{"id":"W4306729986","doi":"10.1109/tpami.2022.3215307","title":"Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital","funders":"Innosuisse - Schweizerische Agentur für Innovationsförderung","keywords":"Artificial intelligence; Computer science; ENCODE; Leverage (statistics); Pose; Monocular; Pattern recognition (psychology); Feature learning; Feature extraction; Invariant (physics); Computer vision; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003001915,0.0001592025,0.0002061723,0.0006313396,0.00102802,0.0001537363,0.00022384,0.00003304585,0.0003015946],"category_scores_gemma":[0.00000715263,0.0001640414,0.0002274934,0.0006996318,0.00002221401,0.0002853429,0.000006530191,0.0003020407,0.00001683287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006392299,"about_ca_system_score_gemma":0.00001176892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005126843,"about_ca_topic_score_gemma":0.0001494029,"domain_scores_codex":[0.9985266,0.0001653631,0.0003382545,0.0005022229,0.0003022486,0.0001652634],"domain_scores_gemma":[0.9992674,0.0001492979,0.000163312,0.0002888304,0.00006200515,0.00006914473],"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":[0.00001455393,0.0001628739,0.0002082536,0.000008021762,0.0001711453,0.000003940005,0.0003424589,0.2879733,0.0003870031,0.00008716046,0.00001352439,0.7106278],"study_design_scores_gemma":[0.0001637281,0.0004769203,0.0003276237,0.000008913007,0.0002224141,0.000006406015,0.0001018066,0.9542435,0.04307853,0.0008948729,0.0002674347,0.000207863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01655393,0.00001391919,0.9825156,0.0002800439,0.0001903216,0.0002425131,0.00002861341,0.0001117716,0.00006324103],"genre_scores_gemma":[0.9950448,0.00002098944,0.003927678,0.0003530773,0.0000219527,0.0001742885,0.00007576722,0.00001154722,0.0003698666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.978588,"threshold_uncertainty_score":0.7906806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03403468356699616,"score_gpt":0.3093340023542688,"score_spread":0.2752993187872727,"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."}}