{"id":"W3077098836","doi":"10.3390/s20174673","title":"Energy-Guided Temporal Segmentation Network for Multimodal Human Action Recognition","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China-Henan Joint Fund; National Natural Science Foundation of China; Nanyang Technological University","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Construct (python library); Pattern recognition (psychology); Task (project management); Energy (signal processing); Action recognition; Action (physics); Machine learning; Frame (networking); Class (philosophy); Mathematics","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":[0.0001041297,0.0001228207,0.0001172829,0.00005397354,0.0003513992,0.000159037,0.0001282882,0.00007195085,0.00005059406],"category_scores_gemma":[0.00001618079,0.0001321539,0.00008961344,0.0002068924,0.00001911557,0.0004376023,0.00002565108,0.00007528486,0.00008065633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004164222,"about_ca_system_score_gemma":0.00002367471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005764625,"about_ca_topic_score_gemma":0.00004257799,"domain_scores_codex":[0.9989884,0.00007191186,0.0002436738,0.0003327043,0.0001548465,0.0002084061],"domain_scores_gemma":[0.9995003,0.00004188718,0.0001444494,0.0001162967,0.0001106401,0.0000864227],"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":[0.0002024382,0.0002876068,0.001013687,0.0001835215,0.0001925843,0.00002628353,0.004333675,0.006715739,0.08028831,0.007878194,0.09117708,0.8077009],"study_design_scores_gemma":[0.003882858,0.0008735037,0.001753198,0.00007634861,0.00007576241,0.00003046925,0.0004731597,0.7276278,0.1857463,0.03050945,0.04787767,0.001073505],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5317432,0.000009267417,0.4646574,0.001401561,0.0005801924,0.0003655223,0.00001717264,0.0004865204,0.0007391496],"genre_scores_gemma":[0.9606646,0.000006645494,0.03550077,0.002021225,0.001100782,0.00005492955,0.0003704652,0.00001755554,0.0002630232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8066274,"threshold_uncertainty_score":0.5389079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09490681399533432,"score_gpt":0.3094997564524858,"score_spread":0.2145929424571515,"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."}}