{"id":"W2091181450","doi":"10.1117/12.476317","title":"Incorporating Audio Cues into Dialog and Action Scene Extraction","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dialog box; Computer science; Audio visual; Classifier (UML); Artificial intelligence; Speech recognition; Action recognition; Action (physics); Audio signal processing; Feature extraction; Computer vision; Audio signal; Multimedia; Speech coding; World Wide Web","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":[0.0008621039,0.0002234125,0.0002987954,0.0001294444,0.0001586144,0.0002616156,0.0005745728,0.0001486039,0.000003321161],"category_scores_gemma":[0.0007145357,0.0001917206,0.0003049421,0.000469879,0.0001163408,0.001449967,0.0001272883,0.0002191494,7.682617e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001280649,"about_ca_system_score_gemma":0.00003485148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001845301,"about_ca_topic_score_gemma":8.546466e-7,"domain_scores_codex":[0.9982603,3.529064e-8,0.0005639505,0.0003989161,0.0005388077,0.0002380452],"domain_scores_gemma":[0.9981179,0.0001087892,0.000451627,0.00006086403,0.001162739,0.0000980942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001127336,0.00005399013,0.001625532,0.0001411894,0.0001371152,4.53902e-8,0.0001799952,0.00009104527,0.3977637,0.5977181,0.0003701266,0.00190786],"study_design_scores_gemma":[0.001646536,0.0005295523,0.005580488,0.0004062113,0.0002787256,0.00005010928,0.001642587,0.4567508,0.4806383,0.04761709,0.003971796,0.0008877738],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9888,0.00009788953,0.00753714,0.001465858,0.0002513768,0.0002455665,0.000002754447,0.00008183374,0.001517546],"genre_scores_gemma":[0.7141356,0.0001234098,0.28532,0.00007005225,0.0001839065,0.00004986545,0.000003858444,0.00002221341,0.00009111054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.550101,"threshold_uncertainty_score":0.7818139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0139327860538024,"score_gpt":0.2414906279017053,"score_spread":0.2275578418479029,"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."}}