{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001562748,0.00006216473,0.00004902352,0.00006008642,0.0001175258,0.0006821093,0.0001942652,0.00003414109,0.00001268832],"category_scores_gemma":[0.00001468972,0.00005382192,0.00005558324,0.0002049505,0.00001585743,0.0006542132,0.00002126463,0.00004168117,0.0001063555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004793319,"about_ca_system_score_gemma":0.00004531132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000272607,"about_ca_topic_score_gemma":0.000002476898,"domain_scores_codex":[0.9993669,0.000006464929,0.00008372234,0.0002862076,0.0001064428,0.0001502908],"domain_scores_gemma":[0.9997565,0.00002627491,0.00001886702,0.0001212882,0.00004660884,0.000030473],"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":[0.000007501894,0.0000402018,0.0003819744,0.0002192624,0.00002142437,0.000005072071,0.0004752716,0.00004084329,0.1535221,0.0115827,0.002206814,0.8314968],"study_design_scores_gemma":[0.0002125423,0.00009222225,0.008266993,0.00006458988,0.000007635305,0.00001654656,0.00007495348,0.9216935,0.06183064,0.002423948,0.005114094,0.0002023393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1022364,0.0003006086,0.8942702,0.001209907,0.0005161754,0.00009277683,0.000001023428,0.0003775535,0.0009952559],"genre_scores_gemma":[0.9189025,0.000005060157,0.07577927,0.00009660247,0.00005264845,0.00002192152,0.000008878592,0.000006941571,0.005126233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9216527,"threshold_uncertainty_score":0.6577595,"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."}}