{"id":"W3205492849","doi":"10.1109/icra48506.2021.9561107","title":"Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction","year":2021,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Pedestrian; Computer science; Weighting; Cluster analysis; Minimum bounding box; Graph; Bounding overwatch; Benchmark (surveying); Data mining; Machine learning; Artificial intelligence; Theoretical computer science; Transport engineering; Geography","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":[0.0000987195,0.0001251962,0.0001263301,0.0001553671,0.0001186971,0.00002223707,0.00005200109,0.000213904,0.00005640459],"category_scores_gemma":[0.00001154768,0.000139285,0.0001046614,0.0002357383,0.00002069972,0.000228523,0.000006799187,0.0002053802,0.000007773448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000780897,"about_ca_system_score_gemma":0.00003571868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002888029,"about_ca_topic_score_gemma":0.0001319138,"domain_scores_codex":[0.9993116,0.00001522572,0.0002308673,0.0001941415,0.00006927919,0.0001788933],"domain_scores_gemma":[0.9996356,0.00004672829,0.00003558611,0.0001791726,0.00006526397,0.00003758909],"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":[0.00006083658,0.00005230937,0.001041814,0.0000971652,0.00006566236,0.000003155253,0.00005020881,0.9753348,0.00360308,0.001401408,0.0005841872,0.01770534],"study_design_scores_gemma":[0.0005095175,0.00004615716,0.0002515621,0.00002012685,0.00002782197,0.000006877314,0.000126744,0.93792,0.05461049,0.002935796,0.003413161,0.0001317496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1717966,0.00005876517,0.8251924,0.0002061189,0.0005186835,0.0001690972,0.00001670221,0.001156005,0.0008855611],"genre_scores_gemma":[0.9884053,0.00006215044,0.01106495,0.00003454826,0.00007923634,0.00006388516,0.000158045,0.00002615943,0.0001056537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8166087,"threshold_uncertainty_score":0.5679877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03743080217815473,"score_gpt":0.2484994538221879,"score_spread":0.2110686516440331,"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."}}