{"id":"W2158008709","doi":"10.1109/icpr.2006.224","title":"Adaptive Step Size Window Matching for Detection","year":2006,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Matching (statistics); Object detection; Window (computing); Set (abstract data type); Algorithm; Computational complexity theory; Point (geometry); Selection (genetic algorithm); Artificial intelligence; Pattern recognition (psychology); Mathematics","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":[0.0004604288,0.00007917095,0.00009899272,0.00003304378,0.0001193385,0.00009729691,0.0002237582,0.00003784868,0.000004791261],"category_scores_gemma":[0.00003494299,0.0000685445,0.00006311589,0.0001561857,0.00001020441,0.0003013734,0.00004118974,0.00005411579,0.00001322782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002275959,"about_ca_system_score_gemma":0.00001645588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002807169,"about_ca_topic_score_gemma":0.0002930727,"domain_scores_codex":[0.9992844,0.0000564861,0.0001272064,0.0002341967,0.0001096135,0.0001880734],"domain_scores_gemma":[0.9991696,0.0004905998,0.00004710134,0.0002128966,0.0000567406,0.00002300317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004063859,0.00007923397,0.001307553,0.00002006721,0.00002747755,0.000006846825,0.0001880963,0.001695008,0.02489447,0.1257554,0.0006103542,0.8453749],"study_design_scores_gemma":[0.002275718,0.0005580699,0.1691151,0.00003662585,0.00001588955,0.00005239441,0.0001215238,0.1759077,0.1889106,0.4497494,0.01233772,0.0009193334],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01206668,0.0000234401,0.9819245,0.0001741708,0.0003361598,0.0001471069,8.245394e-7,0.0002343817,0.005092736],"genre_scores_gemma":[0.5933359,4.037243e-7,0.4060233,0.00009913813,0.00009611921,0.00001298815,2.209171e-7,0.000004192717,0.0004277597],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8444555,"threshold_uncertainty_score":0.2795163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01766974875868356,"score_gpt":0.2653214840217811,"score_spread":0.2476517352630976,"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."}}