Edinburgh Research Explorer

Are multimedia identification tools biodiversity-friendly?

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • Alexis Joly
  • Hervé Goëau
  • Pierre Bonnet
  • Concetto Spampinato
  • Hervé Glotin
  • Andreas Rauber
  • Willem-Pier Vellinga
  • Bob Fisher
  • Henning Müller

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://dl.acm.org/citation.cfm?id=2661826
Original languageEnglish
Title of host publicationProceedings of the 3rd ACM International Workshop on Multimedia Analysis for Ecological Data (MAED 2014)
Place of PublicationNew York, NY, USA
PublisherACM
Pages31-36
Number of pages6
ISBN (Print)978-1-4503-3123-4
DOIs
Publication statusPublished - 2014

Abstract

This paper discusses the results of the LifeCLEF 2014 multimedia identification challenges with regards to the requirements of real-world ecological surveillance systems. In particular, we study the identification performances of the evaluated systems as a function of the ordinariness or rarity of the species in the dataset. This allows us to assess the ability of the underlying methods to be robust to heavily tailed distributions such as the ones encountered in real-world collections of life observations. Results show that all methods are more or less affected by the long-tail curse but that the best methods making use of classifiers with good discrimination capacities do resist the phenomenon pretty well.

    Research areas

  • audio, bird, fish, identification, image, life, multimedia, plant, species, video

Download statistics

No data available

ID: 17858032