# Unicoder-VL: A Universal Encoder for Vision and Language by Cross-Modal Pre-Training

> Research article (Proceedings of the AAAI Conference on Artificial Intelligence, 2020) · cited 744× · AI/ML

**Wikidata**: [openalex:W2998356391](https://www.wikidata.org/wiki/openalex:W2998356391)  
**Source**: https://4ort.xyz/entity/unicoder-vl-a-universal-encoder-for-vision-and-language-by-cross-modal-pre-training