{"id":"W2152233525","doi":"10.1109/tpami.2012.147","title":"Visual Saliency Based on Scale-Space Analysis in the Frequency Domain","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":574,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Artificial intelligence; Kadir–Brady saliency detector; Salient; Computer science; Frequency domain; Pattern recognition (psychology); Computer vision; Fourier transform; Detector; Spatial frequency; Convolution (computer science); Kernel (algebra); Scale space; Visualization; Entropy (arrow of time); Image processing; Mathematics; Image (mathematics); Saliency map; Optics; Artificial neural network; Physics","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":[0.001005182,0.0002774471,0.0003668135,0.001649412,0.0003089506,0.0001816416,0.0005685695,0.00008908765,0.0001946691],"category_scores_gemma":[0.000005767761,0.0001986991,0.000511198,0.005803173,0.00007495621,0.0003747008,0.000004564671,0.0003886554,0.00005736311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006165271,"about_ca_system_score_gemma":0.00001555643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001321178,"about_ca_topic_score_gemma":0.003522343,"domain_scores_codex":[0.9975126,0.0004529075,0.0004752343,0.0005585846,0.0005880013,0.0004127027],"domain_scores_gemma":[0.9988101,0.0002134838,0.000131049,0.0006390007,0.00005160144,0.0001547978],"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":[0.00007222894,0.004985947,0.1331851,0.00004365628,0.00187591,0.00002867302,0.007295259,0.1074277,0.001255601,0.002702721,0.00001700769,0.7411103],"study_design_scores_gemma":[0.0003079859,0.0005979081,0.1155734,0.00002884929,0.001730563,0.00001151903,0.0006504689,0.8588736,0.02069826,0.0007374045,0.00006126893,0.0007288342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06284083,0.00004174863,0.9354799,0.0008822244,0.0002049246,0.000150849,0.00001277214,0.00006657496,0.000320107],"genre_scores_gemma":[0.9972528,0.00004810294,0.001342899,0.001223284,0.00002559644,0.00004639155,0.000006259522,0.000008714927,0.00004601903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9344119,"threshold_uncertainty_score":0.8102715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01777406914844843,"score_gpt":0.2915349400361138,"score_spread":0.2737608708876654,"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."}}