{"id":"W2969772853","doi":"10.1016/j.imavis.2019.08.008","title":"Self-supervised blur detection from synthetically blurred scenes","year":2019,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Eusko Jaurlaritza","keywords":"Artificial intelligence; Computer science; Ground truth; Computer vision; Segmentation; Image (mathematics); Pattern recognition (psychology); Image restoration; Object (grammar); Image segmentation; Image processing","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":[0.00026771,0.000181599,0.0002092172,0.000100788,0.0002070911,0.000499551,0.0004975504,0.00007053828,0.00000997354],"category_scores_gemma":[0.00007517381,0.0001682947,0.00004804074,0.0002491517,0.00004195263,0.0009854414,0.0006073198,0.0001831783,0.00007277612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002618296,"about_ca_system_score_gemma":0.00002533236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001384656,"about_ca_topic_score_gemma":7.19863e-7,"domain_scores_codex":[0.9985517,0.00007383244,0.0002607459,0.0006079453,0.0002317364,0.0002740317],"domain_scores_gemma":[0.9989534,0.0002378782,0.0001076648,0.0004701281,0.0001435891,0.00008733178],"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":[0.000008495129,0.00005542552,0.0002808112,0.00004705261,0.000008445685,0.00001038554,0.0003779153,0.000005780102,0.24937,0.000218552,0.00003083379,0.7495863],"study_design_scores_gemma":[0.0003076614,0.0001028268,0.0007474941,0.0001493122,0.000006080584,0.00001784956,0.00002154849,0.9342751,0.05938137,0.004146977,0.0006089063,0.000234862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1182476,0.0002302227,0.8793847,0.0002400034,0.0002083792,0.0001574016,7.856536e-7,0.00106189,0.0004690026],"genre_scores_gemma":[0.487933,0.00001293856,0.5118585,0.0001290653,0.00004516188,0.000001150296,7.43764e-7,0.00001019021,0.000009207281],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9342693,"threshold_uncertainty_score":0.6862858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006246579469884188,"score_gpt":0.2789864774374947,"score_spread":0.2727398979676106,"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."}}