English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The availability of large-scale video action understanding datasets hasfacilitated advances in the interpretation of visual scenes containing people.However, learning to recognise human actions and their social interactions inan unconstrained real-world environment comprising numerous people, withpotentially highly unbalanced and long-tailed distributed action labels from astream of sensory data captured from a mobile robot platform remains asignificant challenge, not least owing to the lack of a reflective large-scaledataset. In this paper, we introduce JRDB-Act, as an extension of the existingJRDB, which is captured by a social mobile manipulator and reflects a realdistribution of human daily-life actions in a university campus environment.JRDB-Act has been densely annotated with atomic actions, comprises over 2.8Maction labels, constituting a large-scale spatio-temporal action detectiondataset. Each human bounding box is labeled with one pose-based action labeland multiple~(optional) interaction-based action labels. Moreover JRDB-Actprovides social group annotation, conducive to the task of grouping individualsbased on their interactions in the scene to infer their socialactivities~(common activities in each social group). Each annotated label inJRDB-Act is tagged with the annotators' confidence level which contributes tothe development of reliable evaluation strategies. In order to demonstrate howone can effectively utilise such annotations, we develop an end-to-endtrainable pipeline to learn and infer these tasks, i.e. individual action andsocial group detection. The data and the evaluation code is publicly availableat https://jrdb.erc.monash.edu/.

JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection