{"id":"W4255957727","doi":"10.36227/techrxiv.14887869","title":"Joint Selection using Deep Reinforcement Learning for Skeleton-based Activity Recognition","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Skeleton (computer programming); Joint (building); Artificial intelligence; Computer science; Benchmark (surveying); Selection (genetic algorithm); Pattern recognition (psychology); Reinforcement learning; Activity recognition; Machine learning; Human skeleton; Frame (networking); Engineering","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":[0.001010606,0.0007148805,0.001078905,0.0004948702,0.0002341552,0.000430218,0.00110682,0.0006950281,0.001589494],"category_scores_gemma":[0.002023473,0.0003305555,0.0004722407,0.00046711,0.0005250328,0.0006557738,0.0006671844,0.001063654,0.0004458066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007637965,"about_ca_system_score_gemma":0.0008469308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007320418,"about_ca_topic_score_gemma":0.006965758,"domain_scores_codex":[0.9995887,0.0001123007,0.00002138268,0.0001305268,0.00008319353,0.00006396414],"domain_scores_gemma":[0.9992722,0.0003282501,0.0001128734,0.00008366781,0.0001282821,0.00007469398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002581727,0.0003108337,0.002768534,0.00005185638,0.00007658039,0.0001239431,0.00005497503,0.5796508,0.01061581,0.002259052,0.002806324,0.4010231],"study_design_scores_gemma":[0.000003914733,0.00001593063,0.0001312824,0.000001317975,0.000002156762,0.000006080837,0.000001455251,0.9985688,0.0005937874,0.0005995058,0.00007381959,0.000002016023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06522831,0.0005996404,0.9304041,0.0002192941,0.0000624297,0.00005988858,0.0000925736,0.001978465,0.001355238],"genre_scores_gemma":[0.8774427,0.0001901944,0.1187648,0.0001641084,0.00004820453,0.00008440785,0.00030459,0.0000911414,0.002909878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007320418,"threshold_uncertainty_score":0.01455557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07631882016381267,"score_gpt":0.2907579784407176,"score_spread":0.2144391582769049,"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."}}