{"id":"W4402703726","doi":"10.1109/access.2024.3461739","title":"Key Factors Determining the Required Number of Training Images in Person Re-Identification","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Identification (biology); Key (lock); Training (meteorology); Artificial intelligence; Machine learning; Computer vision; Computer security","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":[0.003173746,0.00103045,0.0009770343,0.0007802793,0.0008116532,0.0013643,0.001977985,0.001071165,0.003106617],"category_scores_gemma":[0.02672369,0.0005026262,0.0004887049,0.00087796,0.0009199827,0.004311481,0.001336107,0.001988527,0.001770831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008448355,"about_ca_system_score_gemma":0.001041205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002873827,"about_ca_topic_score_gemma":0.00394566,"domain_scores_codex":[0.9965599,0.0008124857,0.0002911934,0.001015716,0.001112682,0.000208072],"domain_scores_gemma":[0.9867582,0.006552546,0.00102431,0.003618087,0.001814096,0.0002326966],"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":[0.0008197345,0.0004195624,0.01833334,0.0004824711,0.00008230358,0.0003301072,0.0004142411,0.08865289,0.05268451,0.01212283,0.006119218,0.8195388],"study_design_scores_gemma":[0.00004413943,0.0003131592,0.02052227,0.0001328338,0.00008816515,0.001261164,0.0004164664,0.8678257,0.08253381,0.01637763,0.01039074,0.00009393002],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1498491,0.002413176,0.8378155,0.001090286,0.0002425832,0.0002659295,0.0005395378,0.002163823,0.005620134],"genre_scores_gemma":[0.605652,0.001263031,0.3879012,0.0002165465,0.0001473539,0.000302384,0.0008854045,0.000424938,0.003207176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003173746,"threshold_uncertainty_score":0.01678461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1112864276106125,"score_gpt":0.3603405087921313,"score_spread":0.2490540811815188,"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."}}