{"id":"W3119170582","doi":"10.1109/wacv48630.2021.00130","title":"Benchmark for Evaluating Pedestrian Action Prediction","year":2021,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; NCR","keywords":"Benchmark (surveying); Pedestrian; Computer science; Baseline (sea); Code (set theory); Machine learning; Action (physics); Rank (graph theory); Pedestrian detection; Artificial intelligence; Data mining; 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":[0.00020895,0.0000511293,0.00005290209,0.00004303985,0.0001780672,0.0001405881,0.0000795316,0.00003734718,0.0002388228],"category_scores_gemma":[0.00008263425,0.00005116695,0.00005170024,0.000151244,0.000004452389,0.0005404485,0.00002670291,0.0000465331,0.00004030782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003019492,"about_ca_system_score_gemma":0.00007710106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004471733,"about_ca_topic_score_gemma":0.00001641453,"domain_scores_codex":[0.9993674,0.00003791168,0.0001311236,0.0002171331,0.0001366599,0.0001097871],"domain_scores_gemma":[0.9995146,0.00006935623,0.00004407361,0.0001537333,0.0001810197,0.00003717487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001052795,0.0001186929,0.000280354,0.00005059315,0.00003032743,0.000003318276,0.0002641025,0.0001322527,0.03689021,0.01656826,0.0113743,0.9342771],"study_design_scores_gemma":[0.001999902,0.000497547,0.008993842,0.00005906024,0.00004770778,0.0001046079,0.0004369132,0.6658964,0.2201658,0.04744234,0.05396674,0.0003891538],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0457533,0.0000181757,0.9409824,0.0006704079,0.0008249074,0.0001429485,0.000003580419,0.0001904772,0.01141379],"genre_scores_gemma":[0.8888843,0.00002647902,0.1043288,0.0006235449,0.0004992459,0.00009348284,0.0001088359,0.000008482606,0.005426863],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9338879,"threshold_uncertainty_score":0.2614942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1378911262732665,"score_gpt":0.3712976924771637,"score_spread":0.2334065662038972,"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."}}