{"id":"W3008546095","doi":"10.1109/access.2020.3023599","title":"Infrared and 3D Skeleton Feature Fusion for RGB-D Action Recognition","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; RGB color model; Pattern recognition (psychology); Convolutional neural network; Feature (linguistics); Feature extraction; Computer vision; Modular design; Skeleton (computer programming)","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":[0.00007477223,0.0001057539,0.0001069738,0.00007263786,0.0001859203,0.000376853,0.0002471547,0.00009523951,0.0000341713],"category_scores_gemma":[0.00003660478,0.0001033713,0.00004146239,0.0002243269,0.00001367081,0.001720382,0.00006357046,0.0001222716,0.00004214406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001756247,"about_ca_system_score_gemma":0.00002121432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005348347,"about_ca_topic_score_gemma":0.000006111206,"domain_scores_codex":[0.9992455,0.00003129105,0.0001235059,0.0003257663,0.0001284019,0.0001454855],"domain_scores_gemma":[0.9995203,0.00005473787,0.00009609648,0.0001208117,0.000109901,0.00009813452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007297122,0.00004307123,0.00008624853,0.0001392693,0.00001830786,0.000004581848,0.0005401028,0.00001125511,0.01401204,0.0001385588,0.04267958,0.942254],"study_design_scores_gemma":[0.005684858,0.001182679,0.00808192,0.0002885681,0.0001252934,0.00007593763,0.0001871152,0.1424527,0.4906383,0.07350009,0.2761325,0.001650047],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.296698,0.00006641349,0.692687,0.005605532,0.001199903,0.0006578616,0.00002846917,0.0004312035,0.002625567],"genre_scores_gemma":[0.9726625,0.0002546156,0.01621515,0.008246515,0.001555185,0.0001480191,0.0001393225,0.00002927736,0.0007494308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.940604,"threshold_uncertainty_score":0.4215359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09625338521946276,"score_gpt":0.3216041742879233,"score_spread":0.2253507890684605,"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."}}