{"id":"W7085121138","doi":"10.1109/raiic65850.2025.11170191","title":"Application of Vision-Language Models to Pedestrian Behavior Prediction and Scene Understanding in Autonomous Driving","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pedestrian; Metric (unit); Perception; Trajectory; Key (lock); Advanced driver assistance systems","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":[0.0002237423,0.00007306748,0.0001031826,0.000300045,0.00007154846,0.00005384142,0.0002534208,0.00004377293,0.000001784911],"category_scores_gemma":[0.00001981209,0.00007595363,0.00001521374,0.0005800503,0.0000178339,0.0002211714,0.0001767797,0.00009017957,0.000001919407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001396691,"about_ca_system_score_gemma":0.00003877494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001574538,"about_ca_topic_score_gemma":0.0002315952,"domain_scores_codex":[0.9992209,0.00002931936,0.0002233265,0.0003087806,0.0001022684,0.0001154269],"domain_scores_gemma":[0.999451,0.00007924294,0.00005125181,0.0003477169,0.00002244544,0.00004831208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007923109,0.0002851569,0.1688531,0.00005518149,0.000009813358,0.00000140244,0.003744713,0.05514231,0.03190983,0.4938728,0.00003885857,0.2460789],"study_design_scores_gemma":[0.00016859,0.00002065738,0.1891996,0.00002440214,0.000003873872,8.784524e-7,0.0001339875,0.8068459,0.0002967707,0.003248497,0.000006784013,0.0000500536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2513401,0.00001348124,0.7462702,0.0006478979,0.00002132562,0.0003594122,0.000001119243,0.00009777031,0.001248733],"genre_scores_gemma":[0.9386209,0.000002184939,0.06116504,0.00004588399,0.000005691689,0.0001069111,0.000002627775,0.000004040146,0.00004677623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7517036,"threshold_uncertainty_score":0.3097299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01962526538052656,"score_gpt":0.3073331807172857,"score_spread":0.2877079153367591,"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."}}