{"id":"W3214261769","doi":"","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Temporal Synchronicity","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Synchronicity; Computer science; Modal; Modalities; Representation (politics); Artificial intelligence; Speech recognition; Asynchronous communication; Audio visual; Feature learning; Pattern recognition (psychology); Natural language processing; Machine learning; Psychology","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":[0.001228118,0.001581503,0.001016278,0.0007926985,0.0003743882,0.0009763829,0.002928365,0.001639944,0.003752117],"category_scores_gemma":[0.004657698,0.0005845437,0.001142509,0.000896721,0.0009584109,0.002089543,0.002354466,0.002751541,0.00202132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007103132,"about_ca_system_score_gemma":0.0009549104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003621916,"about_ca_topic_score_gemma":0.005648771,"domain_scores_codex":[0.9991154,0.0002081559,0.00002895918,0.0004013704,0.000148593,0.00009752581],"domain_scores_gemma":[0.9986234,0.0004186703,0.0001576441,0.0004492988,0.0002406132,0.0001104366],"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":[0.0007084096,0.0005657425,0.002099198,0.000302061,0.0002717727,0.0001922901,0.000192965,0.3381816,0.03084685,0.007393078,0.02592216,0.5933239],"study_design_scores_gemma":[0.00002259602,0.00008129553,0.0002522022,0.000009973829,0.00001430123,0.0000423639,0.00001524584,0.9897475,0.003874543,0.004873726,0.00105638,0.000009827809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04389897,0.0006899228,0.9412658,0.0003890835,0.0001760796,0.0001085733,0.0008820453,0.008706734,0.00388276],"genre_scores_gemma":[0.7113932,0.0003390709,0.2667023,0.0008503687,0.0002861803,0.0003668927,0.00705676,0.0008921447,0.01211298],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003752117,"threshold_uncertainty_score":0.01255208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04758006904470114,"score_gpt":0.2186203644114222,"score_spread":0.1710402953667211,"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."}}