{"id":"W2968524820","doi":"10.1109/icra.2019.8794278","title":"Classifying Pedestrian Actions In Advance Using Predicted Video Of Urban Driving Scenes","year":2019,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Pedestrian; Computer science; Encoder; Artificial intelligence; Ground truth; Sequence (biology); Computer vision; Key (lock); Pedestrian crossing; Pattern recognition (psychology); Computer security; Transport engineering; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005257493,0.0001112506,0.0002283917,0.0002112209,0.00005491262,0.00005731721,0.0004232727,0.00006049123,0.00002054993],"category_scores_gemma":[0.0001350846,0.0001059708,0.00005650656,0.0007804716,0.0000263395,0.0008048348,0.0001286408,0.0001464467,0.000006416215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005126573,"about_ca_system_score_gemma":0.0001030741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001374293,"about_ca_topic_score_gemma":0.0001258431,"domain_scores_codex":[0.9987492,0.0001442078,0.0003148919,0.0003300856,0.0001995719,0.0002620692],"domain_scores_gemma":[0.9989585,0.0002940384,0.0001344239,0.0004963248,0.00006694726,0.0000497598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004530993,0.00003477691,0.9541922,0.0000422852,0.000009907621,0.000003708321,0.0002981957,0.003057285,0.02326937,0.003515896,0.00001522844,0.01555659],"study_design_scores_gemma":[0.0008794861,0.00007799581,0.6293466,0.0003421454,0.000005684236,0.00001830501,0.0001496301,0.3495176,0.01678971,0.001229326,0.00130592,0.0003376325],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5393758,0.00006032553,0.4579192,0.0000858421,0.0003974258,0.0001145157,6.547246e-7,0.00009792828,0.00194827],"genre_scores_gemma":[0.8191484,0.00001308463,0.1806555,0.00003088247,0.00003231246,0.000002369075,5.486286e-7,0.000007423193,0.0001095059],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3464603,"threshold_uncertainty_score":0.4321366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0494333084436518,"score_gpt":0.3272837222633687,"score_spread":0.2778504138197169,"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."}}