{"id":"W2948538458","doi":"10.1109/cybermatics_2018.2018.00093","title":"Double Encoding - Slow Decoding Image to Image CNN for Foreground Identification with Application Towards Intelligent Transportation","year":2018,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Decoding methods; Artificial intelligence; Convolutional neural network; Encoder; Encoding (memory); Pattern recognition (psychology); Feature (linguistics); Computer vision; Segmentation; Image segmentation; 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":[0.000439088,0.0001434856,0.0001192006,0.0001928006,0.0003183281,0.0003851221,0.0003736604,0.0000489805,0.00002524592],"category_scores_gemma":[0.00001258071,0.000124554,0.00006654347,0.000588953,0.00004336194,0.0012388,0.00001893138,0.00005029775,0.0001507368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040048,"about_ca_system_score_gemma":0.00003202192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009947852,"about_ca_topic_score_gemma":0.0002892423,"domain_scores_codex":[0.9985778,0.00001569114,0.0003569683,0.0005304027,0.0002722654,0.0002469274],"domain_scores_gemma":[0.9989282,0.00001979328,0.0001332396,0.000360107,0.0004539329,0.000104711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002696239,0.0001970472,0.0002746663,0.00009951182,0.00003608034,0.00000117619,0.004638275,0.00007184528,0.4710585,0.1365915,0.0009474934,0.3858142],"study_design_scores_gemma":[0.0008433596,0.0006097471,0.00576099,0.00002982285,0.000027381,0.000006710912,0.0004659686,0.1562382,0.8288366,0.003357641,0.003419098,0.0004044509],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05065616,0.000002681805,0.9451045,0.0006592253,0.0002862725,0.0009037163,0.000003029646,0.0002659103,0.002118478],"genre_scores_gemma":[0.8471558,0.000002096839,0.1516503,0.0001607108,0.0001058542,0.0003043643,0.00002913402,0.0000131272,0.0005786219],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7964997,"threshold_uncertainty_score":0.5079166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03054020060579253,"score_gpt":0.3215287366973487,"score_spread":0.2909885360915562,"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."}}