{"id":"W4403635079","doi":"10.1016/j.cviu.2024.104213","title":"A GCN and Transformer complementary network for skeleton-based action recognition","year":2024,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Transformer; Artificial intelligence; Computer science; Action recognition; Skeleton (computer programming); Pattern recognition (psychology); Engineering; Voltage","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":[0.0004082696,0.0006704447,0.0007666061,0.000676506,0.0003534413,0.0004883584,0.001283721,0.0009239968,0.004335537],"category_scores_gemma":[0.0007474063,0.0003158353,0.0005539345,0.0009794062,0.0004079677,0.000761574,0.00076936,0.0009635676,0.001354516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000737462,"about_ca_system_score_gemma":0.00147889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0276146,"about_ca_topic_score_gemma":0.03063135,"domain_scores_codex":[0.9997094,0.00002159243,0.00001142136,0.000124465,0.00008453392,0.00004859641],"domain_scores_gemma":[0.9997414,0.00005134109,0.00001426384,0.00004247729,0.0001169031,0.00003362904],"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":[0.0003106674,0.0001808247,0.0008758403,0.0001029585,0.0000728623,0.0001567858,0.00003724773,0.05668147,0.05903518,0.006047841,0.008001115,0.8684973],"study_design_scores_gemma":[0.00001338848,0.00007243673,0.0006880288,0.00001062787,0.00003329772,0.000106737,0.00001330503,0.9821322,0.01190998,0.002941711,0.002061362,0.00001701862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02318124,0.0007310822,0.9665673,0.0001774347,0.0003475294,0.000110946,0.0004351832,0.003591299,0.004857855],"genre_scores_gemma":[0.4953899,0.0008448494,0.4904578,0.0004216025,0.0001656076,0.0001700575,0.001238755,0.0002539684,0.01105745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0276146,"threshold_uncertainty_score":0.05490774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09234589976460437,"score_gpt":0.3236472678315014,"score_spread":0.2313013680668971,"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."}}