Crossmark

WildCLIP: Scene and Animal Attribute Retrieval from Camera Trap Data with Domain-Adapted Vision-Language Models

Crossref DOI link: https://doi.org/10.1007/s11263-024-02026-6

Published Online: 2024-04-24

Published Print: 2024-09

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Gabeff, Valentin https://orcid.org/0000-0003-3352-1825
Rußwurm, Marc https://orcid.org/0000-0001-6612-5744
Tuia, Devis https://orcid.org/0000-0003-0374-2459
Mathis, Alexander https://orcid.org/0000-0002-3777-2202
Funding

Funding for this research was provided by:

EPFL Lausanne
License Information

Text and Data Mining valid from 2024-04-24

Version of Record valid from 2024-04-24
More Information

Article History

Received: 15 September 2023

Accepted: 29 January 2024

First Online: 24 April 2024