# Multimodal feature fusion based on object relation for video captioning

> Research article (CAAI Transactions on Intelligence Technology, 2022) · cited 16× · AI/ML

**Wikidata**: [openalex:W4205717223](https://www.wikidata.org/wiki/openalex:W4205717223)  
**Source**: https://4ort.xyz/entity/multimodal-feature-fusion-based-on-object-relation-for-video-captioning