BP4D+ (MMSE) is a Binghamton multimodal spontaneous-emotion corpus with 140 subjects, high-resolution face video, thermal imagery, and synchronized physiology including heart rate and blood pressure. Access is by written institutional agreement for non-profit research.

Key numbers
How it works
No model in the hub reports results on this dataset yet.
- Reference labels
- hr, cuff bp, resp rate, emotion
Models trained or evaluated on it
FAQ
How many subjects are in BP4D+ / MMSE?
BP4D+ / MMSE has data from 140 subjects, as listed in its research record.
What signals does BP4D+ / MMSE include?
BP4D+ / MMSE includes video, thermal, bp, heart rate, respiration and EDA data.
How do I get BP4D+ / MMSE, and what is its licence?
It is available from https://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html. Access is controlled by the host (for example registration, credentialing or a data use agreement), so check the source page for the steps. No licence is recorded for it here, so check the terms on the source page before you use it.
Cite
No citation metadata yet.
Cite the ChatPPG record
Cite the dated snapshot 2026-10 for a fixed, reproducible version. Please also cite the original publications listed above.
APA
ChatPPG. (2026). BP4D+ / MMSE: dataset record (Version 2026-10) [Data set]. ChatPPG Research Hub. https://chatppg.com/research/datasets/bp4d-plus
BibTeX
@misc{chatppg_dataset_bp4d_plus,
author = {{ChatPPG}},
title = {{BP4D+ / MMSE: dataset record}},
year = {2026},
month = oct,
version = {2026-10},
howpublished = {\url{https://chatppg.com/research/datasets/bp4d-plus}},
note = {ChatPPG Research Hub, Snapshot 2026-10, https://chatppg.com/research/snapshots/2026-10}
}CITATION.cff
cff-version: 1.2.0 message: "If you use this resource, please cite it as below." type: dataset title: "BP4D+ / MMSE: dataset record" authors: - name: "ChatPPG" url: "https://chatppg.com/research/datasets/bp4d-plus" repository-artifact: "https://chatppg.com/research/snapshots/2026-10" version: "2026-10" date-released: "2026-10-26"
History
Record updated
Papers
Models
Datasets
- K-EmoConSame task: Stressmultimodal emotion in naturalistic debates (n=32, Empatica E4)32 subjects · PPG · ECG · IMU
- MAHNOB-HCISame task: Stressmultimodal emotion / implicit tagging (face video + physiology)30 subjects · PPG · ECG · Resp
WESADSame task: StressWearable Stress and Affect Detection15 subjects · PPG · ECG · IMU
