{"id":"W2901771398","doi":"10.1111/2041-210x.13133","title":"Past, present and future approaches using computer vision for animal re‐identification from camera trap data","year":2018,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":226,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Camera trap; Deep learning; Computer science; Artificial intelligence; Population; Data science; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001230666,0.00008160116,0.0001209207,0.00003866895,0.0002459282,0.00001559595,0.0001164347,0.0001941096,0.00004800032],"category_scores_gemma":[0.00002601396,0.00007971157,0.00001054769,0.00009137321,0.0003193259,0.0003510579,0.0001892417,0.00008793992,0.000004246258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006840102,"about_ca_system_score_gemma":0.000008371811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001410924,"about_ca_topic_score_gemma":0.0004682699,"domain_scores_codex":[0.9987735,0.0004123581,0.0001936161,0.0004266591,0.00004257767,0.0001513487],"domain_scores_gemma":[0.9994291,0.0002337131,0.00009128802,0.0002087517,0.000008189908,0.00002896815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001814734,0.0000789167,0.9275523,0.000007730657,0.00001351182,4.739697e-7,0.0004209547,0.00007920847,0.003766005,0.0001517794,0.00240129,0.0653464],"study_design_scores_gemma":[0.0002248211,0.0001134106,0.7092418,0.000002272532,0.00001872769,0.000003478516,0.00009219738,0.2859514,0.0000498405,0.002492195,0.001749279,0.00006060166],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7955284,0.00007035708,0.2018576,0.00191031,0.0003438141,0.0002384515,0.0000110484,0.0000104869,0.00002954497],"genre_scores_gemma":[0.6392958,0.00001327023,0.3596551,0.0001364582,0.0007999163,0.00001937285,0.00005886531,0.000004944808,0.00001631837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2858722,"threshold_uncertainty_score":0.3250543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09820242396940591,"score_gpt":0.3602016114107164,"score_spread":0.2619991874413105,"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."}}