Work

LifeCLEF Bird Identification Task 2014

Year: 2014

Type: conference-paper

Abstract: The LifeCLEF bird identification task provides a testbed for a system-oriented evaluation of 501 bird species identification. The main originality of this data is that it was specifically built through a citizen science initiative conducted by Xeno-Canto, an international social net-work of amateur and expert ornithologists. This makes the task closer to the conditions of a real-world application than previous, similar ini-tiatives. This overview presents the resources and the assessments of the task, summarizes the retrieval approaches employed by the participating groups, and provides an analysis of the main evaluation results. With a total of ten groups from seven countries and with a total of twenty-nine runs submitted, involving distinct and original methods, this first year task confirms the interest of the audio retrieval community for biodiver-sity and ornithology, and highlights further challenging studies in bird identification.

Source: HAL

Authors: Goëau, Hervé, Glotin, Hervé, Vellinga, Willem-Pier, Planqué, Robert, Rauber, Andreas, Joly, Alexis

Institutions: Laboratoire d'Informatique, de Robotique et de Microélectronique de Montpellier, Centre Inria de Saclay, Institut Universitaire de France, Vrije Universiteit Amsterdam, TU Wien

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Life on land

Open Access status: green

OpenAlex ID: W2293488548

FWCI: 5.06

Cites: 28

Cited by: 47

Related to: 10