{"id":"W4402727350","doi":"10.1109/cvpr52733.2024.02533","title":"MELFuSION: Synthesizing Music from Image and Language Cues Using Diffusion Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Diffusion; Image (mathematics); Speech recognition; Artificial intelligence; Natural language processing; Computer vision","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":[0.000140234,0.0001275791,0.000131186,0.00008371205,0.0001686145,0.0007330261,0.0002510776,0.00004564985,0.0001103077],"category_scores_gemma":[0.00001139676,0.00009695877,0.00003620397,0.0002066055,0.00003588911,0.001191844,0.0004146474,0.00009691586,0.0000163182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001982294,"about_ca_system_score_gemma":0.00003738788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000316962,"about_ca_topic_score_gemma":0.00001431201,"domain_scores_codex":[0.999027,0.00002649489,0.0001395013,0.0004357561,0.0001848334,0.0001863945],"domain_scores_gemma":[0.999532,0.0001079755,0.00002517186,0.0002491506,0.0000177492,0.00006787981],"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":[0.000002462757,0.00002551214,0.00002466199,0.0001141018,0.00001977058,0.0002360068,0.01424621,0.00008963925,0.4555786,0.01358897,0.0008579757,0.5152161],"study_design_scores_gemma":[0.00005852352,0.000005482952,0.000039762,0.0002836282,0.00001071517,0.0000182025,0.0002902928,0.9765921,0.01256716,0.009696549,0.0002757515,0.0001618774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3735726,0.002586305,0.6193105,0.00035288,0.0001772564,0.00003785749,0.000001300803,0.000319894,0.003641422],"genre_scores_gemma":[0.8283167,0.0000386406,0.1706831,0.000538777,0.0001581779,0.000001537712,0.000001043266,0.00001182097,0.0002502313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9765024,"threshold_uncertainty_score":0.7068588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02904567747215398,"score_gpt":0.2567863527629174,"score_spread":0.2277406752907634,"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."}}