{"id":"W4404775376","doi":"10.1049/cit2.12375","title":"Feature pyramid attention network for audio‐visual scene classification","year":2024,"lang":"en","type":"article","venue":"CAAI Transactions on Intelligence Technology","topic":"Music and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province","keywords":"Pyramid (geometry); Audio visual; Computer science; Artificial intelligence; Feature (linguistics); Computer vision; Pattern recognition (psychology); Multimedia; Mathematics","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":[0.0002097058,0.0001888086,0.0001701956,0.0004327654,0.000378387,0.0002028348,0.0005878887,0.0003402439,0.00002546874],"category_scores_gemma":[0.00001734891,0.0001795163,0.0001284831,0.00164525,0.0001738996,0.0003586518,0.00001053053,0.0004690548,0.0001278572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001154998,"about_ca_system_score_gemma":0.00010497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001355946,"about_ca_topic_score_gemma":0.000005248657,"domain_scores_codex":[0.9985728,0.00001941316,0.0002267914,0.0006394206,0.0001530021,0.0003885289],"domain_scores_gemma":[0.9992529,0.00009999143,0.00006258783,0.0004120895,0.0001202547,0.00005213194],"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":[0.000007947274,0.0000494692,0.000009396251,0.00006514183,0.00002943621,0.000004549944,0.00005381081,0.001313283,0.002602192,0.08903898,0.002475998,0.9043498],"study_design_scores_gemma":[0.0001176702,0.0004532228,0.0000914261,0.00048203,0.00006103895,0.0001179165,0.0002212652,0.778997,0.05900413,0.09972665,0.06020654,0.000521132],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008617608,0.0008443329,0.9735088,0.02128129,0.001525127,0.000304017,0.000005730527,0.001434908,0.0002339748],"genre_scores_gemma":[0.9180292,0.000183137,0.07920733,0.0003484352,0.0001645581,0.0002586929,0.000008752665,0.0000250936,0.001774835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9171674,"threshold_uncertainty_score":0.7320461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02904321832120359,"score_gpt":0.3099807059072142,"score_spread":0.2809374875860106,"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."}}