{"id":"W2925058582","doi":"10.1007/978-3-030-27272-2_19","title":"KPTransfer: Improved Performance and Faster Convergence from Keypoint Subset-Wise Domain Transfer in Human Pose Estimation","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Computer science; Convergence (economics); Domain (mathematical analysis); Set (abstract data type); Artificial intelligence; Pattern recognition (psychology); Joint (building); Task (project management); Transfer of learning; Pose; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001500811,0.001528977,0.001170532,0.0008203103,0.0004535103,0.0008845192,0.001376702,0.001442734,0.009586453],"category_scores_gemma":[0.005177198,0.0004879827,0.0004857664,0.0009527194,0.0005727327,0.002273641,0.003020631,0.00145932,0.006132471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002564403,"about_ca_system_score_gemma":0.0007400771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002524083,"about_ca_topic_score_gemma":0.001814601,"domain_scores_codex":[0.9990633,0.0002233881,0.0000460977,0.0002416996,0.0002997394,0.0001257588],"domain_scores_gemma":[0.9988224,0.000447196,0.0000433578,0.0003791429,0.0002496169,0.00005828746],"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":[0.00122937,0.0002120649,0.000865942,0.0002080947,0.00009057097,0.0001683574,0.0001237989,0.03937561,0.0586995,0.002712923,0.006733331,0.8895804],"study_design_scores_gemma":[0.0001101824,0.000401362,0.001919701,0.00002486282,0.00004278901,0.0005360754,0.0001238597,0.8896336,0.09668551,0.005962853,0.004510417,0.00004872883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05150561,0.0005127318,0.9339288,0.0001721269,0.000236468,0.0001293887,0.0002750619,0.0104645,0.002775343],"genre_scores_gemma":[0.4964586,0.0003952799,0.4897734,0.0002089542,0.0001081002,0.0002265236,0.001290199,0.00117233,0.01036654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009586453,"threshold_uncertainty_score":0.03206986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01262125647384182,"score_gpt":0.2382733071163144,"score_spread":0.2256520506424726,"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."}}