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

Understanding which features humans rely on -- in visually recognizing actionsimilarity is a crucial step towards a clearer picture of human actionperception from a learning and developmental perspective. In the present work,we investigate to which extent a computational model based on kinematics candetermine action similarity and how its performance relates to human similarityjudgments of the same actions. To this aim, twelve participants perform anaction similarity task, and their performances are compared to that of acomputational model solving the same task. The chosen model has its roots indevelopmental robotics and performs action classification based on learnedkinematic primitives. The comparative experiment results show that both themodel and human participants can reliably identify whether two actions are thesame or not. However, the model produces more false hits and has a greaterselection bias than human participants. A possible reason for this is theparticular sensitivity of the model towards kinematic primitives of thepresented actions. In a second experiment, human participants' performance onan action identification task indicated that they relied solely on kinematicinformation rather than on action semantics. The results show that both themodel and human performance are highly accurate in an action similarity taskbased on kinematic-level features, which can provide an essential basis forclassifying human actions.

Action similarity judgment based on kinematic primitives