{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001023836,0.00009985075,0.00007816184,0.0001130886,0.0003808861,0.00008183963,0.0001291979,0.00008057377,0.0002993902],"category_scores_gemma":[0.00002563017,0.00009671683,0.00005278547,0.0001710266,0.00002003419,0.001040642,0.00002793609,0.0001996594,0.001120911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000400389,"about_ca_system_score_gemma":0.00001593613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007295306,"about_ca_topic_score_gemma":0.00001434719,"domain_scores_codex":[0.9991591,0.00007280819,0.0001367837,0.0002667874,0.0002013645,0.0001631288],"domain_scores_gemma":[0.9996136,0.00003310161,0.00007626342,0.0001209402,0.00009501911,0.00006109178],"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":[0.00001313738,0.0001696361,0.0003843015,0.00001399884,0.00002169145,0.00001191775,0.000519017,0.00002910143,0.04693621,0.0003075553,0.09906869,0.8525248],"study_design_scores_gemma":[0.001962228,0.0004454155,0.07093557,0.00005362485,0.00002658957,0.0009291637,0.0002754621,0.006365811,0.8541815,0.01068637,0.05294678,0.001191537],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3282417,0.00004005043,0.6535479,0.0008035771,0.0005201002,0.0001305871,0.000004298884,0.0007008819,0.01601089],"genre_scores_gemma":[0.9860179,0.0001501647,0.005086256,0.0005530182,0.0001267331,0.00001570074,0.0001301953,0.000007089767,0.007912963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8513332,"threshold_uncertainty_score":0.9996569,"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."}}