{"id":"W4205487349","doi":"10.1007/s10032-021-00391-3","title":"Segmentation for document layout analysis: not dead yet","year":2022,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Mitacs","keywords":"Computer science; Segmentation; Bounding overwatch; Minimum bounding box; Task (project management); Benchmarking; Annotation; Artificial intelligence; Object (grammar); Image segmentation; Document layout analysis; Pattern recognition (psychology); Image (mathematics); Information retrieval; Machine learning; Data mining","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":[0.001343754,0.001812535,0.002162649,0.002851219,0.0007864843,0.003881669,0.002639509,0.002415949,0.01336356],"category_scores_gemma":[0.002910265,0.001041796,0.001267033,0.003429257,0.001153021,0.004351308,0.001237307,0.001698012,0.01733792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007183289,"about_ca_system_score_gemma":0.001326668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003026665,"about_ca_topic_score_gemma":0.004167357,"domain_scores_codex":[0.9982964,0.0003509825,0.0001036102,0.0005127518,0.000582937,0.0001532734],"domain_scores_gemma":[0.9962322,0.00104245,0.0001889777,0.0008797047,0.001442091,0.0002145378],"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":[0.000183488,0.00007089247,0.0006446808,0.000759302,0.00009955122,0.00004966681,0.0001188968,0.001563395,0.04087686,0.002576027,0.02716196,0.9258953],"study_design_scores_gemma":[0.0001651357,0.0008839645,0.009831396,0.001257518,0.0005750432,0.001603714,0.001235964,0.2009663,0.2426459,0.05441723,0.4859785,0.0004394996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01246677,0.05083363,0.892892,0.003793309,0.002156616,0.000269614,0.002194073,0.02585125,0.009542749],"genre_scores_gemma":[0.08164151,0.02430005,0.8609763,0.001738164,0.001716242,0.0002537459,0.004877002,0.003544408,0.02095256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01336356,"threshold_uncertainty_score":0.04470557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01885778479085148,"score_gpt":0.3029762366451839,"score_spread":0.2841184518543324,"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."}}