{"id":"W1885177706","doi":"10.1109/tdscen.1989.68103","title":"Generic object recognition: building coarse 3D descriptions from line drawings","year":2003,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Object (grammar); Cognitive neuroscience of visual object recognition; Artificial intelligence; Line (geometry); Line drawings; Sketch recognition; Image (mathematics); Human–computer interaction; Computer vision; Natural language processing; Engineering drawing; Mathematics; Engineering","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":[0.0001967282,0.0001173575,0.0001085505,0.0001212204,0.0002547927,0.0002086228,0.0002264727,0.00005963981,0.0006800243],"category_scores_gemma":[0.00006635618,0.0001104441,0.00007850754,0.0005819724,0.00002428635,0.0005833336,0.00004802295,0.0001090584,0.0005998484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004441822,"about_ca_system_score_gemma":0.00003658777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000108661,"about_ca_topic_score_gemma":0.00003224811,"domain_scores_codex":[0.9988969,0.0001009742,0.0002288432,0.0003676087,0.0001980147,0.0002076445],"domain_scores_gemma":[0.9994282,0.00003473299,0.00005951044,0.0002810767,0.00009989444,0.00009656164],"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":[0.00001852079,0.000888671,0.001202668,0.00002436671,0.0001288656,0.00006697312,0.001897034,0.0009176843,0.304179,0.06580096,0.008484357,0.6163909],"study_design_scores_gemma":[0.00279161,0.0007806304,0.003526715,0.0001254276,0.00009577946,0.0002696785,0.0006051289,0.5670812,0.2319277,0.08145654,0.1093267,0.002012902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1628652,0.00004973595,0.8290359,0.0001761693,0.0009857516,0.00008222669,0.00000229111,0.0003496089,0.006453031],"genre_scores_gemma":[0.7036875,0.00002052211,0.2937945,0.000953675,0.00009141383,0.00001804777,0.00000730458,0.000008627333,0.001418387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.614378,"threshold_uncertainty_score":0.7710038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05614483675386607,"score_gpt":0.2752722099264865,"score_spread":0.2191273731726204,"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."}}