{"id":"W4400527613","doi":"10.1109/fg59268.2024.10581998","title":"Dynamic Cross Attention for Audio-Visual Person Verification","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Audio visual; Speech recognition; Human–computer interaction; Multimedia","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":[0.002211333,0.001333692,0.001285553,0.001367173,0.0005127347,0.0009509325,0.00263833,0.001438473,0.00592016],"category_scores_gemma":[0.003295972,0.0004545737,0.00109622,0.0009137852,0.000578507,0.001733695,0.002648842,0.001808062,0.002302628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156935,"about_ca_system_score_gemma":0.001103191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01454336,"about_ca_topic_score_gemma":0.01481047,"domain_scores_codex":[0.9990076,0.0001714876,0.00003367661,0.0004032473,0.0001956728,0.0001882343],"domain_scores_gemma":[0.9991109,0.0003803738,0.00006471329,0.0001773336,0.0002055129,0.00006121143],"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":[0.001212773,0.0004554015,0.003612441,0.0002426417,0.0002752216,0.0002895172,0.0001335672,0.099206,0.03563961,0.00500265,0.01369779,0.8402324],"study_design_scores_gemma":[0.0000244002,0.0001343193,0.002039096,0.00002710002,0.00008257867,0.0002088668,0.00002941837,0.9788867,0.01134633,0.004307253,0.002892944,0.00002098578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1055148,0.007907089,0.861361,0.0008333494,0.0006239779,0.0002375906,0.00117895,0.01110729,0.01123585],"genre_scores_gemma":[0.8750356,0.001243346,0.1083324,0.0008454776,0.0003276819,0.0001302328,0.002582815,0.0003290834,0.01117347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01454336,"threshold_uncertainty_score":0.02891743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01849233654056868,"score_gpt":0.3276650553686752,"score_spread":0.3091727188281065,"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."}}