Datasets › Expi

Expi (Extreme Pose Interaction)

Introduced by Wen Guo et al. in Multi-Person Extreme Motion Prediction18 May 2021 archive 2025-07-28

Extreme Pose Interaction (ExPI) Dataset is a new person interaction dataset of Lindy Hop dancing actions. In Lindy Hop, the two dancers are called leader and follower. The authors recorded two couples of dancers in a multi-camera setup equipped also with a motion-capture system. 16 different actions are performed in ExPI dataset, some by the two couples of dancers, some by only one of the couples. Each action was repeated five times to account for variability. More precisely, for each recorded sequence, ExPI provides: (i) Multi-view videos at 25FPS from all the cameras in the recording setup; (ii) Mocap data (3D position of 18 joints for each person) at 25FPS synchronized with the videos.; (iii) camera calibration information; and (iv) 3D shapes as textured meshes for each frame.

Overall, the dataset contains 115 sequences with 30k visual frames for each viewpoint and 60k 3D instances annotated

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)PaperCode
Multi-Person Pose forecasting Expi - common actions split Best Practices for 2-Body Pose Forecasting Average MPJPE (mm) @ 1000 ms 202 Best Practices for 2-Body Pose Forecasting edodema/BestPractices2Body 6 Compare
Multi-Person Pose forecasting Expi - unseen actions split Best Practices for 2-Body Pose Forecasting Average MPJPE (mm) @ 400 ms 100 Best Practices for 2-Body Pose Forecasting edodema/BestPractices2Body 5 Compare
Human Pose Forecasting Expi - common actions split siMLPe Average MPJPE (mm) @ 200 ms 80 Back to MLP: A Simple Baseline for Human Motion Prediction dulucas/simlpe 1 Compare

Papers archive 2025-07-28

6 shown of 6 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 16. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction 0 1 6 Jun 2023 not harvested
Best Practices for 2-Body Pose Forecasting 1 2 12 Apr 2023 ran 3 of 17 samples (14 unverified)
Back to MLP: A Simple Baseline for Human Motion Prediction 1 3 4 Jul 2022 ran 3 of 7 samples (4 unverified)
Multi-Person 3D Motion Prediction with Multi-Range Transformers 1 2 23 Nov 2021 not harvested
Multi-Person Extreme Motion Prediction 1 2 18 May 2021 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
Learning Trajectory Dependencies for Human Motion Prediction 5 2 15 Aug 2019 ran 0 of 3 samples (3 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

  • Expi
  • Expi - common actions split
  • Expi - unseen actions split

3 variant names, 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