{"id":"W1979100774","doi":"10.1109/icip.2012.6467049","title":"Saliency detection via statistical non-redundancy","year":2012,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Redundancy (engineering); Artificial intelligence; Computer science; Gaussian; Pattern recognition (psychology); Neighbourhood (mathematics); Statistical model; Gaussian process; Statistical analysis; Precision and recall; Computer vision; Algorithm; Data mining; Mathematics; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002421979,0.00009745838,0.00008511112,0.00009010472,0.0001572177,0.0000744303,0.0002166018,0.00005228359,0.0001937307],"category_scores_gemma":[0.00002347158,0.00008412726,0.00004327784,0.0003176715,0.00002565657,0.0008655048,0.00007631731,0.00009545402,0.001062875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000040513,"about_ca_system_score_gemma":0.00001186859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005150868,"about_ca_topic_score_gemma":0.00001310575,"domain_scores_codex":[0.9989914,0.00004853138,0.0001862797,0.0002068873,0.0002376006,0.0003292711],"domain_scores_gemma":[0.9994717,0.00002792156,0.00004101252,0.0002459189,0.000043898,0.0001695191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000009296293,0.0004557745,0.004846072,0.00002074242,0.00001608471,0.000003045855,0.0007186012,0.000006084655,0.05509173,0.1288512,0.0008199963,0.8091614],"study_design_scores_gemma":[0.001279924,0.0009737891,0.5457411,0.00001967143,0.00003113462,0.0003314523,0.0001715128,0.2520935,0.1552509,0.01833298,0.02450842,0.001265701],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02826384,0.00001598924,0.9607619,0.00009247014,0.001529379,0.00008736265,4.627847e-7,0.0002661831,0.008982432],"genre_scores_gemma":[0.9810701,0.000002302542,0.01787291,0.0002057211,0.0001352786,0.00001358848,0.000001207705,0.00000606584,0.0006927968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9528063,"threshold_uncertainty_score":0.9997149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01284168742195125,"score_gpt":0.2766479321892262,"score_spread":0.263806244767275,"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."}}