{"id":"W4411019699","doi":"10.1109/tcss.2025.3566733","title":"Skeleton-Based Action Recognition Using Multibranch Adaptive Graph Convolutional Network With Pose Refinement","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Social Systems","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Skeleton (computer programming); Action recognition; Graph; Artificial intelligence; Graph theory; Convolutional neural network; Theoretical computer science; Pattern recognition (psychology); Mathematics; Combinatorics","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":[0.0003815979,0.001765017,0.0009701767,0.001412233,0.0002779986,0.0004946704,0.001713534,0.0008095318,0.003074785],"category_scores_gemma":[0.0007217781,0.0004871218,0.001120155,0.001121922,0.0005437324,0.001020782,0.0008228974,0.001118978,0.001522101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001124288,"about_ca_system_score_gemma":0.001397143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03168176,"about_ca_topic_score_gemma":0.0520368,"domain_scores_codex":[0.9995738,0.00003216136,0.00001834342,0.0001901068,0.0001187339,0.00006687692],"domain_scores_gemma":[0.9997527,0.00003773331,0.00003369809,0.000068766,0.00007372458,0.00003332713],"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":[0.0002777477,0.0002185166,0.002744936,0.00015094,0.0001898913,0.0002122147,0.00005506591,0.1615885,0.03852605,0.00314112,0.01328613,0.779609],"study_design_scores_gemma":[0.000009727205,0.00005270778,0.001364818,0.0000104999,0.00002957098,0.000092786,0.000008183413,0.9856715,0.008602234,0.001865632,0.002273292,0.00001908931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0445823,0.00129446,0.9300842,0.0003183359,0.0002457972,0.0001622871,0.00135952,0.01734316,0.004609887],"genre_scores_gemma":[0.5574052,0.001405404,0.41706,0.0005747938,0.00009675727,0.0001800081,0.006955461,0.0004685147,0.01585394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03168176,"threshold_uncertainty_score":0.06299472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05208453873856871,"score_gpt":0.283474595162959,"score_spread":0.2313900564243903,"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."}}