Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection
ACII 2026· 2026
PPGFoundation Model
Summary
Dominika Kunc, Przemysław Kazienko, Stanisław Saganowski (Emognition group). arXiv 2608.14675, accepted at ACII 2026. Code: github.com/Emognition/RL-PPG.
Key facts
- License
- Not stated
Reported benchmarks
Human activity recognition (IMU)
prosi · Macro-F1 ↑
#1 of 1
0.64
7 activities, LOSO, PPG-only (Galaxy Watch 3, 25 Hz, 10 s); uniform baseline 0.14
Updated: Oct 12, 2026
Related Research
- Human activity recognition (IMU) leaderboard
Benchmark results for human activity recognition (imu)
- LIMA-Mamba: A lightweight and distribution-robust Mamba network for PPG-based biometrics
Research paper
- A Comparative Study of Signal Representations Methods and Deep Learning Architectures for PPG-Based Cuffless Blood Pressure Estimation
Seven 1D→2D transforms × several CNN variants on the UCI BP database. Best: CWT, errors reported as
- A Decodability-Grounded Audit of Clinical Prediction Claims in PPG Foundation Models
Audits frozen representations of four encoders on 37,784 MC-MED encounters via concept decodability,