{"id":"W1939016344","doi":"10.1007/978-3-540-30503-3_56","title":"Practical Region-Based Matching for Stereo Vision","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer vision; Computer science; Artificial intelligence; Stereopsis; Computer stereo vision; Matching (statistics); Observer (physics); Machine vision; Stereo cameras; Object (grammar); Field (mathematics); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002123475,0.0002805203,0.0002587418,0.0003160079,0.0001105716,0.0001870056,0.0002829915,0.0002537863,0.000009552949],"category_scores_gemma":[0.00004663381,0.000265935,0.00008141603,0.000138878,0.0001491958,0.0001417901,0.00004741114,0.0003652063,0.000007870781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003072764,"about_ca_system_score_gemma":0.0002075482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005184315,"about_ca_topic_score_gemma":0.0000168895,"domain_scores_codex":[0.9985649,0.000007184958,0.0002843728,0.0004722952,0.0003554897,0.0003157825],"domain_scores_gemma":[0.9989855,0.0003805752,0.00006951266,0.0003771216,0.0001029769,0.00008428328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005950057,0.000007648501,0.000002823283,0.00009295539,0.00000351718,0.00002287095,0.00006036527,0.9591483,0.00006814065,0.006375875,0.00002752889,0.03418402],"study_design_scores_gemma":[0.0002600137,0.00009236104,0.000007376887,0.0004722858,0.000008883351,0.00001234659,7.280396e-8,0.946571,0.0007669536,0.05094312,0.0005543596,0.0003112296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004645339,0.00005458473,0.9973133,0.0005760007,0.0009695255,0.0003408031,0.000003400675,0.0001407824,0.0005551563],"genre_scores_gemma":[0.418688,0.00001697379,0.5798036,0.0008508544,0.0004664112,0.000007186923,0.00002805976,0.00009054951,0.00004827029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4186416,"threshold_uncertainty_score":0.9999793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02249870785845733,"score_gpt":0.2668960848775105,"score_spread":0.2443973770190532,"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."}}