Datasets › AIST++

AIST++

archive 2025-07-28

AIST++ is a 3D dance dataset which contains 3D motion reconstructed from real dancers paired with music. The AIST++ Dance Motion Dataset is constructed from the AIST Dance Video DB. With multi-view videos, an elaborate pipeline is designed to estimate the camera parameters, 3D human keypoints and 3D human dance motion sequences:

  • It provides 3D human keypoint annotations and camera parameters for 10.1M images, covering 30 different subjects in 9 views. These attributes makes it the largest and richest existing dataset with 3D human keypoint annotations.
  • It also contains 1,408 sequences of 3D human dance motion, represented as joint rotations along with root trajectories. The dance motions are equally distributed among 10 dance genres with hundreds of choreographies. Motion durations vary from 7.4 sec. to 48.0 sec. All the dance motions have corresponding music.

Benchmarks archive 2025-07-28

All 2 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.

Papers archive 2025-07-28

14 shown of 14 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 21. 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
Motion Anything: Any to Motion Generation 1 1 10 Mar 2025 not harvested
Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives 1 1 15 Mar 2024 ran 10 of 17 samples (7 unverified; 17 pointer-only for licence)
Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture 1 1 1 Sep 2023 not harvested
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration 1 2 5 Apr 2023 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis 0 1 8 Dec 2022 not harvested
UDE: A Unified Driving Engine for Human Motion Generation 1 1 29 Nov 2022 not harvested
Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos 1 2 29 Nov 2022 not harvested
EDGE: Editable Dance Generation From Music 1 2 19 Nov 2022 ran 7 of 11 samples (4 unverified)
Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory 1 1 24 Mar 2022 ran 4 of 5 samples (1 unverified; 5 pointer-only for licence)
HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions 0 1 17 Mar 2022 not harvested
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation 1 1 16 Mar 2022 ran 1 of 8 samples (7 unverified)
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++ 1 1 21 Jan 2021 not harvested
Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning 0 1 11 Jun 2020 not harvested
Music2Dance: DanceNet for Music-driven Dance Generation 0 1 2 Feb 2020 not harvested

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

  • AIST++

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