{"id":"W2778775889","doi":"10.1109/iccv.2017.265","title":"Efficient Online Local Metric Adaptation via Negative Samples for Person Re-identification","year":2017,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"Army Research Office; National Science Foundation","keywords":"Metric (unit); Computer science; Matching (statistics); Adaptation (eye); Contrast (vision); Identification (biology); Set (abstract data type); Artificial intelligence; Margin (machine learning); Similarity (geometry); Cover (algebra); Machine learning; Mathematical optimization; Algorithm; Mathematics; Image (mathematics); Statistics","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":[0.0009745809,0.0001071116,0.0001466686,0.0001454586,0.0005174359,0.0003393435,0.0007035176,0.00005094257,0.000006823945],"category_scores_gemma":[0.0006952336,0.00009245004,0.00008278548,0.0002022309,0.0000664389,0.000265977,0.00006695612,0.00006430003,0.00001418179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005404679,"about_ca_system_score_gemma":0.00004242838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003527334,"about_ca_topic_score_gemma":0.000353666,"domain_scores_codex":[0.998884,0.00008761803,0.0001996384,0.0003970493,0.0002330747,0.0001986388],"domain_scores_gemma":[0.99829,0.0004759024,0.000253738,0.0007286264,0.0001976624,0.00005407129],"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":[0.00001852253,0.0001239403,0.0005459026,0.0000205578,0.00002539399,0.000001251881,0.001281168,0.01502779,0.0008588538,0.01084744,0.0001832819,0.9710659],"study_design_scores_gemma":[0.0003442142,0.00006529981,0.08090744,0.000008988533,0.000007517859,0.000001564377,0.0003271389,0.910842,0.004899037,0.002223377,0.0002413714,0.0001320646],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01610441,0.00004183121,0.9815636,0.001064045,0.0005113524,0.0002685004,0.000009586665,0.0001068326,0.0003298427],"genre_scores_gemma":[0.6622266,0.000002746696,0.3374552,0.00005835214,0.00005946144,0.00001679964,0.000008804393,0.000005266772,0.000166726],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9709339,"threshold_uncertainty_score":0.3979751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1233692533169497,"score_gpt":0.3578340000265187,"score_spread":0.234464746709569,"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."}}