{"id":"W4411360010","doi":"10.1109/cismcompanion65074.2025.11032343","title":"Swin PoseFormer: A Human Activity Recognition Model Using Skeleton Heatmaps","year":2025,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Skeleton (computer programming); Human skeleton; Artificial intelligence; Pattern recognition (psychology); Speech recognition","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":[],"consensus_categories":[],"category_scores_codex":[0.0001567247,0.0001301456,0.00013408,0.0002434074,0.0003506903,0.0001678701,0.0002249029,0.00008150396,0.00007151465],"category_scores_gemma":[0.000008851463,0.0001250305,0.00008578462,0.0003524444,0.00002087553,0.001006005,0.0001017274,0.000143529,0.00008346805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001134527,"about_ca_system_score_gemma":0.00008838026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001733473,"about_ca_topic_score_gemma":0.00006678147,"domain_scores_codex":[0.9990623,0.00004539977,0.0001760845,0.0003402456,0.0001488995,0.0002270726],"domain_scores_gemma":[0.9994935,0.00002173527,0.00005900151,0.0002759312,0.00009503423,0.00005474997],"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":[0.00002215474,0.0005404911,0.0001326893,0.00007811445,0.00007542549,0.00000812723,0.0003108198,0.001071353,0.3158801,0.01948941,0.003084854,0.6593065],"study_design_scores_gemma":[0.0006031664,0.00006169276,0.0006550238,0.0000856296,0.00002263887,0.00001042043,0.00001951163,0.7749266,0.1381313,0.08479789,0.0003794049,0.0003067147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4445832,0.00000494484,0.532361,0.0003034568,0.00012444,0.000113605,0.00000213083,0.000204945,0.0223022],"genre_scores_gemma":[0.9799097,0.000005271876,0.01714114,0.0007982158,0.00004518034,0.00001209381,0.000009882739,0.00000599994,0.002072571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7738552,"threshold_uncertainty_score":0.5098594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05143989263468747,"score_gpt":0.3134218586096778,"score_spread":0.2619819659749903,"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."}}