{"id":"W4210638231","doi":"10.1109/jac-ecc54461.2021.9691441","title":"Vulnerable Road Users Detection and Tracking using YOLOv4 and Deep SORT","year":2021,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Motors (Canada)","funders":"","keywords":"sort; Computer science; Artificial intelligence; Tracking (education); Object detection; Computer vision; Video tracking; Metric (unit); Vehicle tracking system; Frame (networking); Data association; Object (grammar); Real-time computing; Kalman filter; Pattern recognition (psychology); Engineering; Filter (signal processing)","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":[0.0006261897,0.00009208544,0.0001324822,0.00005273873,0.000251891,0.0002964124,0.00008917052,0.0000534713,0.000009708987],"category_scores_gemma":[0.0000964935,0.00008762757,0.00002395443,0.0002548816,0.00002714404,0.0005536408,0.0001071922,0.0001289786,0.000001512406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001566568,"about_ca_system_score_gemma":0.00002916497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001282687,"about_ca_topic_score_gemma":0.0002664188,"domain_scores_codex":[0.9990442,0.00017231,0.0001294215,0.000347666,0.0001116236,0.0001947345],"domain_scores_gemma":[0.9995071,0.0001078054,0.00003665319,0.0002187043,0.00006581697,0.00006396767],"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":[0.000003161476,0.00001679976,0.02149326,0.00002155556,0.00002170397,0.00004811694,0.0004989046,0.0004044864,0.03631683,0.0009847701,0.000003015571,0.9401874],"study_design_scores_gemma":[0.0007546335,0.00006978792,0.184052,0.00004360238,0.0000215676,0.0008343006,0.0003368929,0.6670668,0.1394403,0.005252266,0.001599195,0.0005287015],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4155352,0.0004683953,0.5830581,0.00009037693,0.0001690487,0.00002676557,1.089791e-7,0.00006664775,0.0005853434],"genre_scores_gemma":[0.8507794,0.00006133765,0.1488537,0.0001806064,0.00003684793,0.000001260407,2.2706e-7,0.000005745706,0.00008090972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9396587,"threshold_uncertainty_score":0.3573349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03827536714772253,"score_gpt":0.2959038236622865,"score_spread":0.257628456514564,"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."}}