{"id":"W3045919984","doi":"10.48550/arxiv.2007.15506","title":"SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Benchmark (surveying); Artificial intelligence; Computer science; Generalization; Task (project management); Residual; Domain (mathematical analysis); Domain adaptation; Deep learning; Noise (video); Machine learning; Pixel; Pattern recognition (psychology); Adaptation (eye); Computer vision; Image (mathematics); Algorithm; Mathematics; Geography","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":[0.00125893,0.00156484,0.0008490332,0.000806879,0.0002804534,0.0007695232,0.002028392,0.001518425,0.003175184],"category_scores_gemma":[0.004011158,0.0007182786,0.001339081,0.0006537218,0.0009453673,0.001314071,0.001917414,0.002200305,0.001762853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005488974,"about_ca_system_score_gemma":0.0008700333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00555453,"about_ca_topic_score_gemma":0.009371938,"domain_scores_codex":[0.9994503,0.0001567224,0.00001203328,0.0002224986,0.0001008126,0.00005771677],"domain_scores_gemma":[0.9989884,0.0004181998,0.00007906733,0.0003057577,0.0001184353,0.00009004353],"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":[0.000264208,0.0002112699,0.003474842,0.0001503555,0.0001390108,0.0001309777,0.0001212855,0.7441763,0.01141442,0.004063637,0.008773281,0.2270804],"study_design_scores_gemma":[0.000009909034,0.00003314118,0.0003476918,0.00000716781,0.000004230791,0.00004195415,0.00001422577,0.9936845,0.002141937,0.002946823,0.0007604966,0.000007858849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03960546,0.0002378425,0.952279,0.0001679056,0.00008611084,0.00008053548,0.0005321457,0.005522389,0.001488519],"genre_scores_gemma":[0.559155,0.0002669892,0.4297255,0.0004301841,0.0001240755,0.0002260883,0.004586209,0.000901982,0.004584054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00555453,"threshold_uncertainty_score":0.01104438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1016713713672565,"score_gpt":0.2071955895629111,"score_spread":0.1055242181956547,"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."}}