{"id":"W2945149548","doi":"10.1101/640037","title":"FoxMask: a new automated tool for animal detection in camera trap images","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Biodome; Université du Québec à Rimouski","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Kenneth M. Molson Foundation; Canada Research Chairs; ArcticNet; Parks Canada; Molson Foundation; Polar Knowledge Canada; Université du Québec à Rimouski","keywords":"Computer science; Camera trap; Artificial intelligence; Computer vision; Trap (plumbing); Segmentation; Lagopus; Background subtraction; Pattern recognition (psychology); Arctic; Pixel; Wildlife; Ecology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001110437,0.001087843,0.0008077483,0.002959346,0.0002673319,0.0009134867,0.001373457,0.0006274039,0.009085256],"category_scores_gemma":[0.00368684,0.0006613851,0.0008266895,0.0008836283,0.0003384616,0.001403433,0.001023731,0.0005202274,0.003275043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005431988,"about_ca_system_score_gemma":0.0006417102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002748572,"about_ca_topic_score_gemma":0.003312136,"domain_scores_codex":[0.9990399,0.00009744016,0.00008280087,0.0003136002,0.0003946876,0.00007158196],"domain_scores_gemma":[0.9982816,0.0006724366,0.0003193108,0.0001991304,0.0004019118,0.0001256906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001080877,0.0002068772,0.01325605,0.0009971677,0.0005399186,0.0005103748,0.0003966797,0.0124227,0.118321,0.001778584,0.08217691,0.7683128],"study_design_scores_gemma":[0.0002137864,0.0005051801,0.03283405,0.0001794314,0.0001698594,0.001594861,0.0001399242,0.6463236,0.2130717,0.003438694,0.1012387,0.0002902195],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05668706,0.001015728,0.6224738,0.0001696273,0.0001580734,0.0005445185,0.007155103,0.3091879,0.002608151],"genre_scores_gemma":[0.1389678,0.0002860094,0.8377261,0.0002314618,0.000101336,0.0008512863,0.01023106,0.006983513,0.004621445],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009085256,"threshold_uncertainty_score":0.03039324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024991341295458,"score_gpt":0.214912546937807,"score_spread":0.2046626335248524,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}