{"id":"W3022272795","doi":"10.48550/arxiv.2005.06582","title":"Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Anticipation (artificial intelligence); Computer science; Pedestrian; Artificial intelligence; Feature (linguistics); Action (physics); Machine learning; Event (particle physics); Trajectory; Point (geometry); Recurrent neural network; Sensor fusion; Motion (physics); Variable (mathematics); Computer vision; Artificial neural network; 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":[],"consensus_categories":[],"category_scores_codex":[0.00004655558,0.0001032951,0.0001242187,0.00009512271,0.00006696909,0.000007073338,0.0001082968,0.0001914103,0.00003069006],"category_scores_gemma":[0.0000159337,0.0001287724,0.00003510931,0.0004457718,0.00003684636,0.0002239822,0.00003249589,0.0002757693,0.00002759311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001293101,"about_ca_system_score_gemma":0.00001999436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003746372,"about_ca_topic_score_gemma":0.000132791,"domain_scores_codex":[0.9995023,0.00002679685,0.00008350882,0.0001954277,0.000024037,0.0001678987],"domain_scores_gemma":[0.9997684,0.00001659035,0.00003001087,0.0001113267,0.00001741775,0.00005619482],"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":[0.0002632395,0.00006177064,0.05033255,0.00009526517,0.00006083189,0.0003242785,0.001129874,0.8922331,0.04001904,0.01110583,0.0002469674,0.004127224],"study_design_scores_gemma":[0.0008040931,0.00004413971,0.01566944,0.00001557931,0.00002398648,0.000002364971,0.0006300338,0.9796876,0.002103478,0.0002707957,0.0005694004,0.0001790352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9606688,0.00001963477,0.03826515,0.0001060534,0.00008823569,0.0001048417,0.000004466918,0.0003529939,0.0003898392],"genre_scores_gemma":[0.9997199,0.00005485571,0.0000832122,0.00003850298,0.0000300797,1.266016e-7,0.000008795282,0.00001257698,0.00005191514],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08745452,"threshold_uncertainty_score":0.5251188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1101348896089561,"score_gpt":0.1957848292184561,"score_spread":0.08564993960950006,"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."}}