{"id":"W4327809167","doi":"10.1109/tsmc.2023.3250120","title":"Spatial Hard Attention Modeling via Deep Reinforcement Learning for Skeleton-Based Human Activity Recognition","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Discriminative model; Artificial intelligence; Computer science; Skeleton (computer programming); Reinforcement learning; Deep learning; Activity recognition; Pattern recognition (psychology); Human skeleton; Hidden Markov model; Machine learning; Frame (networking); Process (computing); Joint (building); Engineering","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":[0.0006332147,0.0006581171,0.0007648381,0.0002999545,0.0001814366,0.0004383737,0.001036687,0.0006834958,0.001818108],"category_scores_gemma":[0.001755912,0.0002916969,0.0004266074,0.0002940603,0.0006027995,0.0006535452,0.0006953508,0.001237856,0.0003167493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008976681,"about_ca_system_score_gemma":0.0008905233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008333776,"about_ca_topic_score_gemma":0.007886935,"domain_scores_codex":[0.9997495,0.00006251369,0.00001099027,0.00007786471,0.00005523194,0.00004400552],"domain_scores_gemma":[0.9995521,0.0002118309,0.00007575301,0.00003918933,0.00007975372,0.00004135028],"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":[0.00009720247,0.00009196356,0.0009392986,0.00003382653,0.00003047405,0.0000601504,0.00003680327,0.9090119,0.004638067,0.004846391,0.001213943,0.07899995],"study_design_scores_gemma":[0.000002202477,0.000007551995,0.00005279158,0.00000100319,0.000001474344,0.000003210522,7.883052e-7,0.9987577,0.0002895126,0.0008189097,0.00006377622,0.000001170454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03999623,0.0003542942,0.9568093,0.0002409973,0.00005136201,0.00003357774,0.00005729508,0.0009297484,0.001527256],"genre_scores_gemma":[0.9226128,0.0001601844,0.07327421,0.0001553669,0.00003834558,0.0000773393,0.0001136932,0.00005896853,0.003509049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008333776,"threshold_uncertainty_score":0.01657051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04223951700842035,"score_gpt":0.2555025766333077,"score_spread":0.2132630596248874,"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."}}