Salvato in:
Dettagli Bibliografici
Autori principali: Khaldi, Rohaifa, Alcaraz-Segura, Domingo, Sánchez-Herrera, Ignacio, Martinez-Lopez, Javier, Navarro, Carlos Javier, Tabik, Siham
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.00275
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912383280087040
author Khaldi, Rohaifa
Alcaraz-Segura, Domingo
Sánchez-Herrera, Ignacio
Martinez-Lopez, Javier
Navarro, Carlos Javier
Tabik, Siham
author_facet Khaldi, Rohaifa
Alcaraz-Segura, Domingo
Sánchez-Herrera, Ignacio
Martinez-Lopez, Javier
Navarro, Carlos Javier
Tabik, Siham
contents Social media images provide valuable insights for modeling, mapping, and understanding human interactions with natural and cultural heritage. However, categorizing these images into semantically meaningful groups remains highly complex due to the vast diversity and heterogeneity of their visual content as they contain an open-world human and nature elements. This challenge becomes greater when categories involve abstract concepts and lack consistent visual patterns. Related studies involve human supervision in the categorization process and the lack of public benchmark datasets make comparisons between these works unfeasible. On the other hand, the continuous advances in large models, including Large Language Models (LLMs), Large Visual Models (LVMs), and Large Visual Language Models (LVLMs), provide a large space of unexplored solutions. In this work 1) we introduce FLIPS a dataset of Flickr images that capture the interaction between human and nature, and 2) evaluate various solutions based on different types and combinations of large models using various adaptation methods. We assess and report their performance in terms of cost, productivity, scalability, and result quality to address the challenges of social media image categorization.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00275
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People
Khaldi, Rohaifa
Alcaraz-Segura, Domingo
Sánchez-Herrera, Ignacio
Martinez-Lopez, Javier
Navarro, Carlos Javier
Tabik, Siham
Computer Vision and Pattern Recognition
Artificial Intelligence
Social media images provide valuable insights for modeling, mapping, and understanding human interactions with natural and cultural heritage. However, categorizing these images into semantically meaningful groups remains highly complex due to the vast diversity and heterogeneity of their visual content as they contain an open-world human and nature elements. This challenge becomes greater when categories involve abstract concepts and lack consistent visual patterns. Related studies involve human supervision in the categorization process and the lack of public benchmark datasets make comparisons between these works unfeasible. On the other hand, the continuous advances in large models, including Large Language Models (LLMs), Large Visual Models (LVMs), and Large Visual Language Models (LVLMs), provide a large space of unexplored solutions. In this work 1) we introduce FLIPS a dataset of Flickr images that capture the interaction between human and nature, and 2) evaluate various solutions based on different types and combinations of large models using various adaptation methods. We assess and report their performance in terms of cost, productivity, scalability, and result quality to address the challenges of social media image categorization.
title Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.00275