{"id":"W2952270885","doi":"10.48550/arxiv.1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Pose; Computer science; Artificial intelligence; Benchmark (surveying); Ground truth; Deep learning; Baseline (sea); Task (project management); Surprise; Set (abstract data type); 3D pose estimation; Convolutional neural network; Word error rate; Computer vision; Pixel; Pattern recognition (psychology); Geography; Cartography; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003610018,0.0002429735,0.000266774,0.0002410517,0.0005839085,0.0002518537,0.0009379752,0.0002206729,0.00004314905],"category_scores_gemma":[0.0001100975,0.0002884771,0.0002047087,0.0001063219,0.00006089889,0.0006067497,0.0006246779,0.0002990653,0.0001300124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151978,"about_ca_system_score_gemma":0.00008700551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001102529,"about_ca_topic_score_gemma":0.00006608808,"domain_scores_codex":[0.9985784,0.000118465,0.0001594906,0.0008308335,0.00006841433,0.000244398],"domain_scores_gemma":[0.9981311,0.0001856413,0.0003701561,0.0009530009,0.000251178,0.0001089096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003450513,0.001471966,0.001644248,0.001596167,0.0009798944,0.0006512411,0.001560659,0.2934568,0.0009936253,0.4217752,0.02144409,0.2540811],"study_design_scores_gemma":[0.0006983904,0.0001049575,0.0007926393,0.00009747707,0.00008102207,0.000002245796,0.000008885743,0.8211904,0.0004841965,0.1747436,0.001459158,0.0003370691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09251074,0.000009350223,0.9042096,0.0000489028,0.0005350834,0.0007914756,0.00006276929,0.0002313512,0.001600706],"genre_scores_gemma":[0.992919,0.00001250986,0.005289516,0.00008698823,0.0001609764,0.00001058178,0.0002575328,0.00001609741,0.001246847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9004082,"threshold_uncertainty_score":0.9999567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07424930410867034,"score_gpt":0.2382774319782042,"score_spread":0.1640281278695339,"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."}}