{"id":"W3111248667","doi":"10.1109/tits.2020.3041278","title":"SA-YOLOv3: An Efficient and Accurate Object Detector Using Self-Attention Mechanism for Autonomous Driving","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Beijing Municipal Natural Science Foundation; China Postdoctoral Science Foundation; Beihang University; National Natural Science Foundation of China","keywords":"Detector; Object detection; Inference; Object (grammar); Computer science; Convolution (computer science); Artificial intelligence; Computer vision; Notation; Function (biology); Deep learning; Pattern recognition (psychology); Artificial neural network; Mathematics; Arithmetic","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":[0.0005827351,0.0006504479,0.0007408084,0.0006877896,0.0003177217,0.0006808051,0.002194784,0.0008099168,0.002175556],"category_scores_gemma":[0.000898735,0.0003714687,0.0006304003,0.0004777129,0.000324785,0.001141315,0.0007916586,0.0006750341,0.0009969273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007130227,"about_ca_system_score_gemma":0.00148682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007803042,"about_ca_topic_score_gemma":0.01201538,"domain_scores_codex":[0.9997175,0.0000186797,0.00001306558,0.0000790475,0.000120478,0.00005110958],"domain_scores_gemma":[0.9996246,0.00006547663,0.00003287696,0.00006867416,0.000171692,0.00003656521],"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":[0.0005960259,0.0001707548,0.003509539,0.0002435441,0.0001834498,0.0001420275,0.00008918209,0.04716426,0.1731884,0.003724654,0.01134187,0.7596462],"study_design_scores_gemma":[0.00003753147,0.0003002502,0.002595526,0.0000154683,0.0000720542,0.0002434623,0.00002156121,0.8919886,0.09365422,0.001495993,0.009528891,0.0000464055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05751515,0.00109175,0.9253635,0.000109277,0.0001546218,0.0001166842,0.0002708144,0.01241158,0.002966582],"genre_scores_gemma":[0.4139261,0.0004904022,0.5765352,0.0003214214,0.00005533539,0.0001145316,0.001338973,0.0004118692,0.006806155],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007803042,"threshold_uncertainty_score":0.01551527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0413205380829545,"score_gpt":0.2817225926846917,"score_spread":0.2404020546017372,"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."}}