{"id":"W2107628931","doi":"10.1109/iccv.2005.193","title":"Priors for people tracking from small training sets","year":2005,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":255,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Embedding; Latent variable; Prior probability; Artificial intelligence; Computer science; Probabilistic logic; Gaussian process; Tracking (education); Probability density function; Training (meteorology); Pose; Machine learning; Gaussian; Process (computing); Space (punctuation); Latent variable model; Training set; Computer vision; Mathematics; Bayesian probability; Statistics; 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":[0.00009324501,0.000062101,0.00008126265,0.00004445759,0.0001047102,0.000134454,0.0001873586,0.00003249273,0.0001546099],"category_scores_gemma":[0.0000143137,0.00005825113,0.00005174707,0.00006906078,0.00000425384,0.0004097528,0.00002232755,0.00004655756,0.00009980371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001543468,"about_ca_system_score_gemma":0.00002341802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000233529,"about_ca_topic_score_gemma":0.0004630647,"domain_scores_codex":[0.9994542,0.00001068383,0.0001198446,0.0001952868,0.00006781593,0.0001521748],"domain_scores_gemma":[0.9996668,0.00009284399,0.00003699047,0.0001227187,0.0000340806,0.00004658209],"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":[0.000001529295,0.00002211401,0.00005072477,0.000002380989,0.000007010196,4.496835e-7,0.004553542,0.00003605427,0.0007186228,0.002504062,0.0005663789,0.9915372],"study_design_scores_gemma":[0.002973875,0.0002280805,0.01991593,0.00010246,0.00004037946,0.00002912925,0.002018456,0.685465,0.06827473,0.03819809,0.1816379,0.001115976],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2518708,0.00001109249,0.7428054,0.001194585,0.0001415629,0.0001024951,0.000003083721,0.0001807102,0.00369024],"genre_scores_gemma":[0.8105789,0.000002371456,0.1879684,0.0008472651,0.0001850771,0.00001386431,0.000009373759,0.000005018488,0.0003896994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9904212,"threshold_uncertainty_score":0.2375412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06987727110189179,"score_gpt":0.2761782726597773,"score_spread":0.2063010015578856,"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."}}