{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003669201,0.001159602,0.001596814,0.001028382,0.0007442517,0.001418006,0.002543844,0.00211938,0.003557749],"category_scores_gemma":[0.01689242,0.001785492,0.001457653,0.000974787,0.002115954,0.003767639,0.002794309,0.003941792,0.001267742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001526987,"about_ca_system_score_gemma":0.00132438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005070322,"about_ca_topic_score_gemma":0.007416029,"domain_scores_codex":[0.9986468,0.0004822445,0.00005665096,0.0004345645,0.0002599163,0.0001198031],"domain_scores_gemma":[0.9952843,0.003115659,0.0003087176,0.0007914603,0.000337971,0.0001618445],"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":[0.0001503364,0.0000778728,0.001186349,0.00009142169,0.00005540492,0.00008262807,0.0001149836,0.8976348,0.003009498,0.0349791,0.002594095,0.06002347],"study_design_scores_gemma":[0.00001424411,0.00001859412,0.0003100694,0.00001828214,0.000005193616,0.00001902246,0.000007823548,0.9666698,0.0009346298,0.03140636,0.0005868093,0.000009170377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008912021,0.0001229526,0.9894744,0.000237082,0.00002165063,0.00003294929,0.000134683,0.0004130471,0.0006513052],"genre_scores_gemma":[0.6249916,0.0005648662,0.3651016,0.000573996,0.0001746549,0.0007538617,0.002074953,0.0004295162,0.005334947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005070322,"threshold_uncertainty_score":0.01940483,"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."}}