{"id":"W3003525420","doi":"10.1109/iscc47284.2019.8969682","title":"Deep Learning for the Detection of Tabular Information from Electronic Component Datasheets","year":2019,"lang":"en","type":"article","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Object detection; Domain (mathematical analysis); Component (thermodynamics); Precision and recall; Feature (linguistics); Machine learning; Backbone network; Feature learning; Feature extraction; Transfer of learning; Pyramid (geometry); Pattern recognition (psychology)","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":[0.0002043206,0.00006442806,0.00009855461,0.00004951071,0.00005253999,0.00002582256,0.00005804161,0.00006990436,0.00006819607],"category_scores_gemma":[0.00002062042,0.00004624549,0.00004561713,0.00008619575,0.000003723371,0.0002417995,0.00000976979,0.0001308628,0.00008230369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004999041,"about_ca_system_score_gemma":0.000005009887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002308598,"about_ca_topic_score_gemma":0.00004067292,"domain_scores_codex":[0.9994989,0.00001574054,0.0002096773,0.00005170637,0.0001052056,0.0001187933],"domain_scores_gemma":[0.9996489,0.0001154513,0.00005306113,0.0001326886,0.00003715475,0.00001271858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001165373,0.000007924398,0.0003147729,0.00007588162,0.0001549376,3.80833e-8,0.0003462941,0.4736289,0.2078871,0.0003716939,0.0001994181,0.3168965],"study_design_scores_gemma":[0.0005299373,0.0001042247,0.0009253171,0.0000109746,0.00001590358,7.770363e-7,0.0003270271,0.8244589,0.06564009,0.00003650118,0.1078709,0.0000794443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3414975,0.0001815525,0.6566521,0.00000474991,0.0006617162,0.0004556142,0.000004398277,0.0001098539,0.0004325163],"genre_scores_gemma":[0.9997653,0.0000209328,0.00003942577,0.000006432671,0.00007425959,0.00002148822,0.00004439827,0.000008044221,0.00001968673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6582678,"threshold_uncertainty_score":0.1885836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007041172974796278,"score_gpt":0.193927516598578,"score_spread":0.1868863436237818,"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."}}