{"id":"W4293868248","doi":"10.1109/crv55824.2022.00026","title":"Occluded Text Detection and Recognition in the Wild","year":2022,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Spotting; Computer science; Artificial intelligence; Text recognition; Text detection; Robustness (evolution); Convolutional neural network; Deep learning; Pattern recognition (psychology); Feature extraction; Speech recognition; Natural language processing; Computer vision; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006239822,0.00005596107,0.00005322808,0.0001374943,0.000188317,0.00009329146,0.0002967852,0.00001879641,0.0001098977],"category_scores_gemma":[0.00002238164,0.0000441018,0.00001853699,0.0004508978,0.00001698283,0.0002773575,0.0001684697,0.0001753193,0.00001821385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003202953,"about_ca_system_score_gemma":0.00001076528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009805621,"about_ca_topic_score_gemma":0.00008046832,"domain_scores_codex":[0.9991963,0.0002041439,0.0001173691,0.0001926268,0.0001806623,0.0001089058],"domain_scores_gemma":[0.9996668,0.00008832602,0.00003277908,0.0001755562,0.00001947337,0.0000170762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003935744,0.00004829291,0.0001002,0.00000272069,0.000001687702,0.000008128367,0.0007984762,6.069298e-7,0.001734175,0.0009776611,0.0006259119,0.9956982],"study_design_scores_gemma":[0.003078144,0.002488443,0.03343716,0.00005472852,0.00002726563,0.00255503,0.005885849,0.08363946,0.1641742,0.6343574,0.06863724,0.001665086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3276403,0.00007729747,0.6451886,0.003627653,0.0001986868,0.0007088056,0.000004602241,0.0006830666,0.02187107],"genre_scores_gemma":[0.9914474,0.00001337815,0.006412459,0.001833141,0.00001434839,0.0001883857,0.000002297599,0.000003209347,0.00008537928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9940331,"threshold_uncertainty_score":0.1798419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02048468726008458,"score_gpt":0.2385355945911143,"score_spread":0.2180509073310298,"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."}}