Human activity recognition leaderboard
PAMAP2: macro-F1
7 reported results for human activity recognition on PAMAP2, ranked by macro-F1. Top reported: OntoAR-HAR (87.3 ± 1.1 (%)). Every row cites its source…
This page ranks every result ChatPPG has recorded for human activity recognition on PAMAP2, measured by Macro-F1 on HAR activities (higher is better). Each number is copied from the publication cited in its row, and ranks apply only within this dataset and metric.
| Rank | Method & evaluation | Macro-F1 on HAR activities↑ Higher is better |
|---|---|---|
| 1 | OntoAR-HAR ontoar-har-ontology-guided-agentic-rag-har-2026 (OntoAR-HAR, Gemini 3.0 Flash) Evaluation detailsMean of ten samples; 2026-10-14 | 87.3 ± 1.1 (%) |
| 2 | CHEAR chear-confusion-hierarchy-evidence-aware-llm-har-2026 (CHEAR, Gemini 3 Flash) Evaluation detailsvs ZARA 76.9 in the same table; not ranked against LOSO MorphCL/HARNet; 2026-10-14 | 83.43 (%) |
| 3 | SSL ResNet, UK Biobank (Yuan) Self-supervised ResNet pre-trained on UK Biobank, all layers fine-tuned Evaluation detailsWrist accelerometer resampled to 30 Hz, 10 s windows; subject-wise 5-fold CV (leave-one-subject-out when fewer than 10 subjects); subject-wise macro F1 (Table 2). Shown in % to match this board. Reported as of: 2026-10-16 | 78.9 |
| 4 | ZARA zara-training-free-motion-reasoning-llm-agents-acl-2026 (ZARA, Gemini-2.0-Flash) Evaluation detailsHeld-out-subject class-balanced split, 12 classes — different protocol from the LOSO MorphCL/HARNet row; not ranked against it (protocol isolation). MorphCL LOSO row unchanged | 76.9 (%) |
| 5 | Random forest (Yuan) Random forest on hand-crafted features Evaluation detailsWrist accelerometer resampled to 30 Hz, 10 s windows; subject-wise 5-fold CV (leave-one-subject-out when fewer than 10 subjects); subject-wise macro F1 (Table 2). Shown in % to match this board. Reported as of: 2026-10-16 | 75.3 |
| 6 | MorphCL morphcl-morphological-contrastive-imu-har-2026 (MTL+MorphCL ResNet18, CAPTURE-24 3.7K h) Evaluation detailsLOSO, right wrist 50 Hz 2.56 s, NULL kept; comparator Yuan et al. UKB ResNet18 (harnet-ukb) 77.06 LP / 84.00 FT on same protocol (paper Table 5). | 75.15 LP / 75.80 FT (%) |
| 7 | ResNet from scratch (Yuan) ResNet-V2 trained from scratch Evaluation detailsWrist accelerometer resampled to 30 Hz, 10 s windows; subject-wise 5-fold CV (leave-one-subject-out when fewer than 10 subjects); subject-wise macro F1 (Table 2). Shown in % to match this board. Reported as of: 2026-10-16 | 60.5 |
Rows are ranked only within this task × dataset × metric. Protocols can differ; read each method's evaluation details before comparing. Latest reported row: 2026-10-16.
About the dataset
PAMAP2: Physical Activity Monitoring (n=9, 3× IMU + HR)
- Subjects
- 9
- Signals
- accel, gyro, magnetometer, skin-temp, hr
- Licence
- CC BY 4.0
Sources on this board
- OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition (paper)
- CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition (paper)
- ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents (paper)
- MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity Recognition (paper)
Related leaderboards
Other metrics on PAMAP2
Human activity recognition on other datasets
- opportunity: macro-F1 (6)
- capture-24: macro-F1 (5)
- capture-24: Cohen's kappa (4)
- mhealth: F1 (4)
- mhealth: macro-F1 (4)
- RealWorld HAR: macro-F1 (4)
- WISDM AR v1.1: accuracy (4)
- UCI Human Activity Recognition Using Smartphones (UCI-HAR): F1 (3)
- USC-HAD: F1 (3)
- DEO: balanced accuracy (1)
- har-6bench-avg: macro-F1 (1)
- HHAR: macro-F1 (1)
Data and submissions
Download every leaderboard as JSON or CSV. Missing a published result? Email hello@chatppg.com with the paper link and the exact table it comes from.
Cite this
Cite the page URL and the date you accessed it. Please also cite the original publications listed above.
APA
ChatPPG. (2026). PAMAP2 macro-F1 leaderboard: human activity recognition [Data set]. ChatPPG Research Hub. https://chatppg.com/research/leaderboards/har/pamap2-macro-f1-har
BibTeX
@misc{chatppg_har_pamap2_macro_f1_har,
author = {{ChatPPG}},
title = {{PAMAP2 macro-F1 leaderboard: human activity recognition}},
year = {2026},
month = oct,
howpublished = {\url{https://chatppg.com/research/leaderboards/har/pamap2-macro-f1-har}},
note = {ChatPPG Research Hub}
}CITATION.cff
cff-version: 1.2.0 message: "If you use this resource, please cite it as below." type: dataset title: "PAMAP2 macro-F1 leaderboard: human activity recognition" authors: - name: "ChatPPG" url: "https://chatppg.com/research/leaderboards/har/pamap2-macro-f1-har" date-released: "2026-10-16"