{"id":"W2109142906","doi":"10.1109/icme.2006.262826","title":"Detecting Human Action in Active Video","year":2006,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Computer vision; Artificial intelligence; Clutter; Object (grammar); Matching (statistics); Scheme (mathematics); Action (physics); Set (abstract data type); Video tracking; Broadcasting (networking); Point (geometry); Object detection; Pattern recognition (psychology); Radar; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004194775,0.0006354274,0.0005163604,0.001322185,0.0002750448,0.0005652662,0.001165479,0.0007772912,0.001204123],"category_scores_gemma":[0.001158162,0.0003075395,0.0003817691,0.0006235746,0.0006227582,0.0008473336,0.0005981207,0.0005406468,0.0005070686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003036941,"about_ca_system_score_gemma":0.0004612021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002305849,"about_ca_topic_score_gemma":0.002863961,"domain_scores_codex":[0.9995354,0.00007374688,0.00001451435,0.0001532575,0.0001684301,0.00005455149],"domain_scores_gemma":[0.9994519,0.0001510521,0.00009007637,0.00007950326,0.0001556493,0.00007180377],"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":[0.0004105852,0.0003518492,0.005323347,0.0001531827,0.00007787374,0.0002449849,0.0003117797,0.02944248,0.1672967,0.00863639,0.002484054,0.7852668],"study_design_scores_gemma":[0.00004702772,0.0004944146,0.007649968,0.00001927483,0.00005563904,0.0006408606,0.0001233259,0.8956481,0.08496369,0.004525334,0.005777036,0.00005540601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03076251,0.0001297354,0.9672717,0.00007876178,0.00003406782,0.00007766052,0.00005115741,0.0004995144,0.001094742],"genre_scores_gemma":[0.3727158,0.0002236597,0.6235389,0.0001133632,0.00007695756,0.0000920869,0.0001990787,0.00004558728,0.002994598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002305849,"threshold_uncertainty_score":0.004584908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02860774201355333,"score_gpt":0.2808257266123579,"score_spread":0.2522179845988046,"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."}}