Skip to Main content Skip to Navigation
Conference papers

Similarity and Contrast on Conceptual Spaces for Pertinent Description Generation

Giovanni Sileno 1, 2 Isabelle Bloch 1, 2 Jamal Atif Jean-Louis Dessalles 3, 4 
1 IMAGES - Image, Modélisation, Analyse, GEométrie, Synthèse
LTCI - Laboratoire Traitement et Communication de l'Information
3 DIG - Data, Intelligence and Graphs
LTCI - Laboratoire Traitement et Communication de l'Information
Abstract : Within the general objective of conceiving a cognitive architecture for image interpretation able to generate outputs relevant to several target user profiles, the paper elaborates on a set of operations that should be provided by a cognitive space to guarantee the generation of relevant descriptions. First, it attempts to define a working definition of contrast operation. Then, revisiting well-known results in cognitive studies, it sketches a definition of similarity based on contrast, distin- guished from the metric defined on the conceptual space.
Complete list of metadata

https://hal.telecom-paris.fr/hal-02288501
Contributor : TelecomParis HAL Connect in order to contact the contributor
Submitted on : Saturday, September 14, 2019 - 6:53:39 PM
Last modification on : Wednesday, November 3, 2021 - 6:18:17 AM

Identifiers

  • HAL Id : hal-02288501, version 1

Citation

Giovanni Sileno, Isabelle Bloch, Jamal Atif, Jean-Louis Dessalles. Similarity and Contrast on Conceptual Spaces for Pertinent Description Generation. 40th German Conference on Artificial Intelligence, 2017, Dortmund, Germany. pp.262-275. ⟨hal-02288501⟩

Share

Metrics

Record views

26