{"id":"W2056380775","doi":"10.1109/tpami.2011.253","title":"Learning Sparse Representations for Human Action Recognition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":349,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Cluster analysis; Sparse approximation; Vector quantization; K-SVD; Invariant (physics); Feature vector; Set (abstract data type); Representation (politics); Learning vector quantization; Mathematics","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":[0.0002167008,0.0001662033,0.00019696,0.0006174328,0.0005511653,0.0001180119,0.0001864883,0.00006784141,0.0004185906],"category_scores_gemma":[0.000007797861,0.0001651923,0.0002478205,0.0006275933,0.00004051749,0.0004832842,0.000003034162,0.0002333452,0.00006559103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002715362,"about_ca_system_score_gemma":0.000009651207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008196767,"about_ca_topic_score_gemma":0.00111643,"domain_scores_codex":[0.9987337,0.00009330489,0.0003412448,0.0004852896,0.0001559623,0.0001904748],"domain_scores_gemma":[0.9992341,0.0001159098,0.000149197,0.0002687738,0.0001336238,0.00009833625],"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":[0.00001182036,0.0002001718,0.0002332954,0.00001388428,0.0002974952,0.000002515828,0.000868843,0.0008842016,0.0008805345,0.0001187888,0.000007986252,0.9964805],"study_design_scores_gemma":[0.0004031654,0.0008089749,0.003490623,0.00004996792,0.001260317,0.00002380954,0.0006003282,0.1349325,0.8451142,0.01239279,0.0002328995,0.0006904399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02221859,0.000008943866,0.9767239,0.00007062401,0.0002041134,0.0001926626,0.00002360539,0.0001540801,0.0004034917],"genre_scores_gemma":[0.9959322,0.0001375371,0.003156904,0.0001617126,0.00002942055,0.0001032677,0.00003621861,0.00001136326,0.0004313868],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.99579,"threshold_uncertainty_score":0.6736348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1038711441174204,"score_gpt":0.3220549019212692,"score_spread":0.2181837578038487,"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."}}