# MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition

> Research article (2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022) · cited 123× · AI/ML

**Wikidata**: [openalex:W3194397797](https://www.wikidata.org/wiki/openalex:W3194397797)  
**Source**: https://4ort.xyz/entity/mm-vit-multi-modal-video-transformer-for-compressed-video-action-recognition