# Sketch, Ground, and Refine: Top-Down Dense Video Captioning

> Research article (2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021) · cited 66× · AI/ML

**Wikidata**: [openalex:W3174257385](https://www.wikidata.org/wiki/openalex:W3174257385)  
**Source**: https://4ort.xyz/entity/sketch-ground-and-refine-top-down-dense-video-captioning