{"id":"W2768513778","doi":"10.1049/iet-cvi.2017.0209","title":"Using mel‐frequency audio features from footstep sound and spatial segmentation techniques to improve frame‐based moving object detection","year":2017,"lang":"en","type":"article","venue":"IET Computer Vision","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Atlantic Canada Opportunities Agency","keywords":"Computer vision; Artificial intelligence; Computer science; Object detection; Segmentation; Frame (networking); Object (grammar); Frame rate","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005905028,0.0002390583,0.0002622382,0.0001699201,0.000716495,0.001414232,0.0006193161,0.0001512021,0.000002062235],"category_scores_gemma":[0.0000717087,0.0002263832,0.00007759997,0.0001130032,0.00004646738,0.0009166921,0.0004281073,0.0002167282,0.000004094028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009738978,"about_ca_system_score_gemma":0.00003884623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002158242,"about_ca_topic_score_gemma":0.0004812162,"domain_scores_codex":[0.9981927,0.0002052884,0.0002685797,0.0007196373,0.0003343004,0.0002794749],"domain_scores_gemma":[0.9984101,0.00018774,0.0002728965,0.0008939425,0.0001247205,0.0001106041],"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":[0.00002304116,0.0000239368,0.002362052,0.0000158332,0.00001527535,0.00001365006,0.000280531,0.0001699152,0.1997378,0.00003020698,0.00001991433,0.7973078],"study_design_scores_gemma":[0.0007267852,0.0008391673,0.1765051,0.0002376185,0.00002231314,0.00002005506,0.000007835593,0.4086949,0.3997821,0.01247584,0.00009303123,0.0005952303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2397941,0.00004058157,0.7583687,0.0001871295,0.001080242,0.0002790184,0.000004837867,0.0002095143,0.00003584195],"genre_scores_gemma":[0.5431235,0.000002311498,0.4563275,0.0002190327,0.0003071836,0.00000517691,0.000002396327,0.00001123063,0.000001581689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7967126,"threshold_uncertainty_score":0.9996224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02854742020753184,"score_gpt":0.3418109144867181,"score_spread":0.3132634942791863,"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."}}