{"id":"W4213336482","doi":"10.1109/access.2022.3152189","title":"SATSal: A Multi-Level Self-Attention Based Architecture for Visual Saliency Prediction","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Encoder; Benchmark (surveying); Salient; Human visual system model; Convolutional neural network; Deep learning; Decoding methods; Machine learning; Pattern recognition (psychology); Image (mathematics); Algorithm","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":[0.0004785432,0.000178881,0.0001536422,0.0003305429,0.0007362506,0.0002847554,0.0009531186,0.00006122185,0.00003724792],"category_scores_gemma":[0.00002632165,0.0001828317,0.0001774998,0.0007791331,0.00001985091,0.0007198084,0.0002065087,0.0002329371,0.00001114905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001521434,"about_ca_system_score_gemma":0.00009714055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003400418,"about_ca_topic_score_gemma":0.00002657773,"domain_scores_codex":[0.998034,0.0001856622,0.0003328426,0.0005930078,0.0005203711,0.0003341266],"domain_scores_gemma":[0.999202,0.00006108763,0.0001788534,0.0003395493,0.0001231705,0.00009534137],"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":[0.000842666,0.01218768,0.03212356,0.0009322042,0.000445293,0.00007250773,0.006007513,0.1104784,0.1683501,0.008967649,0.02539336,0.6341991],"study_design_scores_gemma":[0.002443218,0.0008016974,0.0500537,0.0000155412,0.00003324146,0.00003379089,0.0000705374,0.9327793,0.005360562,0.001071124,0.006941314,0.0003960392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.137125,0.00001351907,0.8583132,0.0004683532,0.002667037,0.0006048157,0.00005006796,0.000704939,0.0000530253],"genre_scores_gemma":[0.9835064,0.000001739337,0.01468833,0.0007477617,0.000156025,0.0006228701,0.00004186366,0.00002410774,0.0002108464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8463814,"threshold_uncertainty_score":0.7455659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05731573466890871,"score_gpt":0.340481299320237,"score_spread":0.2831655646513283,"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."}}