{"id":"W2006498932","doi":"10.1016/j.neucom.2007.10.027","title":"The HCM for perceptual image segmentation","year":2008,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Australian Research Council; Canada Research Chairs","keywords":"Gestalt psychology; Merge (version control); Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Artificial neural network; Image segmentation; Pixel; Computer vision; Similarity (geometry); Scale-space segmentation; Image (mathematics); Perception","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009042164,0.00006654157,0.00005050052,0.00001309317,0.001076899,0.0001106517,0.0004541895,0.00001345031,7.97573e-7],"category_scores_gemma":[0.00001413124,0.00004900089,0.00004751739,0.0001513963,0.00004033597,0.0001417361,0.000120394,0.00007216953,0.00001718607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008504736,"about_ca_system_score_gemma":0.00001465179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001773218,"about_ca_topic_score_gemma":6.95718e-7,"domain_scores_codex":[0.9993261,0.00002398865,0.0001339005,0.0002138395,0.000102589,0.0001995533],"domain_scores_gemma":[0.9993201,0.0003117216,0.00005747054,0.0002297102,0.0000456295,0.00003529969],"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":[0.00001126566,0.000105991,0.0007540844,0.000016236,0.00001527146,0.00001662068,0.002430719,0.004856928,0.06931147,0.08219475,0.06026376,0.7800229],"study_design_scores_gemma":[0.0004403282,0.00009948575,0.00813948,0.00000647538,0.000003975294,0.0001120443,0.00006096399,0.9297544,0.004611353,0.002095228,0.05445928,0.0002170004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1210503,0.00002278965,0.8754998,0.002228096,0.0002165948,0.0003281002,5.533398e-7,0.0001583252,0.000495404],"genre_scores_gemma":[0.8999182,0.00001947653,0.09848599,0.0009291396,0.0003555145,0.00005614495,0.000001991352,0.00001035095,0.0002231901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9248974,"threshold_uncertainty_score":0.8282745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02584023343920464,"score_gpt":0.2653457123201369,"score_spread":0.2395054788809323,"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."}}