{"id":"W2980950444","doi":"10.1109/jsen.2019.2947446","title":"Human Action Recognition Using Deep Multilevel Multimodal (${M}^{2}$ ) Fusion of Depth and Inertial Sensors","year":2019,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Discriminative model; Feature extraction; Leverage (statistics); Modality (human–computer interaction); Sensor fusion; Support vector machine; Fuse (electrical); Deep learning; 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":[0.0003933923,0.001422654,0.001001072,0.0008859544,0.00022725,0.0005563635,0.001008819,0.0007424057,0.003847703],"category_scores_gemma":[0.00097739,0.0002785853,0.0009029997,0.0006352179,0.0003411872,0.001138596,0.001829168,0.0008539521,0.001262311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004995615,"about_ca_system_score_gemma":0.0004860211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005841126,"about_ca_topic_score_gemma":0.01006204,"domain_scores_codex":[0.9996289,0.00003409164,0.00001424416,0.0001380417,0.0001099042,0.00007479551],"domain_scores_gemma":[0.9998548,0.00002592455,0.00002650862,0.0000282465,0.00004345422,0.00002104084],"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":[0.0005042501,0.0003022498,0.004864395,0.0002410902,0.0002456442,0.0002807995,0.0001242748,0.05640348,0.04895325,0.003501209,0.01391367,0.8706656],"study_design_scores_gemma":[0.0000294136,0.000324528,0.00923041,0.0000642718,0.0001066352,0.0004050413,0.000108527,0.9411473,0.03357283,0.008374361,0.006574058,0.0000626709],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06925413,0.002049277,0.9099293,0.0004516608,0.0002769814,0.0001682903,0.002464239,0.008862272,0.006543846],"genre_scores_gemma":[0.7415444,0.001185332,0.2441363,0.0007435369,0.0001752346,0.0002578227,0.004477995,0.0001831884,0.007296241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005841126,"threshold_uncertainty_score":0.0128718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0594790668387138,"score_gpt":0.3036822526663079,"score_spread":0.2442031858275941,"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."}}