{"id":"W3097582741","doi":"10.1002/ece3.6840","title":"Automated facial recognition for wildlife that lack unique markings: A deep learning approach for brown bears","year":2020,"lang":"en","type":"article","venue":"Ecology and Evolution","topic":"Face recognition and analysis","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"Raincoast Conservation Foundation; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Ursus; Deep learning; Classifier (UML); Landmark; Pattern recognition (psychology); Identification (biology); Facial recognition system; Support vector machine; Embedding; Computer vision; Machine learning; Ecology; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002753946,0.0001030669,0.0001738913,0.00008859424,0.0003276374,0.00005527144,0.0001163867,0.000161769,0.0000116262],"category_scores_gemma":[0.0002099515,0.0001075336,0.00008554372,0.000203036,0.0000456425,0.0002778458,0.00004671271,0.0001133368,0.00001514245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003467501,"about_ca_system_score_gemma":0.00003396781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005813344,"about_ca_topic_score_gemma":0.00001671063,"domain_scores_codex":[0.9991067,0.0001067588,0.0001518036,0.0003447676,0.00006163106,0.0002283146],"domain_scores_gemma":[0.9995437,0.000118226,0.0001032759,0.00005818497,0.00009046313,0.00008612721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002349216,0.00147367,0.1877064,0.002393062,0.001865122,0.00002010419,0.01757204,0.02944038,0.01080286,0.02254172,0.08078322,0.6430522],"study_design_scores_gemma":[0.000768953,0.0002360595,0.01343609,0.000006545064,0.00003964978,0.00000660458,0.0001697137,0.9805897,0.000101647,0.001777427,0.002714238,0.000153389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06278964,0.00004392753,0.9333861,0.002625763,0.00009929808,0.0004065862,0.00001117984,0.0004249972,0.0002125147],"genre_scores_gemma":[0.9410277,0.00003335926,0.05704144,0.001397214,0.00008566934,0.0001565173,0.000177485,0.000008234009,0.00007237706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9511493,"threshold_uncertainty_score":0.4385093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03680559932852202,"score_gpt":0.2509601660872971,"score_spread":0.2141545667587751,"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."}}