{"id":"W1559083155","doi":"10.1007/978-3-540-88690-7_53","title":"Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Discriminative model; Tree (set theory); Artificial intelligence; Inference; Machine learning; Boosting (machine learning); Tree structure; Pose; Tree traversal; Pattern recognition (psychology); Data mining; Binary tree; Algorithm; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000371209,0.0003092845,0.0003306534,0.000764982,0.0003405221,0.0002339656,0.0006877762,0.0002389817,0.00000815904],"category_scores_gemma":[0.00005064832,0.00030817,0.00006737577,0.0001817881,0.0004991236,0.0007548846,0.000380802,0.0003497007,0.000004846384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001572224,"about_ca_system_score_gemma":0.0001836307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006630903,"about_ca_topic_score_gemma":0.0005769772,"domain_scores_codex":[0.9978299,0.00002238797,0.0004196473,0.0009538617,0.0004207391,0.0003534716],"domain_scores_gemma":[0.998854,0.0003097754,0.0001993823,0.0003993151,0.0001397764,0.00009774845],"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":[0.000006811681,0.00003146716,0.00002385039,0.0000268216,0.000002888245,0.00003613967,0.0008661199,0.03231185,0.0002951841,0.002121779,0.0000150847,0.964262],"study_design_scores_gemma":[0.0006058257,0.0001275108,0.0002069176,0.0002250488,0.000002867867,0.00007451652,1.333487e-7,0.8677981,0.0009440701,0.1296598,0.00004894074,0.0003062073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001648324,0.00006979197,0.9959822,0.0001738424,0.0005210851,0.0005954566,0.000009900243,0.0000782944,0.0009211026],"genre_scores_gemma":[0.8014848,0.00003268531,0.1978076,0.0003882803,0.000183384,0.00001208426,0.00002344196,0.00001613871,0.00005156384],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9639558,"threshold_uncertainty_score":0.9999371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02743791766359206,"score_gpt":0.2585265673797306,"score_spread":0.2310886497161386,"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."}}