{"id":"W2003301053","doi":"10.1016/j.imavis.2012.11.002","title":"On growth and formlets: Sparse multi-scale coding of planar shape","year":2012,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Image warping; Mathematics; Planar; Algorithm; Computer science; Topology (electrical circuits); Shape analysis (program analysis); Generalization; Sparse approximation; Artificial intelligence; Pattern recognition (psychology); Computer vision; Combinatorics; Mathematical analysis","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":[0.0002969516,0.00009748193,0.000141444,0.0000980093,0.0002163307,0.0001215391,0.0001187017,0.00003942994,0.000001557235],"category_scores_gemma":[0.00004447141,0.00008553689,0.00002306222,0.0001158561,0.00007169174,0.0006562246,0.0001245265,0.0001047992,0.000003390768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005203465,"about_ca_system_score_gemma":0.00001039454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001042872,"about_ca_topic_score_gemma":3.465437e-7,"domain_scores_codex":[0.9992517,0.00003246859,0.0001848637,0.0002051306,0.0001127358,0.0002130889],"domain_scores_gemma":[0.9995245,0.0001262761,0.0001125451,0.0001107177,0.00004414943,0.00008185255],"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":[0.00001203995,0.0001028277,0.008682187,0.0001840533,0.000008589031,0.00000366507,0.002145361,0.000002279222,0.02348552,0.002864574,0.000154691,0.9623542],"study_design_scores_gemma":[0.001170236,0.0001963078,0.0281082,0.0005818049,0.00001362676,0.000248034,0.000239021,0.9293691,0.03855908,0.001096621,0.00007432437,0.0003436768],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3860626,0.0002758178,0.6129357,0.00008904518,0.0001992043,0.00004189917,7.396971e-7,0.00005099725,0.0003440142],"genre_scores_gemma":[0.8032684,0.0000221211,0.1965492,0.00009081229,0.00005719449,3.038679e-7,6.202238e-7,0.000004682807,0.000006683826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9620106,"threshold_uncertainty_score":0.3488093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01802358497467986,"score_gpt":0.2894189740441668,"score_spread":0.2713953890694869,"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."}}