{"id":"W3186553538","doi":"10.36227/techrxiv.14887869.v1","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":5,"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; Human skeleton; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004343203,0.0002949163,0.0003213088,0.0003129025,0.0004119881,0.0006595432,0.0002114654,0.0003029928,0.0002764396],"category_scores_gemma":[0.00009655394,0.0003288014,0.0003186635,0.0002332698,0.00001621281,0.0005327516,0.0002653412,0.0006419537,0.00002243833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004135146,"about_ca_system_score_gemma":0.000399256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001922994,"about_ca_topic_score_gemma":0.00007029589,"domain_scores_codex":[0.9980037,0.0001684218,0.0003803588,0.0007846276,0.0003254651,0.0003374722],"domain_scores_gemma":[0.9985157,0.00009475564,0.0004346821,0.00030364,0.0005562307,0.0000950221],"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":[0.00003919602,0.0002087477,0.0000347862,0.0006055082,0.0001375121,0.000005490836,0.000297466,0.6333378,0.02647251,0.0001362595,0.0001416428,0.3385831],"study_design_scores_gemma":[0.0003686023,0.0001001359,0.00008435625,0.0001958284,0.00004155121,0.000006616113,0.00002918942,0.8679639,0.129858,0.0007806576,0.0002017634,0.0003693535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0926311,0.00001213809,0.9044954,0.0001604388,0.0008005468,0.0006473021,9.592738e-7,0.0003792597,0.0008728619],"genre_scores_gemma":[0.8972208,0.00001519432,0.1014245,0.0003020166,0.000295491,0.0001905032,0.0002671098,0.00002605187,0.000258344],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8045897,"threshold_uncertainty_score":0.9999164,"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."}}