{"id":"W2965110031","doi":"10.1109/crv.2019.00030","title":"Traffic Risk Assessment: A Two-Stream Approach Using Dynamic-Attention","year":2019,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Focus (optics); Convolutional neural network; Categorical variable; Artificial intelligence; Recurrent neural network; Frame (networking); Object detection; Implementation; Object (grammar); Frame rate; Sequence (biology); Computer vision; Artificial neural network; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007442747,0.001357722,0.0009867201,0.001941532,0.000390156,0.001444353,0.001984803,0.001141155,0.001971652],"category_scores_gemma":[0.00176278,0.0005204082,0.0008606661,0.0009266311,0.0003910981,0.001895342,0.001257593,0.001217496,0.0005416777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001413961,"about_ca_system_score_gemma":0.0009967767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01666858,"about_ca_topic_score_gemma":0.01553149,"domain_scores_codex":[0.9994167,0.00008430728,0.00002230667,0.0002006389,0.0001829118,0.00009324848],"domain_scores_gemma":[0.9993514,0.0001726158,0.00006508325,0.00005835716,0.0002813253,0.00007131464],"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":[0.0005518603,0.0006693766,0.00815702,0.0001825642,0.0002416192,0.0006684496,0.0002795984,0.3870364,0.02312307,0.008824184,0.00579716,0.5644686],"study_design_scores_gemma":[0.000005040522,0.000044395,0.000724706,0.000006435156,0.0000208693,0.00004743853,0.0000252835,0.9943807,0.002083281,0.002076438,0.0005747754,0.00001062133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05557826,0.0007796672,0.9361975,0.0006079524,0.0001474984,0.000161936,0.0002511669,0.001911471,0.004364398],"genre_scores_gemma":[0.7790325,0.0006407281,0.2128715,0.0002508269,0.0002196562,0.0001327524,0.0006618255,0.0001504498,0.006039775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01666858,"threshold_uncertainty_score":0.0331431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009792322182666246,"score_gpt":0.2791888751739031,"score_spread":0.2693965529912369,"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."}}