{"id":"W4381325436","doi":"10.1016/j.array.2023.100300","title":"ResneSt-Transformer: Joint attention segmentation-free for end-to-end handwriting paragraph recognition model","year":2023,"lang":"en","type":"article","venue":"Array","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Transformer; End-to-end principle; Encoder; Paragraph; Speech recognition; Pattern recognition (psychology); Pipeline (software); Computer vision; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002976021,0.001155638,0.0006536433,0.0004329417,0.0002436121,0.0006047399,0.002964238,0.000870851,0.006044462],"category_scores_gemma":[0.0007591112,0.0005692024,0.0009353675,0.000328227,0.0003085657,0.001222877,0.0008524233,0.001492407,0.002741826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000785795,"about_ca_system_score_gemma":0.001401518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009011785,"about_ca_topic_score_gemma":0.01547222,"domain_scores_codex":[0.9998054,0.00001560611,0.00001017898,0.00008244441,0.0000532262,0.00003315428],"domain_scores_gemma":[0.9998093,0.00004323272,0.00001917531,0.00004740502,0.00006191248,0.0000190546],"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":[0.0003388565,0.0001745005,0.001155075,0.0001959503,0.0001379378,0.0003122578,0.0001035115,0.4392798,0.04437322,0.006426362,0.01494161,0.492561],"study_design_scores_gemma":[0.00000780684,0.0000314053,0.0001327638,0.000004902641,0.00001091409,0.00003534189,0.000003986165,0.9904928,0.006859816,0.001126453,0.001287885,0.000005972317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01733537,0.0003882884,0.9639611,0.0001093429,0.0000963459,0.0001387483,0.0005462476,0.01415115,0.003273481],"genre_scores_gemma":[0.4771909,0.0005054091,0.4889994,0.0004359667,0.00008201523,0.0004715264,0.00475954,0.001114994,0.02644012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009011785,"threshold_uncertainty_score":0.0202207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04780665872640486,"score_gpt":0.2854302757035785,"score_spread":0.2376236169771737,"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."}}