{"id":"W4386325246","doi":"10.18280/ts.400412","title":"Deep Image Processing for Lower Limb Rehabilitation Training Action and Effect Recognition: GaitSet Algorithm and Full-Field Optical Flow Approaches","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"People's Government of Jilin Province","keywords":"Optical flow; Training (meteorology); Computer science; Artificial intelligence; Action recognition; Computer vision; Action (physics); Image (mathematics); Field (mathematics); Flow (mathematics); Algorithm; Pattern recognition (psychology); Mathematics; Physics; Geometry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007461723,0.0007132113,0.0005569835,0.0009022459,0.00021734,0.0007284283,0.0006879648,0.0008414701,0.001419415],"category_scores_gemma":[0.001146883,0.000291435,0.0006468944,0.0006030449,0.0003984047,0.0007672668,0.0006735101,0.001056723,0.0002861723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004953102,"about_ca_system_score_gemma":0.001195047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002881503,"about_ca_topic_score_gemma":0.003776178,"domain_scores_codex":[0.9998296,0.00002298068,0.00001477447,0.00004270689,0.00006607101,0.00002381555],"domain_scores_gemma":[0.9997808,0.00006591988,0.00003382142,0.00002360066,0.00007250766,0.00002333472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002378232,0.0002637322,0.001943501,0.0001962559,0.0001125085,0.0001422518,0.00008256012,0.1189661,0.0427144,0.008046452,0.003647954,0.8236464],"study_design_scores_gemma":[0.00001261685,0.0001266684,0.001100687,0.00002124874,0.00002071039,0.0001056954,0.00001137854,0.9850231,0.009499883,0.002701224,0.001357647,0.0000189855],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01347842,0.000362637,0.9845544,0.0001586348,0.00007112854,0.00008480437,0.00006459808,0.0004899185,0.0007355091],"genre_scores_gemma":[0.3113398,0.0009357709,0.6820174,0.0003085746,0.0001072814,0.0002932728,0.0003271199,0.0001077488,0.004562937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002881503,"threshold_uncertainty_score":0.005729496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04979899791692938,"score_gpt":0.2971844153295615,"score_spread":0.2473854174126321,"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."}}