{"id":"W2174855376","doi":"10.1109/tpami.2002.1023808","title":"Detecting binocular half-occlusions: empirical comparisons of five approaches","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Matching (statistics); Binocular disparity; Binocular vision; Image (mathematics); Pattern recognition (psychology); 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":[0.0001881438,0.0002063481,0.000387291,0.0005622158,0.0002873435,0.00007503128,0.000448934,0.00005236823,0.000152318],"category_scores_gemma":[0.00001148549,0.00017581,0.0002872599,0.001396774,0.00009676778,0.0002676094,0.00001591323,0.0003087119,0.00002229271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000228129,"about_ca_system_score_gemma":0.000006721723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003282044,"about_ca_topic_score_gemma":0.0002227012,"domain_scores_codex":[0.9983953,0.0001030464,0.0004557427,0.0005204644,0.0002899786,0.0002354791],"domain_scores_gemma":[0.9989165,0.0002080912,0.0001494049,0.0005291846,0.00006315923,0.0001336549],"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":[0.000003624657,0.0002590842,0.0009883498,0.00001307904,0.0002356862,0.000006395109,0.0009284677,0.04466222,0.0002337093,0.00003197729,0.00001202177,0.9526254],"study_design_scores_gemma":[0.000079474,0.00006754203,0.0003396668,0.00002453812,0.0001635446,0.00001157467,0.0001687919,0.9428823,0.05589014,0.00008845407,0.00009915327,0.0001848445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0026137,0.0003425664,0.9959724,0.0006797448,0.00008694187,0.0000928952,0.000009083959,0.00007305926,0.0001296432],"genre_scores_gemma":[0.9765193,0.0002569437,0.02279143,0.0002806878,0.000008446652,0.000009348441,0.000001014918,0.000008763079,0.0001240873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9739056,"threshold_uncertainty_score":0.7169325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07130721579069287,"score_gpt":0.3095824787666298,"score_spread":0.2382752629759369,"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."}}