Research map / Video / Video segmentation and tracking
Continuous Heart Rate Variability Estimation from Egocentric Systems for Skill Assessment
Berken Utku Demirel, Christian Holz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add low-high decomposition (ablation) | 3D backbone · egoPPG-DB HR (4 s) | MAE (bpm): 21.76 -> 14.80 | Improved |
| add cross-domain pretraining (ablation) | 3D backbone + low-high · egoPPG-DB HR (4 s) | MAE (bpm): 14.80 -> 12.72 | Improved |
| add cross-domain pretraining (ablation) | 3D backbone + low-high · egoPPG-DB IBI (4 s) | MAE (ms): 117.72 -> 105.91 | Improved |
| use Fourier magnitude input in pretraining (ablation) | EgoHRV · egoPPG-DB HR (4 s) | MAE (bpm): 14.87 -> 12.72 | Improved |
| add NLL objective in pretraining (ablation) | EgoHRV · egoPPG-DB HR (4 s) | MAE (bpm): 15.34 -> 12.72 | Improved |
| add NLL objective in pretraining (ablation) | EgoHRV · egoPPG-DB HR (4 s) | Pearson r: 0.08 -> 0.42 | Improved |
| use U-Net instead of 3-layer MLP encoder (ablation) | EgoHRV · egoPPG-DB HR (4 s) | MAE (bpm): 13.40 -> 12.72 | Improved |
| replace PulseFormer with EgoHRV | EgoHRV · egoPPG-DB HR (4 s) | MAE (bpm): 22.10 -> 12.72 | Improved |
| replace PulseFormer with EgoHRV | EgoHRV · egoPPG-DB SDNN | MAE (ms): 33.71 -> 10.89 | Improved |
| add HRV features instead of 60 s mean HR | TimeSformer proficiency · EgoExo4D (Ego) | top-1 accuracy (%): 44.30 -> 46.75 | Improved |
| add uncertainty log-variance to HRV features (ablation) | PhysFusion · EgoExo4D (Ego) | top-1 accuracy (%): 45.31 -> 46.75 | Improved |
| add IMU input to uncertainty head (ablation) | EgoHRV · uncertainty calibration | expected calibration error (%): 20.0 -> 9.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PhysFormer — PhysFormer: Facial Video-Based Physiological Measurement With Temporal Difference Transformer (CVPR 2022) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks (NeurIPS 2025 · similarity 0.88)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.84)
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (CVPR 2024 · similarity 0.84)
- EEVR: A Dataset of Paired Physiological Signals and Textual Descriptions for Joint Emotion Representation Learning (NeurIPS 2024 · similarity 0.83)
- WildPPG: A Real-World PPG Dataset of Long Continuous Recordings (NeurIPS 2024 · similarity 0.83)
- EgoGen: An Egocentric Synthetic Data Generator (CVPR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
