Skip to Main content Skip to Navigation
Conference papers

Qualitative descriptors and action perception

Abstract : This article presents the notion of qualitative descriptor, a theoretical tool which describes within the same formalism different approaches to transform quantitative data into qualitative data. This formalism is used with a grouping algorithm to extract qualitative phases from a data flow. Work on action perception, based on qualitative descriptors, is used to illustrate these ideas. The grouping algorithm generates a qualitative symbolic data flow from a video sequence. The ultimate aim is to provide an unsupervised learning algorithm working this qualitative flow to extract abstract description for common actions such as “take”, “push” and “pull”.
Document type :
Conference papers
Complete list of metadatas
Contributor : Lip6 Publications <>
Submitted on : Wednesday, August 9, 2017 - 3:12:42 PM
Last modification on : Friday, December 13, 2019 - 11:44:05 AM

Links full text



Jean-Christophe Baillie, Jean-Gabriel Ganascia. Qualitative descriptors and action perception. AI 2000 - 13th Biennial Conference of the Canadian Society for Computational Studies of Intelligence, May 2000, Montréal, Québec, Canada. pp.316-325, ⟨10.1007/3-540-45486-1_26⟩. ⟨hal-01573430⟩



Record views