{"id":"W2111062549","doi":"10.1109/icip.2000.899373","title":"Efficient high-order image subsampling using FANNs","year":2002,"lang":"en","type":"article","venue":"","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Image (mathematics); Artificial neural network; Feed forward; Artificial intelligence; Pattern recognition (psychology); Feedforward neural network; SIGNAL (programming language); Signal processing; Order (exchange); Image processing; Algorithm; Computer vision; Engineering; Digital signal processing; Computer hardware","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":[0.00003577617,0.00009055102,0.00007289708,0.00004816023,0.00008910388,0.00005780825,0.00009264694,0.00003632021,0.0003845404],"category_scores_gemma":[0.000005609603,0.00008739356,0.0000224506,0.0002251937,0.00002129409,0.00003860846,0.00002106061,0.0000826601,0.00008901607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003556232,"about_ca_system_score_gemma":0.000002292228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001585674,"about_ca_topic_score_gemma":6.056314e-7,"domain_scores_codex":[0.9995211,0.000002277047,0.0001163979,0.0001097478,0.00006797907,0.0001824661],"domain_scores_gemma":[0.9997336,0.000009861996,0.00001138016,0.0001674279,0.00004234806,0.00003536161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.606139e-7,0.0001654241,0.00005254155,0.000156,0.00003132671,0.000007801481,0.0005228137,0.4444876,0.5141776,0.008011466,0.005671797,0.02671475],"study_design_scores_gemma":[0.00005282356,0.000002229038,0.00002172974,0.0000109022,0.000006488341,0.000004661094,0.00001509645,0.9709854,0.02682086,0.0002156203,0.00173454,0.0001296637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08817652,0.0001573772,0.8983486,0.00006385677,0.00004388391,0.00008158379,0.000002660245,0.001175653,0.01194993],"genre_scores_gemma":[0.6637439,0.000009268014,0.3359749,0.00003124958,0.00003537018,0.00001088391,0.000001377233,0.00002312802,0.0001699387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5755673,"threshold_uncertainty_score":0.4210448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02189755945504283,"score_gpt":0.2485047239318505,"score_spread":0.2266071644768076,"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."}}