{"id":"W2892270085","doi":"10.1016/j.neucom.2018.08.039","title":"Deep saliency detection via channel-wise hierarchical feature responses","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Softmax function; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Feature extraction; Benchmark (surveying); Channel (broadcasting); Feature learning; Deep learning; Cross entropy; Entropy (arrow of time)","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":[0.0003613444,0.0001949702,0.0001550287,0.0002578547,0.0006757575,0.0002058248,0.0005670572,0.0001135833,0.000009992957],"category_scores_gemma":[0.0001270371,0.0001872984,0.0001075526,0.0008730016,0.00008863729,0.0003777459,0.0003016606,0.0003646984,0.0001949551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003919841,"about_ca_system_score_gemma":0.00002449494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001172989,"about_ca_topic_score_gemma":0.00002184213,"domain_scores_codex":[0.9980004,0.0002872616,0.000258994,0.0006491037,0.0003658361,0.0004384409],"domain_scores_gemma":[0.9990507,0.0001118874,0.000125868,0.0004161624,0.0001476509,0.0001477136],"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":[0.0001231442,0.0002034503,0.0005584638,0.00003207089,0.00001742898,0.0000636701,0.002057805,0.0002478626,0.114832,0.00180767,0.0002556809,0.8798007],"study_design_scores_gemma":[0.0004257266,0.0008700018,0.0271995,0.00002565766,0.000006772186,0.0003476298,0.00002225254,0.9314063,0.03279187,0.002367411,0.004191172,0.0003456656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2252737,0.00001767936,0.7709955,0.0006514793,0.001609253,0.0001463497,1.881955e-7,0.0005858364,0.0007200026],"genre_scores_gemma":[0.9927657,0.000002174386,0.005309158,0.0009281876,0.0007426382,0.000008090082,6.971582e-7,0.0000177953,0.0002255105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9311585,"threshold_uncertainty_score":0.7637806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01617082142043701,"score_gpt":0.274293262200596,"score_spread":0.258122440780159,"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."}}