{"id":"W2798322161","doi":"10.1016/j.imavis.2020.103887","title":"EML-NET: An Expandable Multi-Layer NETwork for saliency prediction","year":2020,"lang":"en","type":"preprint","venue":"Image and Vision Computing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Leverage (statistics); Encoder; Inference; Scalability; Artificial intelligence; Encoding (memory); Layer (electronics); Computational model; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000604457,0.001093602,0.0007734328,0.000715379,0.000372938,0.0007356542,0.002859184,0.001247465,0.007066181],"category_scores_gemma":[0.001778087,0.0006658892,0.000615877,0.0005393927,0.0003139183,0.001835052,0.001367764,0.001375415,0.001744337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001007399,"about_ca_system_score_gemma":0.000715778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008553068,"about_ca_topic_score_gemma":0.01702129,"domain_scores_codex":[0.9998367,0.00002109941,0.000008045424,0.00006783806,0.00003573652,0.0000305356],"domain_scores_gemma":[0.9996006,0.0001524347,0.00003072994,0.00006560505,0.0001012169,0.00004944588],"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":[0.0009116193,0.0003591274,0.001737098,0.0002914751,0.0002599497,0.0001994656,0.00007213424,0.2121085,0.02210629,0.007512168,0.03668291,0.7177592],"study_design_scores_gemma":[0.00002114035,0.00003766433,0.0001949113,0.000009345959,0.00002147621,0.00001771604,0.000003871271,0.9908468,0.003471059,0.00374091,0.001627547,0.000007580204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03751,0.001834758,0.9377965,0.0006441757,0.0004160365,0.0001566911,0.001863167,0.01475329,0.005025405],"genre_scores_gemma":[0.483302,0.0008160998,0.4921398,0.0008444212,0.0002801576,0.0003213798,0.003443648,0.0008100945,0.01804238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008553068,"threshold_uncertainty_score":0.02363878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05634051383164976,"score_gpt":0.3734769481801531,"score_spread":0.3171364343485034,"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."}}