{"id":"W4392940744","doi":"10.1109/cac59555.2023.10451388","title":"Skeleton-Based Multi-Stream Adaptive Graph Convolutional Network for Indoor Scene Action Recognition","year":2023,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Action recognition; Skeleton (computer programming); Graph; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Computer vision; Theoretical computer science","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":[0.0003028931,0.000152291,0.0001364089,0.0002527555,0.0003672812,0.00009951497,0.0001888396,0.0001086308,0.0001171276],"category_scores_gemma":[0.00003665942,0.0001519139,0.0001475014,0.0007636743,0.00003850911,0.000520219,0.00003382478,0.0001168395,0.0006145886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006355109,"about_ca_system_score_gemma":0.0001005592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003410102,"about_ca_topic_score_gemma":0.00008979179,"domain_scores_codex":[0.9987054,0.00006670171,0.000240649,0.0004109901,0.0002161129,0.0003601171],"domain_scores_gemma":[0.9990766,0.0002522941,0.0001208825,0.0001800487,0.0002733637,0.00009681503],"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":[0.0003069694,0.0006650601,0.001117956,0.00009614669,0.0001934664,0.00001480054,0.0001844451,0.005032755,0.002801689,0.01416956,0.1163908,0.8590264],"study_design_scores_gemma":[0.002757255,0.0003547303,0.01097529,0.00008055772,0.00002701996,0.000006650881,0.00008517624,0.9387032,0.01138724,0.03021517,0.004938823,0.0004688819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02094132,0.0000114551,0.9756207,0.0005605361,0.0009050412,0.0005190285,0.00005419368,0.0008741643,0.0005135175],"genre_scores_gemma":[0.7812055,0.00003649833,0.2129676,0.001592645,0.0009036457,0.000582399,0.001153125,0.00003270427,0.00152592],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9336705,"threshold_uncertainty_score":0.7899497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.118846647879051,"score_gpt":0.30769305893941,"score_spread":0.188846411060359,"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."}}