作者位次 #4/6ACL 2026Poster· Natural Language Processing
Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification
Jiayu Zhang · Shuo Ye · Qilang Ye · Zihan Song · JIAJIAN HUANG · Zitong Yu
摘要
Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling missing modalities, suffering from severe performance degradation in real-world scenarios with data interruptions. Furthermore, prevailing methods f...