{"id":"W4322627674","doi":"10.1007/s11063-023-11180-w","title":"A Deep Model of Visual Attention for Saliency Detection on 3D Objects","year":2023,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Outaouais; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Fixation (population genetics); Convolutional neural network; Metric (unit); Visual attention; Human eye; Computer vision; Object detection; Human visual system model; Salient; Visualization; Kadir–Brady saliency detector; Image (mathematics); Cognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002128842,0.0001415062,0.0001445458,0.0003157516,0.0002607257,0.0001076912,0.0002471939,0.00005871155,7.928464e-7],"category_scores_gemma":[0.00005095157,0.0001343882,0.0001106382,0.0007714034,0.00003789951,0.0005792683,0.00004808711,0.0001106121,0.00001802737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000423638,"about_ca_system_score_gemma":0.00002245236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004045846,"about_ca_topic_score_gemma":0.000005575172,"domain_scores_codex":[0.9986435,0.00004075219,0.0002734353,0.0004052519,0.000339135,0.0002978805],"domain_scores_gemma":[0.9994929,0.00003593953,0.0001712245,0.0001585709,0.00008988902,0.00005142511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003918943,0.0000602888,0.00004544116,0.0001312946,0.000005502486,0.00000158784,0.0006426369,0.04012781,0.6598231,0.0001155676,0.00006843151,0.2989391],"study_design_scores_gemma":[0.0003326716,0.0002615147,0.0008546484,0.00003506003,0.000007581776,0.000004243778,0.00004543419,0.9743634,0.02354389,0.0003994487,0.00001022281,0.0001418765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4573572,0.000003260023,0.5412759,0.0005666792,0.0003285962,0.00014577,5.127061e-7,0.0002882372,0.00003386593],"genre_scores_gemma":[0.996614,0.000001503444,0.002218184,0.0009512851,0.00006955313,0.00005520869,0.000004753737,0.00001625251,0.00006928665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9342356,"threshold_uncertainty_score":0.5480191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03243324371324625,"score_gpt":0.2982049443463128,"score_spread":0.2657717006330665,"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."}}