# AVQA: A Dataset for Audio-Visual Question Answering on Videos

> Research article (Proceedings of the 30th ACM International Conference on Multimedia, 2022) · cited 49× · AI/ML

**Wikidata**: [openalex:W4304098310](https://www.wikidata.org/wiki/openalex:W4304098310)  
**Source**: https://4ort.xyz/entity/avqa-a-dataset-for-audio-visual-question-answering-on-videos