{"id":"W3110317294","doi":"10.1109/iv51971.2022.9827055","title":"Multi-Modal Hybrid Architecture for Pedestrian Action Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Intelligent Vehicles Symposium (IV)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Huawei Technologies (Canada)","funders":"","keywords":"Pedestrian; Computer science; Modal; Artificial intelligence; Pedestrian detection; Feed forward; Architecture; Range (aeronautics); Machine learning; Pedestrian crossing; Engineering; Transport engineering; Control engineering","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":[0.0004499892,0.0009014536,0.0006352669,0.0005441946,0.0003086201,0.0004159457,0.001317728,0.0008099928,0.001774139],"category_scores_gemma":[0.0006514526,0.0003479638,0.0006095178,0.0004601947,0.0002659543,0.0007685393,0.00067903,0.001084879,0.0007531562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005736172,"about_ca_system_score_gemma":0.0005879807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01260194,"about_ca_topic_score_gemma":0.01799008,"domain_scores_codex":[0.9998139,0.00002395629,0.000007843732,0.00007812509,0.00003916313,0.00003695651],"domain_scores_gemma":[0.9997371,0.00006036287,0.00002780941,0.0000292286,0.0001195722,0.0000259914],"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":[0.0003135122,0.0003525341,0.004798935,0.00006913951,0.0001274605,0.0001611482,0.0000789903,0.7243293,0.01223696,0.001914744,0.004702879,0.2509145],"study_design_scores_gemma":[0.00000127801,0.00001736556,0.0002306031,0.000002019386,0.000006013773,0.000008326929,0.00000281682,0.9988177,0.0004543196,0.0003374515,0.0001186069,0.000003444874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1247056,0.00127369,0.8631103,0.0004355006,0.0002411852,0.00006040278,0.000470676,0.005197866,0.0045047],"genre_scores_gemma":[0.9357979,0.0002799235,0.05812511,0.0002002615,0.00006887897,0.00007150173,0.0006422692,0.00005448214,0.004759696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01260194,"threshold_uncertainty_score":0.0250572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02033659369225852,"score_gpt":0.2409992678532265,"score_spread":0.220662674160968,"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."}}