{"id":"W3122447812","doi":"10.15353/jcvis.v6i1.3533","title":"2D Positional Embedding-based Transformer for Scene Text Recognition","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"ATS Automation Tooling Systems (Canada); University of Waterloo","funders":"Ontario Centres of Excellence","keywords":"Computer science; Transformer; Artificial intelligence; Encoder; Embedding; Leverage (statistics); Architecture; Pattern recognition (psychology); Text recognition; Computer vision; Image (mathematics); Engineering; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0006672548,0.0001322503,0.0002537874,0.0002893416,0.0001708888,0.0004790954,0.0001653207,0.00004285657,0.00001870371],"category_scores_gemma":[0.00006621631,0.0001178153,0.0001592027,0.0002170867,0.0000376374,0.0008938872,0.00001571822,0.0001301675,0.000006131904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005608507,"about_ca_system_score_gemma":0.0002842851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000200054,"about_ca_topic_score_gemma":2.16568e-7,"domain_scores_codex":[0.9984393,0.0001234,0.0006196708,0.0001820919,0.0004825145,0.0001530891],"domain_scores_gemma":[0.9973063,0.0004264362,0.0003419025,0.00008241546,0.001722277,0.0001206574],"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":[0.000208648,0.0008273895,0.0005064906,0.0006221666,0.0002004058,0.0001711459,0.0007273717,0.01470509,0.01731113,0.01139956,0.02654272,0.9267779],"study_design_scores_gemma":[0.002420478,0.0003178402,0.001883473,0.001132949,0.00003883638,0.002474399,0.0001507386,0.9450583,0.006811094,0.03320404,0.006189688,0.0003181461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006878939,0.000715021,0.9880996,0.003400045,0.0004652099,0.0001625492,0.00002549962,0.00005124515,0.0002019412],"genre_scores_gemma":[0.7549889,0.00001985474,0.2438898,0.0008173902,0.0001823797,0.00001063038,0.0000468937,0.00001197907,0.00003218921],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9303532,"threshold_uncertainty_score":0.4804369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01543053248644881,"score_gpt":0.2989395937905886,"score_spread":0.2835090613041398,"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."}}