactless Physiological Sensing
OpenFACS is an open source FACS-based 3D face animation system. OpenFACS is a software that allows the simulation of realistic facial expressions through the manipulation of specific action units as defined in the Facial Action Coding System.
Research: 3D Computer Vision, Affective Computing
Implementation of the gaze model "On gaze deployment to audio-visual cues of social interactions".
Research: Visual Attention
Constrained Levy Exploration (CLE) generates a visual scanpath by computing gaze shifts as Levy flights on any kind of saliency map (bottom-up or top-down) computed for the given image.
Research: Visual Attention
Implementation of Ecological Sampling (ES) method, which generates gaze shifts on video clips (frame sequences) based on a stochastic model of eye guidance.
Research: Visual Attention
Implementation of the gaze model "Gazing at Social Interactions Between Foraging and Decision Theory".
Research: Visual Attention
DANTE (Dimensional ANnotation Tool for Emotions) is an emotional annotation tool to annotate any kind of video in terms of valence and arousal continuous dimensions.
Research: Affective Computing, Contactless Physiological Sensing
This package contains the Matlab implementation of R-SVD, an algorithm for dictionary learning in sparsity models based on the orthogonal Procrustes shape analysis.
Research: 3D Computer Vision
LiMapS and k-LiMapS are fast iterative methods for finding sparse solutions to underdetermined linear systems, based on a fixed-point iteration scheme which combines nonconvex Lipschitzian-type mappings with canonical orthogonal projectors.
Research: 3D Computer Vision
AMHUSE (A Multimodal dataset for HUmor SEnsing) is a multimodal dataset acquired with the aim to study emotional response in presence of amusement stimulus.
Research: Contactless Physiological Sensing, Affective Computing
