Viktor Domazetoski
@viktordo.bsky.social
PhD student at University of Exeter & University of Queensland. Interested in researching AI and its responsible application to Ecology, Environmental Monitoring and Nature Conservation.
Reposted by Viktor Domazetoski
Tired of digitizing biodiversity data by hand? Consider using large language models to, for example, extract plant functional traits from unstructured texts: See bsapubs.onlinelibrary.wiley.com/doi/full/10.... led by @viktordo.bsky.social @uni-goettingen.de, @exeter.ac.uk, @ribesresearch.bsky.social
Using large language models to extract plant functional traits from unstructured text
Premise Functional plant ecology seeks to understand how functional traits govern species distributions, community assembly, and ecosystem functions. While global trait datasets have advanced the fi...
bsapubs.onlinelibrary.wiley.com
June 6, 2025 at 3:52 PM
Tired of digitizing biodiversity data by hand? Consider using large language models to, for example, extract plant functional traits from unstructured texts: See bsapubs.onlinelibrary.wiley.com/doi/full/10.... led by @viktordo.bsky.social @uni-goettingen.de, @exeter.ac.uk, @ribesresearch.bsky.social
Reposted by Viktor Domazetoski
New dataset & pre-print:
The Coralscapes dataset for semantic scene understanding in coral reefs! 🤿🎥🐟🐠🐡
Coralscapes is the first dataset consistently annotated for general-purpose semantic segmentation in reefs, spanning 174k segmentation masks of 39 benthic classes on 2074 images!
The Coralscapes dataset for semantic scene understanding in coral reefs! 🤿🎥🐟🐠🐡
Coralscapes is the first dataset consistently annotated for general-purpose semantic segmentation in reefs, spanning 174k segmentation masks of 39 benthic classes on 2074 images!
March 28, 2025 at 3:25 AM
New dataset & pre-print:
The Coralscapes dataset for semantic scene understanding in coral reefs! 🤿🎥🐟🐠🐡
Coralscapes is the first dataset consistently annotated for general-purpose semantic segmentation in reefs, spanning 174k segmentation masks of 39 benthic classes on 2074 images!
The Coralscapes dataset for semantic scene understanding in coral reefs! 🤿🎥🐟🐠🐡
Coralscapes is the first dataset consistently annotated for general-purpose semantic segmentation in reefs, spanning 174k segmentation masks of 39 benthic classes on 2074 images!