{"id":"W3215180973","doi":"10.1109/cvpr52688.2022.00337","title":"Sound-Guided Semantic Image Manipulation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea","keywords":"Embedding; Computer science; Image (mathematics); Encoder; Representation (politics); Artificial intelligence; Modal; Space (punctuation); Sound (geography); Computer vision; Speech recognition; Acoustics","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":[0.0003057448,0.001031098,0.0006889665,0.0005833052,0.0002488571,0.0008087264,0.001303933,0.0009157547,0.005058882],"category_scores_gemma":[0.001171422,0.0002790494,0.001303337,0.0005269264,0.001001067,0.002232197,0.001361727,0.001424234,0.001494296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004379389,"about_ca_system_score_gemma":0.0004414368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001572402,"about_ca_topic_score_gemma":0.002562182,"domain_scores_codex":[0.9996729,0.00005250231,0.00001267929,0.0001330771,0.0000831681,0.00004574836],"domain_scores_gemma":[0.999729,0.00009255402,0.00002982961,0.00008448085,0.00004342137,0.00002081599],"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":[0.0005213478,0.0003146857,0.0006515114,0.000439641,0.0001167751,0.0002601207,0.0003348484,0.09895167,0.1195997,0.04274591,0.01047708,0.7255867],"study_design_scores_gemma":[0.00002678428,0.0001369753,0.0004760964,0.0000267007,0.00004374422,0.0001760397,0.00006696009,0.9372942,0.03392729,0.02002595,0.007770814,0.00002839901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01784768,0.0007366356,0.9742041,0.0002029985,0.0001428747,0.00006589077,0.0001929842,0.002613572,0.003993339],"genre_scores_gemma":[0.5968725,0.001334388,0.3756466,0.0005041697,0.0002797411,0.0002345956,0.001340128,0.0006621507,0.02312565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005058882,"threshold_uncertainty_score":0.01692367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.074580362166011,"score_gpt":0.295785068282097,"score_spread":0.221204706116086,"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."}}