{"id":"W3034214762","doi":"10.1109/cvprw50498.2020.00292","title":"Analyzing symbols in architectural floor plans via traditional computer vision and deep learning approaches","year":2021,"lang":"en","type":"article","venue":"UVic’s Research and Learning Repository (University of Victoria)","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Spotting; Symbol (formal); Floor plan; Clutter; Artificial intelligence; Similarity (geometry); Class (philosophy); Object (grammar); Notation; Machine learning; Pattern recognition (psychology); Image (mathematics); Engineering drawing; Programming language; 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":[0.0007705769,0.0001097535,0.0002105664,0.0001455366,0.0008936647,0.0001105505,0.0001218091,0.00009617442,0.000156007],"category_scores_gemma":[0.00005300204,0.0001100396,0.00004441277,0.0003300502,0.0002433652,0.0002411422,0.00004988304,0.0008896227,0.000009614286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001382785,"about_ca_system_score_gemma":0.00004279347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001280356,"about_ca_topic_score_gemma":0.001722703,"domain_scores_codex":[0.997963,0.0008763181,0.0001213911,0.0003670336,0.0003611674,0.0003111329],"domain_scores_gemma":[0.9991385,0.0004584074,0.00005107789,0.00008311695,0.00009370605,0.0001752018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001950601,0.00004364804,0.900561,0.0001166908,0.00004670581,0.0003906076,0.005389153,0.008064268,0.001402705,0.00002354078,0.00001815582,0.0837485],"study_design_scores_gemma":[0.0004023376,0.000445813,0.9135358,0.00009170156,0.000006672113,0.0001299714,0.004465537,0.07996097,0.00003659045,0.00007991364,0.0007020559,0.0001426728],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966583,0.0009412783,0.0004079601,0.00009029295,0.0001000973,0.00006544619,0.000004680818,0.00002687149,0.001705093],"genre_scores_gemma":[0.9978328,0.0001037871,0.001005981,0.000002341444,0.0001354768,9.280147e-8,0.0001001881,0.000003437528,0.0008158382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08360583,"threshold_uncertainty_score":0.6873437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04311033839043367,"score_gpt":0.2300722772348001,"score_spread":0.1869619388443664,"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."}}