Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10609/150905
Título : | Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents |
Autoría: | Weber, Ethan Lapedriza, Agata Papadopoulos, Dim P. Ofli, Ferda Imran, Muhammad Torralba, Antonio |
Citación : | Weber, E. [Ethan], Papadopoulos, D. P. [Dim], Lapedriza, A.[Agata], Ofli, F. [Ferda], Imran, M. [Muhammad], Torralba, A. [Antonio] (2022). Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents. IEEE transactions on pattern analysis and machine intelligence, 45(4), 4768-4781. |
Resumen : | Natural disasters, such as floods, tornadoes, or wildfires, are increasingly pervasive as the Earth undergoes global warming. It is difficult to predict when and where an incident will occur, so timely emergency response is critical to saving the lives of those endangered by destructive events. Fortunately, technology can play a role in these situations. Social media posts can be used as a low-latency data source to understand the progression and aftermath of a disaster, yet parsing this data is tedious without automated methods. Prior work has mostly focused on text-based filtering, yet image and video-based filtering remains largely unexplored. In this work, we present the Incidents1M Dataset, a large-scale multi-label dataset which contains 977,088 images, with 43 incident and 49 place categories. We provide details of the dataset construction, statistics and potential biases; introduce and train a model for incident detection; and perform image-filtering experiments on millions of images on Flickr and Twitter. We also present some applications on incident analysis to encourage and enable future work in computer vision for humanitarian aid. Code, data, and models are available at http://incidentsdataset.csail.mit.edu. |
Palabras clave : | Visual recognition Scene understanding Image dataset Social media Disaster analysis Incident detection |
DOI: | https://doi.org/10.1109/TPAMI.2022.3191996 |
Tipo de documento: | info:eu-repo/semantics/article |
Versión del documento: | info:eu-repo/semantics/preprint |
Fecha de publicación : | 11-ene-2022 |
Licencia de publicación: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Aparece en las colecciones: | Articles cientÍfics Articles |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
2201.04236v1.pdf | 28,22 MB | Adobe PDF | Visualizar/Abrir |
Comparte:
Los ítems del Repositorio están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.