{"id":"W4409347241","doi":"10.1609/aaai.v39i15.33770","title":"Few-Shot Audio-Visual Class-Incremental Learning with Temporal Prompting and Regularization","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China; Institute for Catastrophic Loss Reduction","keywords":"Audio visual; Shot (pellet); Class (philosophy); Computer science; Regularization (linguistics); Artificial intelligence; Computer vision; Computer graphics (images); Speech recognition; Multimedia; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001566379,0.0015274,0.001382776,0.0006863248,0.0004590384,0.001196168,0.004463767,0.001855231,0.003675015],"category_scores_gemma":[0.005941334,0.0005634014,0.0009837183,0.0007666298,0.0008672047,0.002337838,0.002809867,0.003148669,0.001032001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009606764,"about_ca_system_score_gemma":0.001732573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005119877,"about_ca_topic_score_gemma":0.007015127,"domain_scores_codex":[0.9990006,0.0001671536,0.00004220734,0.0004348035,0.0002309605,0.0001244243],"domain_scores_gemma":[0.9980612,0.0008586254,0.000155406,0.0003924271,0.0003510089,0.0001812919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005834822,0.0004882987,0.002622652,0.000549082,0.0001587169,0.0002307823,0.0002709037,0.2663914,0.02418762,0.0075693,0.01126393,0.685684],"study_design_scores_gemma":[0.00002463251,0.0000832708,0.0002647977,0.00001149759,0.0000176847,0.00005483274,0.00002275002,0.9901319,0.004222978,0.004258459,0.0008944114,0.00001277906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05593336,0.001252716,0.9326597,0.0004209994,0.0002077171,0.0002245007,0.0004224296,0.005905531,0.00297317],"genre_scores_gemma":[0.7017283,0.0004593134,0.2878711,0.0007964785,0.0001820858,0.0003703413,0.002157837,0.0004173814,0.006017138],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005119877,"threshold_uncertainty_score":0.01229417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04107647709409171,"score_gpt":0.2939509568040334,"score_spread":0.2528744797099416,"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."}}