{"id":"W2158638750","doi":"10.1109/cvpr.2005.132","title":"Discriminative Density Propagation for 3D Human Motion Estimation","year":2005,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":219,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Discriminative model; Artificial intelligence; Inference; Computer science; Generative model; Motion capture; Pattern recognition (psychology); Probabilistic logic; Bayesian inference; Conditional probability distribution; Belief propagation; Machine learning; Computer vision; Bayesian probability; Generative grammar; Motion (physics); Mathematics; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001739612,0.0008518087,0.0008553345,0.001613706,0.0004997723,0.0007643481,0.002154341,0.00129334,0.002151468],"category_scores_gemma":[0.008505945,0.001096956,0.0008984336,0.00149423,0.001112402,0.002174442,0.001349894,0.001738724,0.0009035734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238422,"about_ca_system_score_gemma":0.0009260018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01169944,"about_ca_topic_score_gemma":0.01093847,"domain_scores_codex":[0.9992486,0.0002038626,0.00003092488,0.0001791664,0.0002785233,0.00005884988],"domain_scores_gemma":[0.997945,0.001299412,0.0001629194,0.0002485879,0.0002809175,0.00006328954],"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":[0.00009606521,0.00007317656,0.00106887,0.00008165366,0.0000605532,0.00006743798,0.0001208486,0.7129055,0.004731366,0.04458673,0.001981732,0.234226],"study_design_scores_gemma":[0.000003743701,0.000005217773,0.0001073185,0.00000324777,0.000003243691,0.00001708256,0.000002499955,0.9881865,0.0006811362,0.01063422,0.0003500366,0.000005744769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008971019,0.00003106024,0.9987159,0.00001942453,0.000004028042,0.000007124031,0.0000140268,0.0002035911,0.0001077204],"genre_scores_gemma":[0.1903272,0.0003225434,0.8063256,0.0001213401,0.00006254661,0.0001702338,0.000391408,0.0002084319,0.002070688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01169944,"threshold_uncertainty_score":0.02326268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03055082250475222,"score_gpt":0.2931255146242817,"score_spread":0.2625746921195295,"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."}}