{"id":"W2612706635","doi":"10.1109/iccv.2017.288","title":"A Simple Yet Effective Baseline for 3d Human Pose Estimation","year":2017,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1491,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Nvidia","keywords":"Computer science; Pose; Artificial intelligence; Benchmark (surveying); Ground truth; Deep learning; Feed forward; Computer vision; Task (project management); Convolutional neural network; Baseline (sea); Outlier; 3D pose estimation; Pixel; Set (abstract data type); Word error rate; Surprise; Pattern recognition (psychology)","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":[0.001030733,0.003264765,0.001349145,0.001455265,0.0008305795,0.001797397,0.002055507,0.001993956,0.02541926],"category_scores_gemma":[0.004334065,0.0009089958,0.00122873,0.001084403,0.0008382853,0.002069747,0.003515679,0.002088521,0.02091479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008861801,"about_ca_system_score_gemma":0.00147662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007837751,"about_ca_topic_score_gemma":0.01494036,"domain_scores_codex":[0.9981799,0.0002013506,0.0000537142,0.000888858,0.0004847805,0.0001914675],"domain_scores_gemma":[0.9991352,0.0001265115,0.00004978693,0.0003502307,0.0002599133,0.00007846385],"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":[0.0007222933,0.0003989657,0.003709408,0.0006437417,0.0002377918,0.0003025362,0.0001363768,0.04334399,0.0671791,0.009365208,0.09398147,0.7799791],"study_design_scores_gemma":[0.0001476027,0.0008831426,0.01778148,0.0004703953,0.0001543755,0.00170944,0.0002024197,0.6852255,0.09520585,0.03157239,0.166454,0.0001933356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02246448,0.003348998,0.8942441,0.0006170448,0.001798663,0.0002773412,0.01273898,0.0393891,0.02512124],"genre_scores_gemma":[0.3200019,0.002016793,0.5963827,0.001297939,0.000571536,0.0006897956,0.04476432,0.00267802,0.03159703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02541926,"threshold_uncertainty_score":0.08503592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02483308322566915,"score_gpt":0.3302361433871676,"score_spread":0.3054030601614984,"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."}}