{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001124011,0.001882047,0.0008403191,0.001749734,0.0004850765,0.001838157,0.001565351,0.001604468,0.00308836],"category_scores_gemma":[0.003644123,0.0004342725,0.001667107,0.001024855,0.0005351617,0.002202256,0.001471529,0.001749591,0.001711578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008904057,"about_ca_system_score_gemma":0.0006087121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008467922,"about_ca_topic_score_gemma":0.01583701,"domain_scores_codex":[0.9994541,0.000121575,0.00003140419,0.0002268733,0.0001162516,0.00004973068],"domain_scores_gemma":[0.9992182,0.0004140712,0.00006464253,0.0001407597,0.0001035748,0.00005856882],"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":[0.001271029,0.0006966157,0.007755421,0.00113717,0.0005369669,0.0003162187,0.0004353065,0.2014737,0.06561641,0.009805459,0.02681974,0.6841359],"study_design_scores_gemma":[0.00007602105,0.0001792393,0.001355388,0.00003825871,0.00006122547,0.0001362711,0.00009179846,0.9721748,0.01371247,0.005944771,0.00618732,0.0000423811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1359184,0.004620687,0.8274124,0.001061976,0.0005153853,0.0005142404,0.007067823,0.01530376,0.007585285],"genre_scores_gemma":[0.4719756,0.001344589,0.5005979,0.0005707951,0.0002072881,0.0003271397,0.01484616,0.00108399,0.009046486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008467922,"threshold_uncertainty_score":0.01683724,"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."}}