Publikation: MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset [36]. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammalnet.github.io.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
CHEN, Jun, Ming HU, Darren J. COKER, Michael L. BERUMEN, Blair R. COSTELLOE, Sara BEERY, Anna ROHRBACH, Mohamed ELHOSEINY, 2023. MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada (und Online), 18. Juni 2023 - 22. Juni 2023. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : Vancouver, Canada, 18-22 June 2023 : proceedings. Piscataway, NJ: IEEE, 2023, pp. 13052-13061. ISBN 979-8-3503-0130-4. Available under: doi: 10.1109/cvpr52729.2023.01254BibTex
@inproceedings{Chen2023-06Mamma-69039, year={2023}, doi={10.1109/cvpr52729.2023.01254}, title={MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding}, isbn={979-8-3503-0130-4}, publisher={IEEE}, address={Piscataway, NJ}, booktitle={2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : Vancouver, Canada, 18-22 June 2023 : proceedings}, pages={13052--13061}, author={Chen, Jun and Hu, Ming and Coker, Darren J. and Berumen, Michael L. and Costelloe, Blair R. and Beery, Sara and Rohrbach, Anna and Elhoseiny, Mohamed} }
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/69039"> <dc:creator>Berumen, Michael L.</dc:creator> <dc:contributor>Costelloe, Blair R.</dc:contributor> <dc:creator>Rohrbach, Anna</dc:creator> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/69039"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-01-15T11:17:06Z</dcterms:available> <dc:contributor>Elhoseiny, Mohamed</dc:contributor> <dc:creator>Chen, Jun</dc:creator> <dc:contributor>Beery, Sara</dc:contributor> <dc:creator>Elhoseiny, Mohamed</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/> <dcterms:issued>2023-06</dcterms:issued> <dc:creator>Costelloe, Blair R.</dc:creator> <dcterms:abstract>Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset [36]. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammalnet.github.io.</dcterms:abstract> <dc:contributor>Berumen, Michael L.</dc:contributor> <dc:language>eng</dc:language> <dc:creator>Coker, Darren J.</dc:creator> <dc:contributor>Coker, Darren J.</dc:contributor> <dc:contributor>Chen, Jun</dc:contributor> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-01-15T11:17:06Z</dc:date> <dcterms:title>MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding</dcterms:title> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>Hu, Ming</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43615"/> <dc:creator>Hu, Ming</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:creator>Beery, Sara</dc:creator> <dc:contributor>Rohrbach, Anna</dc:contributor> </rdf:Description> </rdf:RDF>