{"id":"W2145536551","doi":"10.1109/tcsvt.2008.928888","title":"Human Activity Recognition Based on Silhouette Directionality","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Silhouette; Artificial intelligence; Computer vision; Computer science; Activity recognition; Cluster analysis; Feature vector; Directionality; Pattern recognition (psychology); Background subtraction; Zoom; Feature extraction; Motion (physics); Feature (linguistics); Pixel; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006300238,0.0002157854,0.0003488786,0.000540535,0.0008553936,0.00005898761,0.0002762019,0.0002499508,0.000003910506],"category_scores_gemma":[0.00002850628,0.0002097914,0.000126819,0.0005539537,0.0001401193,0.0002255564,0.000001976933,0.0003265448,0.00001288243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000831802,"about_ca_system_score_gemma":0.00005614195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000102224,"about_ca_topic_score_gemma":0.00004307142,"domain_scores_codex":[0.9983405,0.0001821025,0.0002896074,0.0006342995,0.000233174,0.0003203174],"domain_scores_gemma":[0.9987116,0.0003522704,0.0001410152,0.0005670505,0.000153156,0.00007490368],"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":[0.00008244142,0.001370535,0.00161276,0.0003397326,0.0002242053,0.00006477391,0.0002028832,0.006483646,0.02786389,0.005757743,0.0006729243,0.9553245],"study_design_scores_gemma":[0.01552629,0.01057439,0.04986919,0.001417689,0.0002665077,0.002408191,0.0001739216,0.3439759,0.5015402,0.03518751,0.03370849,0.005351782],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.14575,0.00004659755,0.8512354,0.0005659617,0.0009263954,0.0004647504,0.00004789754,0.0006373177,0.0003257118],"genre_scores_gemma":[0.9982792,0.00001519206,0.0009806128,0.0001797583,0.00005243325,0.0003470883,0.000001788998,0.00001920177,0.000124793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9499727,"threshold_uncertainty_score":0.8555043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06953694203647971,"score_gpt":0.297580803117985,"score_spread":0.2280438610815053,"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."}}