To: | Bioacoustics-L <>, <> |
---|---|
Subject: | [imageclef] LifeCLEF 2014 Bird Identification Task - Training Data Release |
From: | Herve Glotin <> |
Date: | Wed, 12 Feb 2014 21:27:25 +0100 |
LifeCLEF 2014 Bird
Identification Task - Training Data Release
http://www.imageclef.org/2014/lifeclef/bird The task will be focused on bird identification based on different types of audio records over 500 species from South America centered on Brazil (14027 audio records, 9688 in the training package, 4339 in the test package). This challenge is the biggest ever organized, after the pionner ICML 2013 and NIPS 2013 bird challenges that dealt 'only' with less than one hundred of species but interested many teams (online proc.: http://sabiod.org). The main originality of this data is that it was specifically
built through a citizen sciences initiative conducted by
Xeno-canto, an international social network of amateur and expert
ornithologists. This makes the task closer to the conditions of a
real-world application: (i) audio records of the same species are
coming from distinct birds living in distinct areas (ii) audio
records by different users that might not used the same
combination of microphones and portable recorders (iii) audio
records are taken at different periods in the year and different
hours of a day involving different background noise (other bird
species, insect chirping, etc).
The following sample illustrates the quality of
the audio records: Additional information includes contextual meta-data (author, date, locality name, comment, quality rates). The link of the
training data (18 Go in 1 tar.gz file + readme.pdf) is
available since few days in the registration system to any
user who subscribes to the bird task. A set of audio
features for both training and test recordings are also provided
in the registration system that could be used by any participant
(18 Go in 1 tar.gz file for the training data).
The participants will have
a chance to submit a paper describing their system, which will
be published in the CLEF Labs Working Notes. Furthermore, the
groups of the best performing systems will be invited to give
an oral presentation at CLEF 2014 and others will be given the
option of presenting a poster. For more information, please visit: Schedule: 01.12.2013: Registration opens (register here) 10.02.2014: training data release 15.04.2014: test data release 01.05.2014 deadline for submission of runs 15.05.2014: release of results 15.06.2014: deadline for submission of working notes 15-18.09.2014: CLEF 2014 Conference (Sheffield, UK) Organizers: - Hervé Glotin, University of Toulon, France, m("univ-tln.fr","//glotin");" target="_blank"> - Hervé Goëau, Inria Zenith team, France, m("inria.fr","herve.goeau");" target="_blank"> - Andreas Rauber, TU Wien, Austria, m("ifs.tuwien.ac.at","//rauber");" target="_blank"> - Willem-Pier Vellinga, Xeno-Canto foundation for nature sounds, The Netherlands, m("xeno-canto.org","//wp");" target="_blank"> -- Herve' Glotin, Pr. Institut Univ. de France (IUF) & Univ. Toulon (UTLN) Head of information DYNamics & Integration (DYNI @ UMR CNRS LSIS) http://glotin.univ-tln.fr m("univ-tln.fr","glotin");"> |
<Prev in Thread] | Current Thread | [Next in Thread> |
---|---|---|
|
Previous by Date: | Recordings of 'signature whistles'?, Aguasonic Acoustics |
---|---|
Next by Date: | [CFP] uLearnBio-ICML 2014: Workshop on Unsupervised Learning from Bioacoustic Big Data, Herve Glotin |
Previous by Thread: | Recordings of 'signature whistles'?, Aguasonic Acoustics |
Next by Thread: | [CFP] uLearnBio-ICML 2014: Workshop on Unsupervised Learning from Bioacoustic Big Data, Herve Glotin |
Indexes: | [Date] [Thread] [Top] [All Lists] |
The University of NSW School of Computer and Engineering takes no responsibility for the contents of this archive. It is purely a compilation of material sent by many people to the Bioacoustics-L mailing list. It has not been checked for accuracy nor its content verified in any way. If you wish to get material removed from the archive or have other queries about the archive e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU