{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008552134,0.0004979339,0.0005297375,0.0007400931,0.0002166899,0.0007543148,0.00167921,0.0003358597,0.00003232081],"category_scores_gemma":[0.00002152116,0.0004825764,0.00009256436,0.000818987,0.0003502307,0.001315938,0.000780325,0.001090948,0.00002529558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002167841,"about_ca_system_score_gemma":0.0002925505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003292442,"about_ca_topic_score_gemma":0.00034416,"domain_scores_codex":[0.9961779,0.0001504452,0.0006933312,0.001761003,0.0005842656,0.0006330219],"domain_scores_gemma":[0.9983773,0.0001987486,0.0001172759,0.001017721,0.0001371851,0.0001518208],"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":[0.0000701035,0.0003788217,0.0139154,0.0005743286,0.00003323702,0.00006788527,0.01982071,0.1871643,0.04468952,0.0004309916,0.000009952427,0.7328447],"study_design_scores_gemma":[0.000787423,0.0001481476,0.02340413,0.0005094158,0.000006799996,0.00001387785,0.000002023126,0.9290051,0.02745419,0.01806135,0.000008660166,0.0005989022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.481833,0.00005829092,0.5163211,0.0002632518,0.001010074,0.000429381,0.0000092005,0.00006386349,0.00001178672],"genre_scores_gemma":[0.9056714,0.00005432645,0.09337549,0.0006662283,0.0001421892,0.0000402424,0.00003117439,0.00001740955,0.000001536642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7418408,"threshold_uncertainty_score":0.9997626,"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."}}