{"id":"W3170952646","doi":"10.1109/tcsvt.2021.3087002","title":"CATFPN: Adaptive Feature Pyramid With Scale-Wise Concatenation and Self-Attention","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"National Key Research and Development Program of China; Key Laboratory of System Control and Information Processing; State Key Laboratory of Integrated Services Networks; National Natural Science Foundation of China","keywords":"Pyramid (geometry); Feature (linguistics); Concatenation (mathematics); Computer science; Artificial intelligence; Pattern recognition (psychology); Block (permutation group theory); Object detection; Backbone network; Feature extraction; Benchmark (surveying); Context (archaeology); Computer vision; Mathematics","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":[0.00009374152,0.0001744459,0.000236757,0.0002106203,0.0003879175,0.00009164762,0.0001758352,0.0001891406,4.978955e-7],"category_scores_gemma":[0.000003389664,0.0001556338,0.00003640587,0.0006693812,0.000114742,0.0002987781,0.000004442126,0.0002279882,0.000002738742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000647171,"about_ca_system_score_gemma":0.00005328257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008543089,"about_ca_topic_score_gemma":0.00009097209,"domain_scores_codex":[0.998797,0.00003663004,0.0001931801,0.0005950928,0.0001335462,0.0002445747],"domain_scores_gemma":[0.9990497,0.0001033036,0.0001011558,0.0004032459,0.0002685754,0.00007396706],"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":[0.00009389599,0.001244698,0.0006450675,0.0006181955,0.0006893659,0.0001044924,0.001250618,0.01500092,0.07354639,0.3039253,0.0006541362,0.6022269],"study_design_scores_gemma":[0.0107659,0.004611455,0.003279447,0.001065023,0.000693712,0.007999116,0.003136288,0.7889128,0.1200707,0.02120892,0.03513677,0.003119862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03032014,0.0007262137,0.9652392,0.002177511,0.0002450723,0.0007327566,0.00002740515,0.0004836042,0.00004813612],"genre_scores_gemma":[0.9935828,0.0002079012,0.005293759,0.00007920763,0.0000215568,0.0005373629,0.000003594869,0.00001828131,0.0002555388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9632627,"threshold_uncertainty_score":0.634656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362741790620734,"score_gpt":0.2313012032247169,"score_spread":0.2176737853185096,"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."}}