{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003833925,0.0003385712,0.0003050287,0.0002972602,0.0006364972,0.00003657398,0.0004662389,0.0001696358,0.0002108002],"category_scores_gemma":[0.00001527558,0.0003896034,0.0002453813,0.0002699807,0.00008243768,0.0001299992,0.0001133739,0.0009426784,0.00004850996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005449532,"about_ca_system_score_gemma":0.00005296065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003370324,"about_ca_topic_score_gemma":0.00005120492,"domain_scores_codex":[0.9980558,0.00008707658,0.0005128648,0.0004928354,0.0002919468,0.0005595089],"domain_scores_gemma":[0.9991832,0.0001118521,0.00009810333,0.0004516132,0.00004122818,0.0001140146],"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":[0.0003765805,0.0002771997,0.001083886,0.0001810287,0.0002589041,0.00002529867,0.0008886742,0.6301566,0.3167995,0.0002094417,0.006265547,0.04347735],"study_design_scores_gemma":[0.001108739,0.0006303445,0.0005383128,0.00001831534,0.0001197029,0.000208356,0.000683015,0.6371849,0.2154696,0.0009596029,0.1424157,0.0006635007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7855868,0.0004992789,0.2040712,0.0009086808,0.00389295,0.001405929,0.0007608587,0.002474642,0.0003996778],"genre_scores_gemma":[0.9962543,0.0002650436,0.001109489,0.0001206344,0.000325982,0.0007865934,0.0002048282,0.0001094271,0.0008236598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2106675,"threshold_uncertainty_score":0.9998556,"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."}}