{"id":"W1626388679","doi":"10.1109/wvm.1991.212802","title":"Getting around the aperture problem using point and line correspondences","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Point (geometry); Rigidity (electromagnetism); Computer science; Variety (cybernetics); Line (geometry); Noise (video); Artificial intelligence; Computer vision; Stability (learning theory); Algorithm; Mathematics; Image (mathematics); Engineering; Geometry; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008526954,0.0008327641,0.00103552,0.001072117,0.0006589869,0.001180091,0.0007398821,0.001610389,0.003512013],"category_scores_gemma":[0.003810539,0.0007075375,0.0006498261,0.001102868,0.0009548522,0.002746407,0.001861609,0.001168697,0.001523336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003282596,"about_ca_system_score_gemma":0.0006426901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001879134,"about_ca_topic_score_gemma":0.001276067,"domain_scores_codex":[0.9993097,0.0001632231,0.00003062289,0.0001799454,0.0002518895,0.00006476112],"domain_scores_gemma":[0.9989686,0.0003868188,0.0001566467,0.0002531562,0.0001858337,0.00004909806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004613799,0.00008027175,0.001372794,0.0002640421,0.0001167233,0.0003970794,0.0006557018,0.15465,0.0749198,0.03473015,0.005616707,0.7267354],"study_design_scores_gemma":[0.00007402004,0.0001663132,0.001295396,0.0000320902,0.00004397394,0.0006331773,0.0001755201,0.8948333,0.04678339,0.04445473,0.01143046,0.00007755665],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008642299,0.00007924128,0.9901508,0.00005756367,0.00001879188,0.00001263622,0.00002308174,0.0005225771,0.0004930313],"genre_scores_gemma":[0.1168604,0.0002260741,0.880074,0.00006461469,0.000044057,0.00004654438,0.0002070845,0.0001672173,0.002310038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003512013,"threshold_uncertainty_score":0.01174891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03460610588749431,"score_gpt":0.2776442919658295,"score_spread":0.2430381860783352,"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."}}