{"id":"W4405272702","doi":"10.1109/ubmk63289.2024.10773601","title":"Word Image Representation at Local and Global Levels Based on Vision Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Transformer; Computer vision; Artificial intelligence; Word (group theory); Image (mathematics); Representation (politics); Natural language processing; Linguistics; Engineering; Electrical engineering; Political science; Voltage","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":[0.0001783997,0.0001043841,0.00008592438,0.00006952024,0.00006650011,0.0002658733,0.0001476038,0.00005491657,0.0001744084],"category_scores_gemma":[0.000009522795,0.0000861831,0.00005206641,0.0003737825,0.00006479859,0.0005872044,0.00005086035,0.0000686822,0.0001351824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001242837,"about_ca_system_score_gemma":0.00003692571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003232096,"about_ca_topic_score_gemma":0.00002760881,"domain_scores_codex":[0.9990032,0.00004444536,0.0001471311,0.0004029114,0.0002501873,0.0001520645],"domain_scores_gemma":[0.999615,0.00008645219,0.00001306151,0.0001730787,0.00003365188,0.00007873037],"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":[0.00001264292,0.00002224383,0.00003969614,0.00002577154,0.000004608074,0.00003555993,0.00007290006,0.000004864113,0.002047268,0.004442486,0.004220224,0.9890717],"study_design_scores_gemma":[0.0005188448,0.0003957654,0.004561358,0.0002109834,0.00001189243,0.0000571659,0.00004747391,0.7832772,0.1910179,0.01559601,0.00394122,0.0003642022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0062231,0.00002917889,0.9690147,0.002563768,0.000103577,0.0001716461,0.000009351045,0.000759275,0.0211254],"genre_scores_gemma":[0.943467,0.00001082523,0.05553548,0.000621177,0.00001356256,0.00001541468,0.000005842622,0.000005958941,0.0003247822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9887075,"threshold_uncertainty_score":0.3514445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01798399319047412,"score_gpt":0.3111256265403669,"score_spread":0.2931416333498928,"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."}}