{"id":"W2126374091","doi":"10.1109/icassp.2004.1326578","title":"Interactive video retrieval using embedded audio content","year":2004,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Search engine indexing; Feature (linguistics); Feature vector; Wavelet; Similarity (geometry); Relevance feedback; Mixture model; Artificial intelligence; Scheme (mathematics); Feature extraction; Pattern recognition (psychology); Laplace operator; Digital audio; Wavelet transform; Image retrieval; Audio signal; Image (mathematics); Speech recognition; Mathematics; Speech coding","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":[0.0001453031,0.0001124339,0.0001389832,0.00006383697,0.0001313544,0.0002137629,0.0004020301,0.00003946684,0.00004827253],"category_scores_gemma":[0.00006287439,0.00009164224,0.00005818815,0.0002856439,0.00003809344,0.0008896153,0.0002024868,0.0001222725,0.0000621757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327987,"about_ca_system_score_gemma":0.000153795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005531811,"about_ca_topic_score_gemma":0.000003274693,"domain_scores_codex":[0.999033,0.00001940618,0.0001852023,0.0003115769,0.0002148054,0.0002360419],"domain_scores_gemma":[0.9994123,0.00003293489,0.00009240104,0.000268953,0.0001110281,0.0000824083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002135338,0.0006926066,0.0005696555,0.0001108081,0.0002409402,0.0004038698,0.02409487,0.00712892,0.6898054,0.2037662,0.002570132,0.07040311],"study_design_scores_gemma":[0.002666387,0.0002080111,0.0009668863,0.0003599535,0.00002360633,0.0002446402,0.0008102154,0.05665494,0.9103563,0.02472479,0.002165302,0.0008189655],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1558286,0.00004607438,0.8366068,0.001170175,0.0003897062,0.00007054783,2.499755e-7,0.0001470165,0.005740865],"genre_scores_gemma":[0.8690952,0.000001632238,0.1278723,0.002495826,0.0000849308,4.50426e-7,3.268972e-7,0.00000603819,0.0004433309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7132666,"threshold_uncertainty_score":0.3737062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06486971994848416,"score_gpt":0.2884432812918527,"score_spread":0.2235735613433685,"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."}}