# VicTR: Video-conditioned Text Representations for Activity Recognition

> Research article (2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024) · cited 22× · AI/ML

**Wikidata**: [openalex:W4402727584](https://www.wikidata.org/wiki/openalex:W4402727584)  
**Source**: https://4ort.xyz/entity/victr-video-conditioned-text-representations-for-activity-recognition