Papers › BABEL: Bodies, Action and Behavior with English Labels

BABEL: Bodies, Action and Behavior with English Labels

17 Jun 2021CVPR 2021 1arXiv:2106.09696archive 2025-07-28

Abhinanda R. Punnakkal, Arjun Chandrasekaran, Nikos Athanasiou, Alejandra Quiros-Ramirez, Michael J. Black

Understanding the semantics of human movement -- the what, how and why of the movement -- is an important problem that requires datasets of human actions with semantic labels. Existing datasets take one of two approaches. Large-scale video datasets contain many action labels but do not contain ground-truth 3D human motion. Alternatively, motion-capture (mocap) datasets have precise body motions but are limited to a small number of actions. To address this, we present BABEL, a large dataset with language labels describing the actions being performed in mocap sequences. BABEL consists of action labels for about 43 hours of mocap sequences from AMASS. Action labels are at two levels of abstraction -- sequence labels describe the overall action in the sequence, and frame labels describe all actions in every frame of the sequence. Each frame label is precisely aligned with the duration of the corresponding action in the mocap sequence, and multiple actions can overlap. There are over 28k sequence labels, and 63k frame labels in BABEL, which belong to over 250 unique action categories. Labels from BABEL can be leveraged for tasks like action recognition, temporal action localization, motion synthesis, etc. To demonstrate the value of BABEL as a benchmark, we evaluate the performance of models on 3D action recognition. We demonstrate that BABEL poses interesting learning challenges that are applicable to real-world scenarios, and can serve as a useful benchmark of progress in 3D action recognition. The dataset, baseline method, and evaluation code is made available, and supported for academic research purposes at https://babel.is.tue.mpg.de/.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

abhinanda-punnakkal/BABEL officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Action RecognitionAction ClassificationAction LocalizationAction RecognitionMotion SynthesisTemporal Action Localization

Datasets

Introduced by this paper, per the archive.

BABEL

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification BABEL 2s-AGCN CE Top-1 44.87 #1 of 1 Archive leaderboard report
Action Classification BABEL 2s-AGCN CE Top-1-norm 17.16 #1 of 1 Archive leaderboard report
Action Classification BABEL 2s-AGCN CE Top-5 71.78 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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