{"id":"W2734950743","doi":"10.1109/ijcnn.2017.7966307","title":"A fast method for saliency detection by back-propagating a convolutional neural network and clamping its partial outputs","year":2017,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computer science; Pascal (unit); Convolutional neural network; Pixel; Pattern recognition (psychology); Salience (neuroscience); Deep learning; Benchmark (surveying); Gradient descent; Object detection; Image (mathematics); Computer vision; Artificial neural network","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006060443,0.0001433441,0.0001539607,0.00004018817,0.001340572,0.0005471162,0.000341372,0.00007909519,0.000014801],"category_scores_gemma":[0.0001303253,0.0001311802,0.00007869158,0.00008988593,0.00004516647,0.0009180266,0.0002660633,0.0001136796,0.00001726323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002933347,"about_ca_system_score_gemma":0.00001869316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004392363,"about_ca_topic_score_gemma":0.00005094554,"domain_scores_codex":[0.9986107,0.0001005634,0.0002696365,0.0004721486,0.0001971529,0.0003498349],"domain_scores_gemma":[0.9992068,0.00006844456,0.0002227172,0.0002755014,0.0001191816,0.0001073885],"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":[0.00009397051,0.0001070659,0.001810971,0.00009248125,0.00005389729,0.000002430636,0.00042658,0.001005688,0.09867268,0.06543954,0.001574902,0.8307198],"study_design_scores_gemma":[0.0005878874,0.0001988758,0.002688515,0.00001471291,0.000007693078,0.00002873906,0.0000225069,0.9819797,0.01181026,0.001339884,0.001128187,0.0001930867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01928515,0.000049533,0.9779072,0.000657922,0.001034711,0.0003186737,0.000003060751,0.0001303792,0.0006133289],"genre_scores_gemma":[0.9337627,0.000003726612,0.06495917,0.0002793108,0.0002864056,0.00005447361,0.000002842439,0.000009425681,0.0006419283],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.980974,"threshold_uncertainty_score":0.9999595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03988104908559037,"score_gpt":0.3265477079992886,"score_spread":0.2866666589136982,"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."}}