The iBVP dataset is a collection of synchronized RGB and thermal infrared videos with PPG ground-truth signals acquired from an ear. It includes manual signal quality labels and dense signal-quality assessment using the SQA-PhysMD model. The dataset is designed to induce real-world variations in psycho-physiological states and head movement.
The iBVP dataset, introduced in the paper 'iBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels', provides a comprehensive set of synchronized RGB and thermal videos with PPG signals. It is ideal for researchers working on remote photoplethysmography (rPPG) and signal quality assessment. The dataset is available for academic research purposes and can be requested by submitting a signed EULA.
The DAIC-WOZ dataset contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post-traumatic stress disorder. This repository provides code for extracting question-level features from the DAIC-WOZ dataset, which can be used for multimodal analysis of depression levels.
An evolving list of electronic media datasets used to model mental health status. This repository curates a variety of datasets from different sources, including social media platforms, online forums, and academic studies, to support research in mental health modeling and AI applications.
Lingxin (SoulChat) is a psychological health large model fine-tuned with millions of Chinese long-text instructions and multi-turn empathetic dialogue data in the field of psychological counseling.