Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
John Kosinski's 2026 analysis documents the frame-by-frame AI detection results for video VID00002 recorded on 2013-07 29. The dataset includes 111 full frames, 111 cropped frames, annotated images, JSON outputs, and a structured table of outcomes. It evaluates the performance of the MegaDetector and SpeciesNet classifiers on a specific subject.
Dataset is 53.0 MB and contains multiple file formats (JPG, PDF, JSON, PNG). License is CC-BY-4.0. No column names or sample data are provided for the structured table.