{"id":"W4366959057","doi":"10.1109/cbase57816.2022.00022","title":"Attention-aware CNN model for Traffic Signs Classification","year":2022,"lang":"en","type":"article","venue":"","topic":"Vehicle License Plate Recognition","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Bottleneck; Computer science; Benchmark (surveying); Artificial intelligence; Traffic sign recognition; Traffic sign; Machine learning; Residual neural network; Sign (mathematics); Deep learning; Embedded system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000186109,0.0009824065,0.0004038729,0.0005647393,0.0001845998,0.0004367705,0.001064231,0.0005504518,0.00321029],"category_scores_gemma":[0.0004170762,0.0002364471,0.0005476641,0.0004443963,0.0001812803,0.0007145798,0.0003557417,0.0008947959,0.001310487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008244173,"about_ca_system_score_gemma":0.000819927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02852493,"about_ca_topic_score_gemma":0.03180452,"domain_scores_codex":[0.999896,0.000007694832,0.000004339991,0.00003176161,0.00002127689,0.00003886299],"domain_scores_gemma":[0.9999036,0.00001485096,0.000010368,0.00001237818,0.00004981415,0.000008986386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004892285,0.0003433618,0.006516431,0.0001969246,0.0002219889,0.0002912666,0.0000601434,0.4680745,0.03121095,0.004118919,0.02138184,0.4670944],"study_design_scores_gemma":[0.000005581111,0.00004567209,0.001248898,0.00001131763,0.00003551874,0.00003528067,0.000008377426,0.9923288,0.004247771,0.0007349531,0.001291303,0.000006504744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5194808,0.006983859,0.4208781,0.001542988,0.001169687,0.0002110798,0.003675769,0.01079958,0.03525814],"genre_scores_gemma":[0.9529166,0.0009717291,0.0231149,0.000255304,0.0001403015,0.00006663312,0.00310215,0.0001039541,0.01932839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02852493,"threshold_uncertainty_score":0.05671781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04300470580394554,"score_gpt":0.2334726023507639,"score_spread":0.1904678965468184,"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."}}