The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The study presents a deep‑learning object detection framework that identifies products derived from threatened species—elephant, pangolin, and tiger—using real‑world images from online marketplaces, enforcement seizures, and market inspections. Trained on 39,941 images, the best model achieved 84.2% overall accuracy, with 93.6% for pangolin, 90.3% for tiger, and 71.1% for elephant. The optimized model was deployed in a prototype smartphone app, which reached 91.3% accuracy and an F‑score of 0.86 on an independent test set, demonstrating its potential for real‑time monitoring of wildlife trade.
arXiv:2606. 09353v1 Announce Type: cross Abstract: Individual animal recognition can be useful in the search for lost or stolen pets, the tracking of individuals of endangered species, and the recognition of animals in crowded farms.
arXiv:2607. 26743v1 Announce Type: cross Abstract: Artificial intelligence has shown considerable potential for archaeological applications, yet its use in zooarchaeology remains limited, particularly for the identification of avian skeletal remains.
arXiv:2606. 07558v1 Announce Type: cross Abstract: Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at scale.
The advent of foundation models have enabled a new era in zero-shot classification. Yet, key challenges persist. Despite their impressive generalization power that leverages the immense pre-training k...
arXiv:2608.31107v1 Announce Type: new Abstract: The advent of foundation models have enabled a new era in zero-shot classification. Yet, key challenges persist. Despite their impressive generalizatio...