{"id":"W2158866619","doi":"10.1109/tpami.2006.149","title":"Recovering 3D human body configurations using shape contexts","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":249,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Division of Mathematical Sciences; University of Toronto","keywords":"Computer vision; Artificial intelligence; Computer science; Human-body model; Kinematics; Context (archaeology); Process (computing); Matching (statistics); Human body; Joint (building); Articulated body pose estimation; Variety (cybernetics); Tracking (education); Shape context; Frame (networking); Image (mathematics); 3D pose estimation; Mathematics; Engineering","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":[0.0001393973,0.0001981462,0.0002519485,0.000543762,0.0005385982,0.0002762748,0.0002307256,0.00006338402,0.0005801411],"category_scores_gemma":[0.000001801343,0.0001940099,0.0002024396,0.0006770685,0.00005002974,0.0004465665,0.000003645336,0.0002104597,0.00004368458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000445734,"about_ca_system_score_gemma":0.00001538751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002095654,"about_ca_topic_score_gemma":0.001704236,"domain_scores_codex":[0.9986352,0.00006840028,0.0004178139,0.0004558775,0.0002086028,0.0002140667],"domain_scores_gemma":[0.9992958,0.00008069174,0.0001307419,0.0003208889,0.00009188915,0.00007999987],"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":[0.000005858873,0.0003877355,0.0004861406,0.00002251107,0.0004965191,0.00002903418,0.0002125745,0.0451906,0.02280136,0.0007835741,0.00001790272,0.9295662],"study_design_scores_gemma":[0.0001603138,0.0001047276,0.00202444,0.00003977868,0.0004541798,0.00003099121,0.00002657943,0.803606,0.192065,0.0008618146,0.0001996555,0.0004265922],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04401544,0.0000376733,0.9549842,0.00008621299,0.0001724194,0.0001041609,0.00003166551,0.0001088426,0.0004593088],"genre_scores_gemma":[0.9982922,0.00004282811,0.00108391,0.0002434226,0.00004077403,0.00001338165,0.00001532284,0.00001025999,0.00025792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9542767,"threshold_uncertainty_score":0.7911494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02617981125504508,"score_gpt":0.2814156241246134,"score_spread":0.2552358128695683,"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."}}