{"id":"W3094430014","doi":"10.1007/s11263-021-01529-w","title":"View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose","year":2021,"lang":"en","type":"preprint","venue":"International Journal of Computer Vision","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Embedding; Artificial intelligence; Computer science; Invariant (physics); Computer vision; Probabilistic logic; Pose; Viewpoints; Pattern recognition (psychology); Action recognition; Similarity (geometry); Image (mathematics); Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008311793,0.0003073871,0.0004921132,0.0005891603,0.000183304,0.001499511,0.002179571,0.0002219281,0.00006895381],"category_scores_gemma":[0.00008681823,0.000284982,0.0005701021,0.0001160323,0.00003486401,0.0008844335,0.001821677,0.0006677287,0.00001061065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002695638,"about_ca_system_score_gemma":0.0003435833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008448014,"about_ca_topic_score_gemma":0.000006341734,"domain_scores_codex":[0.9969246,0.0001673461,0.001165849,0.0005203369,0.0009944923,0.0002274131],"domain_scores_gemma":[0.995069,0.0002619691,0.00133209,0.0004051002,0.002782358,0.0001494594],"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":[0.0003663368,0.003779674,0.00009342181,0.0009404957,0.002470321,0.004052695,0.004568909,0.1928128,0.01315647,0.06075961,0.0521685,0.6648308],"study_design_scores_gemma":[0.003139972,0.00114735,0.00177076,0.00681808,0.0001478108,0.002781902,0.00004703589,0.8732901,0.001718767,0.08994797,0.01810491,0.001085319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03865507,0.0001672586,0.9469003,0.001553715,0.01213259,0.0002950018,0.00001739241,0.00005931615,0.0002193669],"genre_scores_gemma":[0.6651522,0.0001274481,0.3276046,0.001028532,0.005785277,0.00001271677,0.0001532421,0.00003838581,0.00009762826],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6804774,"threshold_uncertainty_score":0.9999602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03592826795466383,"score_gpt":0.3421048200845369,"score_spread":0.3061765521298731,"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."}}