{"id":"W2949793910","doi":"10.48550/arxiv.1811.07749","title":"Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Deep learning; Camera trap; Artificial intelligence; Computer science; Data science; Population; Animal behavior; Citizen science; Identification (biology); Frame (networking); Machine learning; Ecology; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006830903,0.001312846,0.0009839901,0.003126257,0.0006170157,0.00314891,0.0024748,0.00243025,0.002179945],"category_scores_gemma":[0.01073867,0.0007499726,0.001128626,0.003476828,0.002505969,0.006026709,0.00189477,0.004026335,0.001536649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932531,"about_ca_system_score_gemma":0.001744628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004135661,"about_ca_topic_score_gemma":0.005081546,"domain_scores_codex":[0.9979199,0.0006707992,0.00011458,0.0006766273,0.000503608,0.0001146484],"domain_scores_gemma":[0.9917128,0.004105193,0.0004811154,0.001040298,0.002323583,0.0003369382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006981126,0.0001005794,0.005675109,0.001737866,0.0001618917,0.0001140635,0.0004681757,0.009766176,0.0028313,0.03670668,0.01292238,0.929446],"study_design_scores_gemma":[0.00003117542,0.0002992368,0.01712074,0.003717572,0.0002565263,0.001825785,0.001732956,0.1996683,0.01606293,0.2744412,0.4844047,0.0004388746],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.007713565,0.1681854,0.800428,0.01008606,0.001247272,0.000156579,0.0003264534,0.0007581324,0.01109852],"genre_scores_gemma":[0.07768548,0.157169,0.7512046,0.003631316,0.001882002,0.0002844824,0.000839306,0.000337987,0.006965956],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.006830903,"threshold_uncertainty_score":0.03612566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2520900230546423,"score_gpt":0.2411283814642594,"score_spread":0.0109616415903829,"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."}}