{"id":"W2398898231","doi":"10.1109/crv.2016.25","title":"Real-Time Human Motion Capture with Multiple Depth Cameras","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Artificial intelligence; Computer vision; Motion capture; Computer science; Segmentation; Motion (physics); Pose; Motion estimation; Synthetic data","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":[0.0001275586,0.0002776481,0.000248103,0.000169486,0.0001790623,0.0002536748,0.0005684479,0.0002453671,0.000392995],"category_scores_gemma":[0.000008043334,0.0001871451,0.00009622759,0.00008581472,0.00004724722,0.0003519619,0.0003838007,0.0003178477,0.000704482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009386699,"about_ca_system_score_gemma":0.00007815163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000521394,"about_ca_topic_score_gemma":0.0003148015,"domain_scores_codex":[0.9984083,0.00007886498,0.0002375913,0.0007053322,0.0003085003,0.0002614414],"domain_scores_gemma":[0.9986973,0.00004120741,0.0002122464,0.0007581995,0.0001767847,0.0001142356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001891788,0.002512449,0.02138088,0.001255507,0.001637697,0.0007052921,0.009376926,0.00152904,0.1801467,0.1244574,0.1822342,0.4745747],"study_design_scores_gemma":[0.01803341,0.001842387,0.2277713,0.006900486,0.0007259401,0.0007769315,0.0005049112,0.1634239,0.2220058,0.3080268,0.03297403,0.01701414],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09282336,0.00001275895,0.7418979,0.000902737,0.0004804461,0.0006227936,0.00002386537,0.001253298,0.1619828],"genre_scores_gemma":[0.9718404,0.00001889285,0.01446792,0.0001995599,0.0003258901,0.00006378285,0.0001144486,0.00002884353,0.01294019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8790171,"threshold_uncertainty_score":0.9054927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01821234853961206,"score_gpt":0.2489113589970887,"score_spread":0.2306990104574766,"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."}}