{"id":"W3112503563","doi":"10.1109/tvt.2020.3043203","title":"Accurate Image-Based Pedestrian Detection With Privacy Preservation","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Encryption; Pedestrian detection; Computer science; Support vector machine; Histogram; Pedestrian; Kernel (algebra); Overhead (engineering); Feature extraction; Block (permutation group theory); Artificial intelligence; Computer vision; Homomorphic encryption; Pattern recognition (psychology); Image (mathematics); Mathematics; Engineering; Computer network","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":[0.0001147397,0.0001584925,0.0001525801,0.0006584231,0.0002433142,0.0001361243,0.0007137419,0.0002161333,0.00002225865],"category_scores_gemma":[0.000030693,0.0001464504,0.00006780415,0.003853973,0.0001038579,0.0005438694,0.000004402027,0.0004050203,0.0001145003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006332891,"about_ca_system_score_gemma":0.00008982888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002179227,"about_ca_topic_score_gemma":0.00002195634,"domain_scores_codex":[0.9987051,0.00006454377,0.0002288501,0.0005061806,0.0002736021,0.0002217492],"domain_scores_gemma":[0.9989488,0.00003799241,0.0001133762,0.0006180361,0.0001883708,0.00009339649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004598684,0.001645557,0.0002111019,0.0002460536,0.0003141258,0.0001735948,0.001078531,0.03047537,0.357913,0.005076641,0.000453767,0.6019524],"study_design_scores_gemma":[0.001044074,0.0005172929,0.0003029437,0.00001230167,0.0000258861,0.00001914738,0.00002691571,0.3842358,0.6046478,0.000331569,0.008575764,0.0002605102],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04366254,0.0000190541,0.9392305,0.01557039,0.0001574278,0.0003141922,0.000005198395,0.001009322,0.00003135116],"genre_scores_gemma":[0.9784272,0.000009833233,0.02090267,0.0005174749,0.00001434412,0.00008332049,0.000002834012,0.00001304425,0.00002923462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9347647,"threshold_uncertainty_score":0.5972076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02452370497894603,"score_gpt":0.2403449485072491,"score_spread":0.2158212435283031,"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."}}