{"id":"W1992824101","doi":"10.1109/mpul.2011.2181025","title":"Real-Time Unconstrained Object Recognition: A Processing Pipeline Based on the Mammalian Visual System","year":2012,"lang":"en","type":"article","venue":"IEEE Pulse","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; Defense Advanced Research Projects Agency; Univerza v Ljubljani; U.S. Department of Defense","keywords":"Flexibility (engineering); Pipeline (software); Computer science; Cognitive neuroscience of visual object recognition; Artificial intelligence; Object (grammar); Computer vision; Function (biology); Visualization; Human–computer interaction; Human visual system model; Image (mathematics); Operating system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000328619,0.0001928896,0.0001623269,0.00007299668,0.0001135845,0.0000670166,0.00009854267,0.00006241904,0.0001819759],"category_scores_gemma":[0.00002911697,0.0001460991,0.0000677799,0.0002223654,0.00004216963,0.0001250416,0.00000509342,0.0001685276,0.0005735838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009654616,"about_ca_system_score_gemma":0.00002804361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001904041,"about_ca_topic_score_gemma":0.000002372092,"domain_scores_codex":[0.9990093,0.00005875116,0.0002130276,0.0001394363,0.0001929336,0.0003865451],"domain_scores_gemma":[0.9995168,0.0001004076,0.00003680132,0.0001923981,0.0000449287,0.0001086604],"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":[0.00054208,0.001107585,0.002540523,0.004321344,0.0002611371,0.000344338,0.006462189,0.03296711,0.3999118,0.0002674531,0.06426711,0.4870074],"study_design_scores_gemma":[0.001136502,0.00007862677,0.0007685366,0.001015052,0.0001245162,0.000140657,0.001070467,0.9113111,0.08139268,0.00002231618,0.002072931,0.000866613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9190776,0.00008145731,0.001489991,0.0004343483,0.001107242,0.0004273455,0.00006707179,0.001502419,0.07581252],"genre_scores_gemma":[0.9983422,0.00000164972,0.0003678943,0.000112919,0.0007300213,0.00002976521,0.00002418329,0.00005261528,0.0003387556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.878344,"threshold_uncertainty_score":0.7372451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01409612854915936,"score_gpt":0.2289230094126267,"score_spread":0.2148268808634673,"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."}}