Automatic Modeling of Social Concepts Evoked by Art Images as Multimodal Frames

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pandiani, Delfina Sol Martinez, Presutti, Valentina
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917414424281088
author Pandiani, Delfina Sol Martinez
Presutti, Valentina
author_facet Pandiani, Delfina Sol Martinez
Presutti, Valentina
contents Social concepts referring to non-physical objects--such as revolution, violence, or friendship--are powerful tools to describe, index, and query the content of visual data, including ever-growing collections of art images from the Cultural Heritage (CH) field. While much progress has been made towards complete image understanding in computer vision, automatic detection of social concepts evoked by images is still a challenge. This is partly due to the well-known semantic gap problem, worsened for social concepts given their lack of unique physical features, and reliance on more unspecific features than concrete concepts. In this paper, we propose the translation of recent cognitive theories about social concept representation into a software approach to represent them as multimodal frames, by integrating multisensory data. Our method focuses on the extraction, analysis, and integration of multimodal features from visual art material tagged with the concepts of interest. We define a conceptual model and present a novel ontology for formally representing social concepts as multimodal frames. Taking the Tate Gallery's collection as an empirical basis, we experiment our method on a corpus of art images to provide a proof of concept of its potential. We discuss further directions of research, and provide all software, data sources, and results.
format Preprint
id arxiv_https___arxiv_org_abs_2110_07420
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Automatic Modeling of Social Concepts Evoked by Art Images as Multimodal Frames
Pandiani, Delfina Sol Martinez
Presutti, Valentina
Computer Vision and Pattern Recognition
Computation and Language
Digital Libraries
Social and Information Networks
Social concepts referring to non-physical objects--such as revolution, violence, or friendship--are powerful tools to describe, index, and query the content of visual data, including ever-growing collections of art images from the Cultural Heritage (CH) field. While much progress has been made towards complete image understanding in computer vision, automatic detection of social concepts evoked by images is still a challenge. This is partly due to the well-known semantic gap problem, worsened for social concepts given their lack of unique physical features, and reliance on more unspecific features than concrete concepts. In this paper, we propose the translation of recent cognitive theories about social concept representation into a software approach to represent them as multimodal frames, by integrating multisensory data. Our method focuses on the extraction, analysis, and integration of multimodal features from visual art material tagged with the concepts of interest. We define a conceptual model and present a novel ontology for formally representing social concepts as multimodal frames. Taking the Tate Gallery's collection as an empirical basis, we experiment our method on a corpus of art images to provide a proof of concept of its potential. We discuss further directions of research, and provide all software, data sources, and results.
title Automatic Modeling of Social Concepts Evoked by Art Images as Multimodal Frames
topic Computer Vision and Pattern Recognition
Computation and Language
Digital Libraries
Social and Information Networks
url https://arxiv.org/abs/2110.07420