Datasets › l2d
l2d (Learning to Dance)
This dataset is composed of paired videos of people dancing 3 different music styles: Ballet, Michael Jackson and Salsa. It contains multimodal data (visual data, temporal-graphs and audio) careful-selected from publicly available videos of dancers performing representative movements of the music style and audio data from the respective styles.
This dataset was used to train and evaluate methodologies for motion generation from audio.
We split the samples into training and evaluation sets.
The training set has 2352 samples of movements sequences with length 64. Which 525 are from Ballet style, 966 from Michael Jackson (MJ) and 861 from Salsa.
The evaluation set has 471 samples. 134 from Ballet, 102 from MJ and 235 from Salsa.
Benchmarks archive 2025-07-28
No leaderboard in the archive resolves to this dataset.
Papers archive 2025-07-28
No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
No task tagged in the archive.
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
Variants archive 2025-07-28
- l2d
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