{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001999657,0.001290915,0.00146716,0.002337595,0.0003655911,0.00160235,0.002034992,0.001366208,0.00174358],"category_scores_gemma":[0.004900836,0.0007289925,0.002060705,0.002032477,0.0007962821,0.00347674,0.001242379,0.0016013,0.001485089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007109569,"about_ca_system_score_gemma":0.0006205761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005146128,"about_ca_topic_score_gemma":0.005966391,"domain_scores_codex":[0.9983048,0.0005906702,0.0001000478,0.0005282945,0.0003216938,0.0001544199],"domain_scores_gemma":[0.9973571,0.001479379,0.0003123839,0.0003666487,0.0003898674,0.00009473616],"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":[0.0009106298,0.000543752,0.006845161,0.0004021335,0.0005134245,0.0002724609,0.0007054951,0.2821654,0.01929343,0.01464505,0.0111207,0.6625823],"study_design_scores_gemma":[0.00001269597,0.00003558488,0.0007814016,0.000009747067,0.00002009715,0.00006315421,0.00002011195,0.991998,0.001256194,0.005114628,0.0006707403,0.00001760148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02185047,0.0009843168,0.9741458,0.0003030144,0.00007878758,0.00005688408,0.0003514111,0.001312745,0.0009165999],"genre_scores_gemma":[0.6264026,0.001766692,0.3619232,0.0003770799,0.000471698,0.0004988901,0.003205521,0.0003396149,0.005014696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005146128,"threshold_uncertainty_score":0.01057535,"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."}}