{"id":"W4382318126","doi":"10.1609/aaai.v37i8.26162","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Music and Audio Processing","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Vector Institute","funders":"Mitacs","keywords":"Computer science; Modal; Synchronicity; Artificial intelligence; Representation (politics); Asynchronous communication; Speech recognition; Feature learning; Pattern recognition (psychology); Action (physics); Natural language processing; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007090474,0.0002577513,0.000290386,0.0001732298,0.0005769827,0.0006461045,0.001530048,0.0001074819,0.00004291562],"category_scores_gemma":[0.0004217935,0.0001880594,0.0001052237,0.001840536,0.0002849315,0.0009347628,0.0004967335,0.0004811406,0.0001658547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000071928,"about_ca_system_score_gemma":0.0002271869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003371706,"about_ca_topic_score_gemma":0.000005358727,"domain_scores_codex":[0.9974631,0.00003367841,0.000521494,0.0007147861,0.0007721639,0.0004947694],"domain_scores_gemma":[0.9983008,0.0001344878,0.0004547203,0.0002697403,0.0007379694,0.0001022904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003392123,0.0004363918,0.01861192,0.00048352,0.0001182233,0.00001157449,0.01496523,0.004496851,0.08961874,0.6220825,0.0004778077,0.248358],"study_design_scores_gemma":[0.00008825998,0.0003356346,0.00224191,0.0003132215,0.00001783864,0.00000985143,0.0008154011,0.6219744,0.3489054,0.02485532,0.0001024633,0.0003403234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9376675,0.0000145785,0.04895199,0.002971363,0.0003150884,0.000443992,0.000001237655,0.0007036112,0.008930653],"genre_scores_gemma":[0.99409,0.00003189563,0.005079553,0.0001475726,0.00009525802,0.00003298634,0.000001167283,0.00001970958,0.0005018873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6174775,"threshold_uncertainty_score":0.766884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06273058182013519,"score_gpt":0.3256660684038744,"score_spread":0.2629354865837392,"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."}}