{"id":"W7106608427","doi":"10.1016/j.procs.2025.10.265","title":"Transformer-based Human Action Recognition using Skeleton Heatmap","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Human skeleton; Skeleton (computer programming); Pipeline (software); Benchmark (surveying); Activity recognition; Generalization; Pattern recognition (psychology); Biometrics; Gaussian","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":[],"consensus_categories":[],"category_scores_codex":[0.0005156094,0.000187614,0.0001619265,0.0007180081,0.0009221158,0.0005790478,0.0008216976,0.0000702358,0.000017599],"category_scores_gemma":[0.00001762577,0.0001900006,0.00008267436,0.001988464,0.0001954237,0.002090973,0.0000770986,0.0001872138,0.00005404893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001988089,"about_ca_system_score_gemma":0.0005206493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002482585,"about_ca_topic_score_gemma":0.00001186125,"domain_scores_codex":[0.9980427,0.00003974179,0.0003089466,0.0007247549,0.0004505542,0.0004332885],"domain_scores_gemma":[0.999029,0.00004646192,0.0001028601,0.0003458575,0.0003530951,0.0001226604],"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":[0.000009446329,0.0002435176,0.0002990124,0.0001338339,0.00001169156,0.000005505794,0.0003362666,0.0004489342,0.07686407,0.003675566,0.0003233233,0.9176489],"study_design_scores_gemma":[0.0007293841,0.0001757073,0.001899757,0.0002190372,0.00001784349,0.00002182467,0.00001284849,0.7160653,0.2649136,0.0144304,0.00111265,0.0004016494],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2074583,0.0000142989,0.7893797,0.0004181483,0.001018765,0.0002397842,0.000001221789,0.0003131685,0.001156598],"genre_scores_gemma":[0.8940795,0.000004486694,0.104446,0.001210517,0.0001849656,0.00002649762,0.000007070272,0.000006785244,0.00003415098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9172472,"threshold_uncertainty_score":0.7747999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0592634990099064,"score_gpt":0.3298153361630602,"score_spread":0.2705518371531538,"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."}}