# Bottom-Up and Top-Down Attention for Image Captioning and VQA.

> Research article (arXiv (Cornell University), 2017) · cited 282× · AI/ML

**Wikidata**: [openalex:W2737766105](https://www.wikidata.org/wiki/openalex:W2737766105)  
**Source**: https://4ort.xyz/entity/bottom-up-and-top-down-attention-for-image-captioning-and-vqa