{"id":"W1577275996","doi":"10.1109/mva.2015.7153256","title":"Towards 3D human posture estimation using multiple kinects despite self-contacts","year":2015,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Computer vision; Artificial intelligence; Optical flow; Motion capture; Fuse (electrical); Vertex (graph theory); Geodesic; Pose; Point cloud; RGB color model; Graph; Motion (physics); Image (mathematics); Mathematics; Theoretical computer science","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":[0.000191848,0.0001198243,0.0001088615,0.0001248726,0.0001576594,0.0002386414,0.0002311339,0.00006987506,0.00002814823],"category_scores_gemma":[0.00006629016,0.0001077449,0.00003718207,0.0002048161,0.00000892199,0.001085157,0.00008691996,0.00009507925,0.0001453867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001471,"about_ca_system_score_gemma":0.00008317739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001804362,"about_ca_topic_score_gemma":0.00005773623,"domain_scores_codex":[0.9990868,0.00004791093,0.000168336,0.0002551831,0.0002491088,0.0001926457],"domain_scores_gemma":[0.9993195,0.0000270506,0.00008084233,0.000243851,0.0001835013,0.0001452791],"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":[0.00007797325,0.002319814,0.008918853,0.0002632826,0.0003653569,0.0003340976,0.02807387,0.01657945,0.1106205,0.07700004,0.02790239,0.7275444],"study_design_scores_gemma":[0.001223008,0.0001973418,0.004748712,0.00003980836,0.0000213072,0.00006482147,0.00006318116,0.9657773,0.01940593,0.004482989,0.003592351,0.0003831933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4193084,0.00001378253,0.5725641,0.0002244406,0.0003165261,0.0001567175,9.178451e-7,0.000492534,0.006922554],"genre_scores_gemma":[0.823514,5.804935e-7,0.1756446,0.0006070177,0.00009351825,0.000004004198,0.00001050817,0.000007282646,0.0001184933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9491979,"threshold_uncertainty_score":0.4393708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05555886466667564,"score_gpt":0.2952513587621294,"score_spread":0.2396924940954537,"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."}}