# Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

> Research article (2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022) · cited 24× · AI/ML

**Wikidata**: [openalex:W4312438304](https://www.wikidata.org/wiki/openalex:W4312438304)  
**Source**: https://4ort.xyz/entity/modeling-motion-with-multi-modal-features-for-text-based-video-segmentation