{"id":"W2135658380","doi":"10.1109/cvpr.2008.4587735","title":"Action recognition by learning mid-level motion features","year":2008,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":452,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"AdaBoost; Computer science; Artificial intelligence; Optical flow; Motion (physics); Pattern recognition (psychology); Action recognition; Action (physics); Feature extraction; Feature (linguistics); Scale (ratio); Machine learning; Computer vision; Image (mathematics); Support vector machine; Class (philosophy)","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":[0.0003020948,0.0008182376,0.000870501,0.001511254,0.0003056565,0.0004691381,0.0009149899,0.0006431944,0.002275446],"category_scores_gemma":[0.001108591,0.0002897227,0.0006706396,0.0006756371,0.0003531762,0.0009018827,0.0005076245,0.0008250873,0.001358672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004358925,"about_ca_system_score_gemma":0.0004707885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00282626,"about_ca_topic_score_gemma":0.004080614,"domain_scores_codex":[0.9996108,0.00003552822,0.00002010122,0.000152204,0.0001241601,0.00005716855],"domain_scores_gemma":[0.9996613,0.00008313985,0.00005496556,0.00005172467,0.0001055277,0.00004326933],"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":[0.0002515441,0.0002757941,0.00442432,0.0001178898,0.00006427336,0.00009991631,0.00005093502,0.02142731,0.06304189,0.001749766,0.004893058,0.9036034],"study_design_scores_gemma":[0.00003037443,0.0003103946,0.01324154,0.0000482846,0.00005332094,0.0003471601,0.00006549463,0.9210488,0.04841542,0.008058187,0.008328944,0.00005222783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05549544,0.0005905424,0.9372374,0.0001280954,0.0001412666,0.0001428395,0.0006553262,0.003071865,0.002537329],"genre_scores_gemma":[0.4554078,0.000504864,0.5351218,0.0001726671,0.0001304804,0.0002107794,0.002809508,0.0001972921,0.005444893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00282626,"threshold_uncertainty_score":0.007612109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08582386955020781,"score_gpt":0.2656382612436054,"score_spread":0.1798143916933976,"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."}}