{"id":"W2057232399","doi":"10.1109/cvpr.2014.333","title":"3D Pose from Motion for Cross-View Action Recognition via Non-linear Circulant Temporal Encoding","year":2014,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":125,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Encoding (memory); Motion (physics); Matching (statistics); Action recognition; Motion capture; Computer vision; Pattern recognition (psychology); Mathematics","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":[0.0004052606,0.0001567208,0.0001714701,0.000126591,0.0002929078,0.0002485457,0.0002100907,0.0001165499,0.000205681],"category_scores_gemma":[0.00004803306,0.0001496473,0.000115086,0.0001558639,0.00002064971,0.001260983,0.00004306315,0.0001152081,0.0005333233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006054582,"about_ca_system_score_gemma":0.00002050079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001661916,"about_ca_topic_score_gemma":0.00004073814,"domain_scores_codex":[0.9987093,0.00006669101,0.0003292466,0.0004596246,0.0002015952,0.0002335614],"domain_scores_gemma":[0.9991514,0.0001082589,0.0001713158,0.0002742388,0.000203973,0.00009082615],"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":[0.00002482389,0.000136567,0.0005707768,0.0000669751,0.00002698671,0.000001637085,0.0001666453,0.00004612776,0.01668119,0.0003338995,0.000454538,0.9814898],"study_design_scores_gemma":[0.001510287,0.0002376801,0.005835625,0.0001314717,0.00003565774,0.00002303068,0.00002630952,0.8858569,0.06675266,0.03136137,0.007696962,0.0005320794],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1329456,0.000007054808,0.863798,0.0001576662,0.00104202,0.0003019438,0.00001218256,0.0002450943,0.001490442],"genre_scores_gemma":[0.9340872,0.00001728252,0.06383113,0.0005707566,0.0008633279,0.00006208872,0.000359395,0.00001540634,0.0001934319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9809577,"threshold_uncertainty_score":0.685497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06430647774588798,"score_gpt":0.3114918242868737,"score_spread":0.2471853465409857,"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."}}