{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048735,0.0003227578,0.0003366261,0.0003067174,0.0008186584,0.0008456628,0.000591837,0.00007146634,0.001385497],"category_scores_gemma":[0.000007968534,0.0003186431,0.0001057171,0.000388959,0.00005973897,0.0007240481,0.0005144396,0.0004513174,0.0002646305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006337999,"about_ca_system_score_gemma":0.00006509883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003314182,"about_ca_topic_score_gemma":0.00000958863,"domain_scores_codex":[0.9972446,0.000325791,0.0004813663,0.0008888483,0.000672455,0.0003869486],"domain_scores_gemma":[0.9988077,0.0001113205,0.0002841302,0.0004499593,0.0001792579,0.0001676905],"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":[0.00002767513,0.0002421463,0.0004896585,0.0001002596,0.00002795096,0.0001083872,0.001011941,0.0001397064,0.002313932,0.0008085313,0.01819372,0.9765361],"study_design_scores_gemma":[0.001861317,0.000945842,0.005124843,0.0002731449,0.00002934325,0.0003931544,0.0001285043,0.9627748,0.001213062,0.02344784,0.002776012,0.001032127],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1783242,0.00002801812,0.8151503,0.002669497,0.001517487,0.0002937778,0.00002458854,0.0002518148,0.001740377],"genre_scores_gemma":[0.9848284,0.00004034393,0.006413164,0.008002577,0.0002681654,0.00006052803,0.0001143711,0.00002559735,0.000246906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.975504,"threshold_uncertainty_score":0.9999266,"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."}}