{"id":"W2049819452","doi":"10.1109/iccv.2007.4409073","title":"Human Pose Estimation using Motion Exemplars","year":2007,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Motion (physics); Similarity (geometry); Position (finance); Inference; Joint (building); Motion estimation; Sampling (signal processing); Pose; Motion capture; Measure (data warehouse); Pattern recognition (psychology); Image (mathematics); Data mining; Engineering","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":[0.0003632859,0.0007246993,0.0008763365,0.00170362,0.0003231209,0.0005203928,0.001021044,0.0008158218,0.001707109],"category_scores_gemma":[0.001651527,0.0005239781,0.0006145946,0.001266998,0.0004131503,0.0007725945,0.0005855982,0.0005526161,0.001151001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002115955,"about_ca_system_score_gemma":0.0002570809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002881667,"about_ca_topic_score_gemma":0.003880965,"domain_scores_codex":[0.999564,0.00008093124,0.00001654671,0.0001809945,0.0001162687,0.00004121727],"domain_scores_gemma":[0.9994783,0.0001317321,0.00008983647,0.0001426389,0.0001218991,0.00003564853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002792706,0.0001480476,0.005375471,0.0001196288,0.0002169869,0.0003640534,0.0001198362,0.18408,0.05581788,0.003964894,0.003866548,0.7456473],"study_design_scores_gemma":[0.00001120603,0.00009491664,0.004264565,0.00002062115,0.00002899026,0.0005216837,0.00003950003,0.9726025,0.01639399,0.003518116,0.002473787,0.00003002271],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02785302,0.0003359127,0.9698249,0.00004299899,0.00002387328,0.00004272895,0.0002182755,0.0009771454,0.0006811037],"genre_scores_gemma":[0.4193472,0.000803475,0.5746569,0.00009838793,0.0001233476,0.0001141269,0.002190655,0.0002056079,0.002460345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002881667,"threshold_uncertainty_score":0.005729735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04043340967132915,"score_gpt":0.3155299123910811,"score_spread":0.275096502719752,"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."}}