English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Camera traps are valuable tools in animal ecology for biodiversity monitoringand conservation. However, challenges like poor generalization to deployment atnew unseen locations limit their practical application. Images are naturallyassociated with heterogeneous forms of context possibly in differentmodalities. In this work, we leverage the structured context associated withthe camera trap images to improve out-of-distribution generalization for thetask of species identification in camera traps. For example, a photo of a wildanimal may be associated with information about where and when it was taken, aswell as structured biology knowledge about the animal species. While typicallyoverlooked by existing work, bringing back such context offers severalpotential benefits for better image understanding, such as addressing datascarcity and enhancing generalization. However, effectively integrating suchheterogeneous context into the visual domain is a challenging problem. Toaddress this, we propose a novel framework that reformulates speciesclassification as link prediction in a multimodal knowledge graph (KG). Thisframework seamlessly integrates various forms of multimodal context for visualrecognition. We apply this framework for out-of-distribution speciesclassification on the iWildCam2020-WILDS and Snapshot Mountain Zebra datasetsand achieve competitive performance with state-of-the-art approaches.Furthermore, our framework successfully incorporates biological taxonomy forimproved generalization and enhances sample efficiency for recognizingunder-represented species.

Bringing Back the Context: Camera Trap Species Identification as Link Prediction on Multimodal Knowledge Graphs