{"id":"W110997863","doi":"10.1016/j.imavis.2006.12.021","title":"Models from image triplets using epipolar gradient features","year":2007,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Epipolar geometry; Artificial intelligence; Matching (statistics); Computer vision; Feature (linguistics); Image (mathematics); Consistency (knowledge bases); Pattern recognition (psychology); Point (geometry); Mathematics; Measure (data warehouse); Computer science; Iterative reconstruction; Data mining; Geometry","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":[0.0006801041,0.0002395847,0.0002671372,0.0001999885,0.000504849,0.0005106062,0.0004784524,0.00006024101,0.000006706779],"category_scores_gemma":[0.0000671741,0.000216271,0.00008791181,0.0003502055,0.00008268884,0.001606145,0.0006904524,0.0002873765,0.00001176971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004351468,"about_ca_system_score_gemma":0.00002292274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009645562,"about_ca_topic_score_gemma":0.000002478082,"domain_scores_codex":[0.9980158,0.0000637678,0.0003985025,0.0006618818,0.0003347948,0.0005252914],"domain_scores_gemma":[0.998746,0.000281399,0.0001677211,0.0004574308,0.0001255803,0.0002218124],"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":[0.00001829901,0.00007157517,0.0001205373,0.00001410546,0.00001321821,0.000209965,0.001429097,0.0003619494,0.1143794,0.002084114,0.0005941219,0.8807036],"study_design_scores_gemma":[0.0006247542,0.00004448914,0.002636373,0.000127511,0.000007167873,0.0000830709,0.0001095203,0.9760332,0.01127811,0.007891272,0.0008512423,0.0003133646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08439636,0.0009855919,0.9128371,0.0002092196,0.0004032348,0.0001168672,0.00000275181,0.0002294433,0.0008194267],"genre_scores_gemma":[0.4729761,0.00002067606,0.5263383,0.0004940876,0.0001339623,1.657687e-7,0.000002631413,0.00001350388,0.00002056183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9756712,"threshold_uncertainty_score":0.8819275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01974494786077186,"score_gpt":0.3357186493584066,"score_spread":0.3159737014976347,"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."}}