Datasets › HARPER
HARPER (Exploring 3D Human Pose Estimation and Forecasting from the Robot’s Perspective: The HARPER Dataset)
We introduce HARPER, a novel dataset for 3D body pose estimation and forecast in dyadic interactions between users and \spot, the quadruped robot manufactured by Boston Dynamics. The key-novelty is the focus on the robot's perspective, i.e., on the data captured by the robot's sensors. These make 3D body pose analysis challenging because being close to the ground captures humans only partially. The scenario underlying HARPER includes 15 actions, of which 10 involve physical contact between the robot and users. The Corpus contains not only the recordings of the built-in stereo cameras of Spot, but also those of a 6-camera OptiTrack system (all recordings are synchronized). This leads to ground-truth skeletal representations with a precision lower than a millimeter. In addition, the Corpus includes reproducible benchmarks on 3D Human Pose Estimation, Human Pose Forecasting, and Collision Prediction, all based on publicly available baseline approaches. This enables future HARPER users to rigorously compare their results with those we provide in this work.
Source: [Download dataset] (https://github.com/intelligolabs/HARPER)
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Human Pose Forecasting | HARPER | EqMotion Average MPJPE (mm) @ 400ms 41 | EqMotion: Equivariant Multi-agent Motion Prediction with... | mediabrain-sjtu/eqmotion +1 | 3 | Compare |
| 2D Pose Estimation | HARPER | HRNet PCK 86,8 | Deep High-Resolution Representation Learning for Human... | open-mmlab/mmdetection +38 | 1 | Compare |
| 3D Pose Estimation | HARPER | HRNet + Depth Average MPJPE (mm) 151 | Deep High-Resolution Representation Learning for Human... | open-mmlab/mmdetection +38 | 1 | Compare |
Papers archive 2025-07-28
4 shown of 4 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 5. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning | 2 | 1 | 20 Mar 2023 | ran 1 of 2 samples (1 unverified) |
| Back to MLP: A Simple Baseline for Human Motion Prediction | 1 | 1 | 4 Jul 2022 | ran 3 of 7 samples (4 unverified) |
| Space-Time-Separable Graph Convolutional Network for Pose Forecasting | 1 | 1 | 9 Oct 2021 | ran 2 of 3 samples (1 unverified) |
| Deep High-Resolution Representation Learning for Human Pose Estimation | 39 | 2 | 25 Feb 2019 | ran 8 of 25 samples (17 unverified) |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- HARPER
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections