{"id":"W2612163384","doi":"10.1109/cvpr.2017.138","title":"Harvesting Multiple Views for Marker-Less 3D Human Pose Annotations","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Pose; Artificial intelligence; Discriminative model; Bottleneck; Computer vision; Machine learning; 3D pose estimation; Pattern recognition (psychology)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004394107,0.0002448103,0.0002848051,0.0001695682,0.0009868504,0.001239913,0.001144585,0.0001842675,0.00006250091],"category_scores_gemma":[0.0001882594,0.0002402828,0.0002006396,0.0000438462,0.00004165673,0.0006062351,0.0007271619,0.0003162232,0.00008954357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004579422,"about_ca_system_score_gemma":0.0001030045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002060207,"about_ca_topic_score_gemma":0.0006391407,"domain_scores_codex":[0.9983951,0.00006810046,0.0004019151,0.0006770726,0.000182511,0.0002753316],"domain_scores_gemma":[0.9979149,0.0001756693,0.0004692233,0.001044824,0.0002937993,0.0001015627],"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":[0.0000135397,0.0004639146,0.001238595,0.0008489765,0.0001956062,0.00002099796,0.001653031,0.0005068488,0.002761452,0.02343775,0.04889412,0.9199651],"study_design_scores_gemma":[0.002940992,0.00021911,0.02473842,0.001473838,0.0001662526,0.00003727555,0.0001850252,0.59412,0.005558041,0.1186305,0.2490429,0.002887628],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01529359,0.00004883979,0.9418414,0.0006069373,0.001778149,0.001080534,0.00007408894,0.0004477535,0.03882869],"genre_scores_gemma":[0.488786,0.00003427179,0.4673809,0.0009238386,0.001457009,0.001045548,0.0007116944,0.00006369261,0.03959704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9170775,"threshold_uncertainty_score":0.9997969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1664153895093603,"score_gpt":0.3597363425397964,"score_spread":0.1933209530304361,"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."}}