{"id":"W4402904188","doi":"10.1109/cvprw63382.2024.00190","title":"Towards Efficient Audio-Visual Learners via Empowering Pre-trained Vision Transformers with Cross-Modal Adaptation","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Audio visual; Transformer; Adaptation (eye); Modal; Speech recognition; Artificial intelligence; Domain adaptation; Computer vision; Multimedia; Engineering; Psychology; Electrical engineering; Voltage","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":[],"consensus_categories":[],"category_scores_codex":[0.0003151143,0.0002044419,0.0001492745,0.0001748265,0.0001987866,0.0009596557,0.0003141623,0.00006781973,0.00003408187],"category_scores_gemma":[0.00001054783,0.0001486294,0.00008085075,0.0007100217,0.00008128317,0.0009182947,0.00005337351,0.000180362,0.00003906454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009316162,"about_ca_system_score_gemma":0.0002546909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004263895,"about_ca_topic_score_gemma":0.0000182441,"domain_scores_codex":[0.9982284,0.00002068482,0.0002348186,0.0005712498,0.0005377386,0.0004071272],"domain_scores_gemma":[0.9995762,0.00003422366,0.00003579457,0.0001541749,0.00006606749,0.000133563],"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":[0.0000885979,0.00008271257,0.0001061801,0.0001558583,0.00004531351,0.00007361532,0.008266983,0.05095666,0.03363718,0.0006369779,0.00004992293,0.9059],"study_design_scores_gemma":[0.0004693793,0.0004928006,0.001589068,0.0001647626,0.000008730922,0.00005537408,0.0003084092,0.8913238,0.104621,0.0001732576,0.0004668731,0.0003265556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2953145,0.0001655068,0.7004982,0.0004749907,0.0002805226,0.0001264413,5.239035e-7,0.0005260857,0.002613282],"genre_scores_gemma":[0.9530401,0.000007147381,0.04618561,0.0001019304,0.00008124286,0.00001063872,0.000003479925,0.00001983965,0.0005499605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9055734,"threshold_uncertainty_score":0.9253982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008765059562367266,"score_gpt":0.3076469750364574,"score_spread":0.2988819154740902,"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."}}