# MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering

> Research article (Findings of the Association for Computational Linguistics: EMNLP 2021, 2021) · cited 16× · AI/ML

**Wikidata**: [openalex:W3212037738](https://www.wikidata.org/wiki/openalex:W3212037738)  
**Source**: https://4ort.xyz/entity/mirtt-learning-multimodal-interaction-representations-from-trilinear-transformers-for-visual-question-answering