{"id":"W2059753722","doi":"10.1109/cvpr.2013.131","title":"Statistical Textural Distinctiveness for Salient Region Detection in Natural Images","year":2013,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Optimal distinctiveness theory; Salient; Artificial intelligence; Pattern recognition (psychology); Computer science; Invariant (physics); Texture (cosmology); Statistical model; Image texture; Pixel; Image (mathematics); Set (abstract data type); Computer vision; Mathematics; 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":[0.0001103689,0.00009430588,0.00009608472,0.0001004921,0.00009321325,0.0001441217,0.0001744365,0.0000379144,0.00002072902],"category_scores_gemma":[0.00006863588,0.00007466857,0.00004233831,0.0002209152,0.00003095055,0.0006223736,0.00005327367,0.00008554785,0.00005307558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007575109,"about_ca_system_score_gemma":0.00001072784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002143216,"about_ca_topic_score_gemma":0.00008746309,"domain_scores_codex":[0.999115,0.0000563654,0.000187421,0.0002969761,0.0001343949,0.0002098326],"domain_scores_gemma":[0.9995793,0.00007986176,0.00004243993,0.0001465362,0.0001015043,0.00005033267],"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":[0.0000452036,0.0001735879,0.001991248,0.00004017928,0.000008715621,0.00000574837,0.0001886958,0.00004220318,0.02309791,0.05100796,0.0009881285,0.9224104],"study_design_scores_gemma":[0.001011324,0.0003505303,0.4822802,0.00001787173,0.000004337719,0.00003553087,0.0001570194,0.4577439,0.03062769,0.02683443,0.0005802948,0.0003568036],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1230254,0.000009089537,0.8752064,0.00043377,0.0005859855,0.0003437491,7.805796e-7,0.0001212581,0.0002735906],"genre_scores_gemma":[0.9920101,0.000001150684,0.007131961,0.0001345429,0.0000363559,0.0001390697,0.00000369344,0.000004978702,0.0005381724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9220536,"threshold_uncertainty_score":0.3044896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01382940570661778,"score_gpt":0.2735053159341758,"score_spread":0.259675910227558,"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."}}