{"id":"W3206818284","doi":"10.48550/arxiv.2110.07082","title":"The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Perception; Lossy compression; Benchmark (surveying); Supervised learning; Representation (politics); Transformation (genetics); Feature learning; Machine learning; Artificial neural network; 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":[0.002560765,0.001137761,0.0006248435,0.0004407384,0.0003883868,0.0008878151,0.001476327,0.0009839818,0.001735635],"category_scores_gemma":[0.01096952,0.0003033836,0.0006808058,0.0004535544,0.001125336,0.002389125,0.001629418,0.002427978,0.0007780967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005792149,"about_ca_system_score_gemma":0.0007392171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002363058,"about_ca_topic_score_gemma":0.003716318,"domain_scores_codex":[0.9988463,0.000478533,0.00005095956,0.0003510375,0.0001850556,0.00008816383],"domain_scores_gemma":[0.9957788,0.002309897,0.0002517918,0.00104052,0.0004626402,0.0001564346],"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":[0.0008814501,0.0007536965,0.005827618,0.0003813553,0.0002281751,0.0001378744,0.0002352843,0.3716578,0.0472079,0.007908844,0.006702972,0.5580772],"study_design_scores_gemma":[0.00002143531,0.0002039772,0.000768163,0.00002187328,0.00002081804,0.00006557766,0.0000319714,0.9814921,0.01236204,0.003594778,0.001405387,0.00001176597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1673804,0.002211401,0.8176901,0.0007842053,0.0002600076,0.0002283635,0.0003987986,0.005112802,0.005933964],"genre_scores_gemma":[0.7811509,0.000540718,0.2122251,0.0004010517,0.0001418129,0.0001930039,0.001179877,0.0004086591,0.003758832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002560765,"threshold_uncertainty_score":0.01354277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08479737383591522,"score_gpt":0.248482000304569,"score_spread":0.1636846264686537,"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."}}