{"id":"W1816678934","doi":"10.48550/arxiv.1312.7302","title":"Learning Human Pose Estimation Features with Convolutional Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Pose; Artificial intelligence; Estimation; Convolutional neural network; Computer science; Machine learning; Pattern recognition (psychology); Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0001117604,0.0002338867,0.0001904393,0.0002161426,0.0004083856,0.0002543459,0.000584341,0.0002362866,0.0001239123],"category_scores_gemma":[0.000009171479,0.0002448471,0.0000992231,0.0002408051,0.00008630643,0.0006132135,0.0004578819,0.0008124826,0.0001369524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001343641,"about_ca_system_score_gemma":0.00008306257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001246649,"about_ca_topic_score_gemma":0.00002862661,"domain_scores_codex":[0.9987313,0.0001206488,0.0001297076,0.0006784758,0.00009247236,0.0002474148],"domain_scores_gemma":[0.9989698,0.00005258245,0.0002541926,0.000401935,0.0002077696,0.000113711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001000892,0.00004966378,0.0007434086,0.00002412727,0.00006509774,0.00005851239,0.0001027084,0.904368,0.00002158454,0.09210004,0.0008133714,0.001643496],"study_design_scores_gemma":[0.0003819708,0.0001050421,0.006487051,0.0001212845,0.00004656558,0.0000150185,0.00003529079,0.9667898,0.00004526056,0.02543499,0.0001581492,0.000379572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2643567,0.00002330754,0.7317113,0.00004312137,0.0002575927,0.0002070302,0.000002206729,0.0003157257,0.003083043],"genre_scores_gemma":[0.9934371,0.00002797222,0.001834319,0.00007711395,0.0001441356,0.000002144807,0.0001195557,0.00001338695,0.004344257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7298769,"threshold_uncertainty_score":0.9984575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03874054701273302,"score_gpt":0.1792084070712257,"score_spread":0.1404678600584927,"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."}}