# Lightweight dense video captioning with cross-modal attention and knowledge-enhanced unbiased scene graph

> Research article (Complex & Intelligent Systems, 2023) · cited 29× · AI/ML

**Wikidata**: [openalex:W4321605134](https://www.wikidata.org/wiki/openalex:W4321605134)  
**Source**: https://4ort.xyz/entity/lightweight-dense-video-captioning-with-cross-modal-attention-and-knowledge-enhanced-unbiased-scene-graph