BABEL: Bodies, Action and Behavior with English Labels

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

PUNNAKKAL, Abhinanda R., Arjun CHANDRASEKARAN, Nikos ATHANASIOU, María Alejandra QUIRÓS RAMÍREZ, Michael J. BLACK, 2021. BABEL: Bodies, Action and Behavior with English Labels. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA, Jun 20, 2021 - Jun 25, 2021. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, pp. 722-731. ISBN 978-1-66544-509-2. Available under: doi: 10.1109/CVPR46437.2021.00078

@inproceedings{Punnakkal2021BABEL-56520, title={BABEL: Bodies, Action and Behavior with English Labels}, year={2021}, doi={10.1109/CVPR46437.2021.00078}, isbn={978-1-66544-509-2}, address={Piscataway, NJ}, publisher={IEEE}, booktitle={Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={722--731}, author={Punnakkal, Abhinanda R. and Chandrasekaran, Arjun and Athanasiou, Nikos and Quirós Ramírez, María Alejandra and Black, Michael J.} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dc:language>eng</dc:language> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:abstract xml:lang="eng">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 language labels for over 43 hours of mocap sequences from AMASS, containing over 250 unique actions. Each action label in BABEL is precisely aligned with the duration of the corresponding action in the mocap sequence. BABELalso allows overlap of multiple actions, that may each span different durations. This results in a total of over 66000 action segments. The dense annotations can be leveraged for tasks like action recognition, temporal 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 for progress in 3D action recognition. The dataset, baseline methods, and evaluation code are available and supported for academic research purposes at</dcterms:abstract> <dc:creator>Athanasiou, Nikos</dc:creator> <dcterms:isPartOf rdf:resource=""/> <dc:contributor>Black, Michael J.</dc:contributor> <dcterms:title>BABEL: Bodies, Action and Behavior with English Labels</dcterms:title> <dc:creator>Chandrasekaran, Arjun</dc:creator> <dc:contributor>Punnakkal, Abhinanda R.</dc:contributor> <bibo:uri rdf:resource=""/> <dc:contributor>Quirós Ramírez, María Alejandra</dc:contributor> <dc:contributor>Athanasiou, Nikos</dc:contributor> <dc:creator>Punnakkal, Abhinanda R.</dc:creator> <dc:contributor>Chandrasekaran, Arjun</dc:contributor> <dspace:isPartOfCollection rdf:resource=""/> <dc:date rdf:datatype="">2022-02-10T13:33:17Z</dc:date> <dc:creator>Quirós Ramírez, María Alejandra</dc:creator> <dc:creator>Black, Michael J.</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:available rdf:datatype="">2022-02-10T13:33:17Z</dcterms:available> <dcterms:issued>2021</dcterms:issued> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


My Account