{"id":"W4319777521","doi":"10.1109/tai.2023.3243596","title":"Audio Representation Learning by Distilling Video as Privileged Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Music and Audio Processing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Representation (politics); Multimedia; Artificial intelligence; Political science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006985039,0.00108079,0.0005646126,0.0008778145,0.0002845429,0.001003609,0.001440435,0.001051031,0.00276326],"category_scores_gemma":[0.003874073,0.0003953865,0.0007026758,0.00084386,0.0006364253,0.003102365,0.001868422,0.002120581,0.001034888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007967311,"about_ca_system_score_gemma":0.0009410972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004687826,"about_ca_topic_score_gemma":0.006118233,"domain_scores_codex":[0.9994838,0.0001098519,0.00001855553,0.0002040939,0.0001049595,0.00007867243],"domain_scores_gemma":[0.9990556,0.0004088058,0.00009933209,0.0002416664,0.0001359617,0.00005865643],"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":[0.0004117349,0.0002489043,0.001500084,0.0001361399,0.00008354395,0.0001320361,0.0001651839,0.1362355,0.02567913,0.01272943,0.005529204,0.817149],"study_design_scores_gemma":[0.00001953035,0.0001036686,0.0004400178,0.00001820694,0.00002417423,0.00004287407,0.00003923705,0.9700176,0.0115739,0.01537265,0.00233314,0.0000151244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05035019,0.0006738062,0.941964,0.0005330193,0.00009017139,0.00005089244,0.0005178302,0.00281563,0.003004347],"genre_scores_gemma":[0.8177223,0.0006105534,0.1708037,0.0003631701,0.0001839777,0.0001262125,0.001984504,0.0001726847,0.008032997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004687826,"threshold_uncertainty_score":0.009321034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04134158209393263,"score_gpt":0.3015254047184407,"score_spread":0.2601838226245081,"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."}}