{"id":"W3092458367","doi":"10.1109/jsen.2020.3028561","title":"CNN-Based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial Sensors","year":2020,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Fuse (electrical); Pattern recognition (psychology); Leverage (statistics); Inertial measurement unit; Feature extraction; Feature (linguistics); Curse of dimensionality; Computer vision; Engineering","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":[0.0004405475,0.001116097,0.0006869792,0.0007120272,0.0002718932,0.0004428485,0.001207705,0.0007004667,0.002053216],"category_scores_gemma":[0.0007924017,0.0003581463,0.0007932229,0.0005962296,0.0003520724,0.001068448,0.0009697442,0.0006453484,0.0005409668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007412981,"about_ca_system_score_gemma":0.000740681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00939027,"about_ca_topic_score_gemma":0.0141887,"domain_scores_codex":[0.9996685,0.00002819753,0.00001511918,0.000123165,0.0000989876,0.00006598675],"domain_scores_gemma":[0.9998388,0.00003403964,0.00002682484,0.00003169018,0.00005324403,0.00001532782],"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":[0.0003187591,0.00016222,0.003657331,0.0001760747,0.0002234704,0.0002124346,0.0001000929,0.1330547,0.06728479,0.003588255,0.006555768,0.7846662],"study_design_scores_gemma":[0.000009291726,0.000164242,0.003279092,0.00001924457,0.00008078441,0.0001612504,0.00002795645,0.9617866,0.02842528,0.003201717,0.002816148,0.00002834643],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0573212,0.001597863,0.932266,0.0002459834,0.0002241396,0.0001017888,0.0005725812,0.003633425,0.004036975],"genre_scores_gemma":[0.7898551,0.000939285,0.2015889,0.000370023,0.00009265426,0.0001187639,0.001303578,0.00009681529,0.005634913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00939027,"threshold_uncertainty_score":0.01867121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.120933301235973,"score_gpt":0.3177869640975022,"score_spread":0.1968536628615292,"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."}}