New benchmark dataset released for cow face recognition

Researchers have introduced ReCowGnition, a new benchmark dataset designed for cow face recognition in realistic agricultural settings. The dataset comprises 6,838 images of 161 distinct cows, collected from a dairy farm. To facilitate research in this area, the project also defines six evaluation protocols for verification and identification, and provides benchmark results for six different models, including foundation models and those trained on limited data. AI

IMPACT This dataset could advance precision livestock farming by enabling more accurate and efficient animal identification and welfare monitoring.

RANK_REASON The cluster contains an academic paper describing a new benchmark dataset and evaluation protocols. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• cs.CV
• DagsHub
• Gotit.pub
• Hugging Face
• ReCowGnition
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →