{"id":"W2968873170","doi":"10.1007/978-3-030-27202-9_35","title":"Spatially-Coherent Segmentation Using Hierarchical Gaussian Mixture Reduction Based on Cauchy-Schwarz Divergence","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Cauchy distribution; Divergence (linguistics); Computer science; Gaussian; Reduction (mathematics); Algorithm; Artificial intelligence; Applied mathematics; Pattern recognition (psychology); Mathematical optimization; Mathematics; Statistics; Geometry; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006383702,0.0005635085,0.0004362902,0.001033862,0.0004184897,0.0005331677,0.001564479,0.0003962191,0.00008127421],"category_scores_gemma":[0.00004586907,0.0005124251,0.0001966002,0.0007669242,0.00035556,0.0006897949,0.0004394478,0.001079955,0.00009182226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006889203,"about_ca_system_score_gemma":0.0007274289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005959221,"about_ca_topic_score_gemma":0.00004743,"domain_scores_codex":[0.9953791,0.0001116863,0.0005868592,0.001767446,0.001568439,0.000586437],"domain_scores_gemma":[0.9979559,0.0001285363,0.0003975868,0.00109587,0.0002194966,0.0002026737],"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":[0.00004926648,0.0001451024,0.0002076261,0.00009606509,0.00001646438,0.00005256623,0.0006219375,0.4644927,0.009503873,0.008315244,0.00002545652,0.5164737],"study_design_scores_gemma":[0.0003765147,0.0004806607,0.0003805147,0.0004259511,0.00001272046,0.00004901798,3.239106e-7,0.9798898,0.006051912,0.01146924,0.0002238944,0.0006394855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001675742,0.0000419428,0.9899303,0.0007848232,0.005779821,0.0006770419,0.000006368599,0.0001780127,0.0009259347],"genre_scores_gemma":[0.754241,0.00001821401,0.2430589,0.00130022,0.0007554022,0.00001320428,0.00002702,0.00005347321,0.0005325042],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7525653,"threshold_uncertainty_score":0.9997327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0235108287181525,"score_gpt":0.2767702642970484,"score_spread":0.2532594355788959,"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."}}