# VisualGPT: Data-efficient Image Captioning by Balancing Visual Input and Linguistic Knowledge from Pretraining

> Research article (arXiv (Cornell University), 2021) · cited 11× · AI/ML

**Wikidata**: [openalex:W3129503315](https://www.wikidata.org/wiki/openalex:W3129503315)  
**Source**: https://4ort.xyz/entity/visualgpt-data-efficient-image-captioning-by-balancing-visual-input-and-linguistic-knowledge-from-pretraining