{"id":"W2903865507","doi":"10.1007/s00138-018-0995-y","title":"Saliency object detection: integrating reconstruction and prior","year":2018,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer vision; Kadir–Brady saliency detector; Saliency map; Computer science; Iterative reconstruction; Object (grammar); Object detection; Pixel; Segmentation; Image (mathematics); Pattern recognition (psychology); Image segmentation","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":[0.0001734551,0.0001035719,0.00008908586,0.0001290932,0.0006725196,0.0001808181,0.0001257259,0.00004849235,0.00002398403],"category_scores_gemma":[0.00002094716,0.00008482393,0.00002597452,0.0004293812,0.0001122249,0.0003178499,0.0001038501,0.000106141,0.00003592847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001475624,"about_ca_system_score_gemma":0.00001064334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000390237,"about_ca_topic_score_gemma":0.00008558531,"domain_scores_codex":[0.9991809,0.00004133128,0.0001939802,0.0003621159,0.0001066159,0.0001151188],"domain_scores_gemma":[0.9995034,0.00002918654,0.00007638865,0.0002266232,0.00008061584,0.00008379408],"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":[0.000002257152,0.00002057212,0.0002578923,0.000005198305,0.000002374901,8.871783e-8,0.0001315519,1.853503e-7,0.0088274,0.01625551,0.00001615466,0.9744808],"study_design_scores_gemma":[0.001924256,0.001959907,0.08642042,0.0001283095,0.00004762637,0.001223418,0.0008689641,0.6893537,0.03756093,0.0445381,0.1347999,0.001174471],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07531378,0.0001230719,0.9200427,0.0005461553,0.0001902872,0.0002570231,0.000001769008,0.0002484951,0.003276757],"genre_scores_gemma":[0.989077,0.00005204851,0.01032281,0.0001644784,0.0001296393,0.00005949708,0.000001565036,0.000005646853,0.000187358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9733064,"threshold_uncertainty_score":0.5172545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00813923495912512,"score_gpt":0.2857965658672855,"score_spread":0.2776573309081604,"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."}}