{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001383947,0.0007755558,0.0005135679,0.0007999307,0.0001701658,0.0004497765,0.0008753334,0.0003506363,0.004218474],"category_scores_gemma":[0.000768784,0.0001777656,0.0004487722,0.0008484481,0.0002729508,0.001531746,0.0006425336,0.000646989,0.002820025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002633307,"about_ca_system_score_gemma":0.0004304188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002209049,"about_ca_topic_score_gemma":0.004336037,"domain_scores_codex":[0.9998063,0.00002089963,0.00001186434,0.00006654551,0.00006916228,0.00002523921],"domain_scores_gemma":[0.9997869,0.00003587522,0.00002571188,0.0000593973,0.00007186697,0.00002016833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003805458,0.0001251666,0.0009291716,0.0001982373,0.00004069566,0.0002422265,0.00006630627,0.03073575,0.08959122,0.005838114,0.01256206,0.8592905],"study_design_scores_gemma":[0.0000344356,0.0002822115,0.001356253,0.00001761867,0.00004649265,0.0004899084,0.00008796877,0.9016439,0.08007947,0.005810035,0.01011769,0.00003410849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0586727,0.0007939282,0.9230117,0.0001799663,0.0002577643,0.0001375433,0.001217593,0.009513135,0.006215719],"genre_scores_gemma":[0.6820721,0.0008447901,0.2944548,0.0003069287,0.000136901,0.0001578688,0.00587086,0.0004440908,0.01571171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004218474,"threshold_uncertainty_score":0.01411217,"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."}}