{"id":"W2554247908","doi":"10.1109/cvpr.2017.139","title":"Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose","year":2017,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":929,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Pose; Representation (politics); Voxel; Convolutional neural network; Feature learning; Pattern recognition (psychology); Dimensionality reduction; Iterative refinement; Curse of dimensionality; Image (mathematics); Deep learning; Computer vision; Machine learning","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":[0.0008232504,0.002092742,0.001044465,0.0009118323,0.0003100244,0.001008639,0.001752316,0.001049942,0.005170308],"category_scores_gemma":[0.003209415,0.0009919736,0.0008900135,0.0007958459,0.0007628792,0.001435721,0.001628798,0.001747918,0.003385397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006332317,"about_ca_system_score_gemma":0.001137312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007765406,"about_ca_topic_score_gemma":0.01992842,"domain_scores_codex":[0.9995621,0.00007190859,0.00001125658,0.0001611571,0.0001291929,0.00006446545],"domain_scores_gemma":[0.9992512,0.0002475867,0.00007360648,0.0002345305,0.0001355873,0.00005745038],"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":[0.0003297608,0.000167277,0.002149924,0.0001833737,0.0001080459,0.0001820182,0.0001235286,0.3919657,0.03073608,0.004887265,0.009643477,0.5595236],"study_design_scores_gemma":[0.0000075735,0.00005373538,0.0006554912,0.00001895473,0.000009396867,0.0001362055,0.00002231127,0.9846431,0.00749965,0.005157012,0.001782848,0.0000136439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00987073,0.0002081649,0.9841837,0.0000940509,0.00005877097,0.00005401759,0.000247968,0.004117861,0.001164629],"genre_scores_gemma":[0.4740213,0.0007243881,0.513497,0.0004231553,0.0001611623,0.0001811262,0.002558952,0.001023897,0.007408967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007765406,"threshold_uncertainty_score":0.01729643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05340889484050255,"score_gpt":0.3029771062922363,"score_spread":0.2495682114517338,"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."}}