{"id":"W4403664791","doi":"10.1016/j.engappai.2024.109458","title":"Dynamically Adaptive Deformable Feature Fusion for multi-scale character detection in ancient documents","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Kyungpook National University","keywords":"Computer science; Character (mathematics); Artificial intelligence; Feature (linguistics); Scale (ratio); Pattern recognition (psychology); Fusion; Natural language processing; Computer vision; Linguistics","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":[0.0002710297,0.0001182979,0.0001212632,0.0003267599,0.00005035074,0.00008967071,0.0003570696,0.00008623418,0.00000413321],"category_scores_gemma":[0.00002443143,0.0001210968,0.00006735101,0.000765284,0.00002265725,0.0003804472,0.00007412017,0.0001673012,0.00003129354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001127783,"about_ca_system_score_gemma":0.00002891693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002316872,"about_ca_topic_score_gemma":0.00004026938,"domain_scores_codex":[0.9990155,0.000009160949,0.0003106332,0.000328444,0.0001343844,0.0002018905],"domain_scores_gemma":[0.9994422,0.00007511261,0.0000481212,0.0002644253,0.0001216886,0.00004840651],"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":[0.000009372879,0.0001146859,0.000004315488,0.00009811759,0.000009020288,7.882023e-7,0.0003819453,0.003019942,0.1800606,0.01641003,0.00001415773,0.799877],"study_design_scores_gemma":[0.000009160978,0.0000380997,0.00007031626,0.00007066258,0.000002792366,0.000002437638,0.00001968466,0.6786009,0.3185807,0.001695197,0.0008201647,0.00008991243],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007805692,0.0001008639,0.9907308,0.000101762,0.0001498555,0.0007422644,0.00001538884,0.0003294803,0.00002394678],"genre_scores_gemma":[0.6661634,0.00002073944,0.3329454,0.00001295487,0.00003345092,0.0007679812,0.000007840144,0.00001102751,0.00003719953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7997871,"threshold_uncertainty_score":0.4938183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01956557004669445,"score_gpt":0.2820630817309452,"score_spread":0.2624975116842507,"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."}}