{"id":"W2130843763","doi":"10.1109/tpami.2009.43","title":"Human Action Recognition by Semilatent Topic Models","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":325,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Harbin Institute of Technology; Microsoft Research","keywords":"Computer science; Artificial intelligence; Action recognition; Topic model; Class (philosophy); Probabilistic latent semantic analysis; Machine learning; Set (abstract data type); Training set; Frame (networking); Representation (politics); Hidden Markov model; Word (group theory); Action (physics); Latent variable; Natural language processing; 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":[0.0001414597,0.0001984639,0.0002256402,0.0004399708,0.0003303893,0.0001805323,0.0002162512,0.00008446202,0.0002206754],"category_scores_gemma":[0.000001089548,0.00018764,0.0002060623,0.0006120419,0.00002387435,0.0006149788,0.000002006057,0.000256897,0.00005330761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004582598,"about_ca_system_score_gemma":0.000007266385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003002384,"about_ca_topic_score_gemma":0.000225701,"domain_scores_codex":[0.9986539,0.00007157832,0.0003428096,0.0004882509,0.000237895,0.0002055857],"domain_scores_gemma":[0.9993575,0.0000326133,0.0001085991,0.0003064985,0.00007634283,0.0001184382],"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":[0.000003083707,0.0002034632,0.00001034467,0.000005007727,0.0001308004,0.000003023703,0.0001366105,0.003195596,0.002890916,0.00005321914,0.00005850769,0.9933094],"study_design_scores_gemma":[0.0002575177,0.0005129463,0.000593249,0.00004899627,0.0005809704,0.00002135834,0.00006422118,0.3477228,0.6321647,0.01722097,0.000171375,0.0006408556],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02429902,0.00004665925,0.9744191,0.0004802207,0.0001458157,0.0001104894,0.00002887249,0.0001442658,0.0003255449],"genre_scores_gemma":[0.9976761,0.0003678838,0.0004376982,0.001020209,0.00002406224,0.00001508412,0.00002966507,0.000006239248,0.0004230848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9926686,"threshold_uncertainty_score":0.7651737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04873622529257237,"score_gpt":0.2883200060787379,"score_spread":0.2395837807861655,"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."}}