{"id":"W2801430626","doi":"10.1109/tvcg.2018.2832097","title":"A Sampling Approach to Generating Closely Interacting 3D Pose-Pairs from 2D Annotations","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Science and Technology Planning Project of Guangdong Province; National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Pose; Markov chain Monte Carlo; Computer vision; Sampling (signal processing); Motion capture; Motion (physics); Set (abstract data type); Representation (politics); Pattern recognition (psychology); Bayesian probability","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":[],"consensus_categories":[],"category_scores_codex":[0.0001720795,0.0002207974,0.000178892,0.0005142586,0.0008946158,0.0005660399,0.0002476762,0.000101182,0.00002242885],"category_scores_gemma":[0.000006656523,0.0002363369,0.00007972793,0.0008885554,0.00005398635,0.0006723097,0.000009241466,0.0002087984,0.0000447234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003042009,"about_ca_system_score_gemma":0.00003605921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005331186,"about_ca_topic_score_gemma":0.00004088597,"domain_scores_codex":[0.9983798,0.0001341794,0.00038277,0.0005924712,0.000268745,0.0002419965],"domain_scores_gemma":[0.9989729,0.0001608646,0.000120999,0.0002892305,0.0002913439,0.0001646934],"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":[0.0001577976,0.003179058,0.0002369057,0.0001654625,0.0006923666,0.00001076441,0.0684168,0.02389821,0.004898833,0.4308071,0.003103837,0.4644329],"study_design_scores_gemma":[0.0003258674,0.0002171947,0.0002399447,0.00008719511,0.00002294068,0.00001314284,0.000137937,0.9945793,0.002523554,0.000463739,0.001093824,0.0002953452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0571005,0.000008458898,0.9407251,0.00005084186,0.001263931,0.0002294618,0.00001685372,0.0003724448,0.0002324252],"genre_scores_gemma":[0.8972993,0.00002156586,0.09920023,0.002877718,0.0004715116,0.00003951823,0.00003098644,0.00002498929,0.00003412093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9706811,"threshold_uncertainty_score":0.9637538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04511996596799066,"score_gpt":0.3026747992018566,"score_spread":0.257554833233866,"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."}}