{"id":"W2170966597","doi":"10.1109/icpr.2008.4761728","title":"Adaptive semantic Bayesian framework for image attention","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Mixture model; Subtractive color; Bayesian probability; Pattern recognition (psychology); Pixel; Semantics (computer science); Image (mathematics); Machine learning; Cluster analysis; Computer vision","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008197663,0.001216709,0.0008151821,0.001705761,0.0009488108,0.001967207,0.002425407,0.0006325673,0.002479877],"category_scores_gemma":[0.000522076,0.001311518,0.000685036,0.0007331701,0.0003142307,0.004088865,0.0003853782,0.001319273,0.002079954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006742579,"about_ca_system_score_gemma":0.0001831346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008166516,"about_ca_topic_score_gemma":0.00002425425,"domain_scores_codex":[0.9919519,0.00005279735,0.001689235,0.002645083,0.002511448,0.001149564],"domain_scores_gemma":[0.9899728,0.000188163,0.001602944,0.0003108156,0.007398497,0.0005267551],"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":[0.002227023,0.004896285,0.01325749,0.0006080931,0.00203375,0.0001423059,0.003990734,0.0000066365,0.02771158,0.2469145,0.007790077,0.6904215],"study_design_scores_gemma":[0.01238422,0.006898375,0.02860086,0.008072424,0.0004586951,0.00165405,0.006041189,0.5004603,0.04644735,0.3802924,0.001338843,0.007351244],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.183544,0.00001006798,0.7243271,0.0107982,0.005576778,0.00225219,0.0009905506,0.001265731,0.07123532],"genre_scores_gemma":[0.9795172,0.0004062542,0.01245812,0.002866271,0.001539689,0.001321501,0.001009061,0.0001430569,0.00073883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7959732,"threshold_uncertainty_score":0.9990689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1081114388172074,"score_gpt":0.3225120086263616,"score_spread":0.2144005698091542,"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."}}