# Narrations / Steps to Video Aligner (NSVA)

![](./src/model.png)

NSVA is a lightweight Transformer-based architecture, where the narration or procedural steps are used as queries, to iteratively attend the video features, and output the alignability or optimal temporal windows.

[[project page]](https://lzq5.github.io/Video-Text-Alignment/)
[[Arxiv]](https://arxiv.org/abs/2312.14055)
[[GitHub]](https://github.com/Lzq5/Video-Text-Alignment)

We provide pre-trained models for HTM-Align and HT-Step. You can use these two models for reproducing our results, following our [[code]](https://github.com/Lzq5/Video-Text-Alignment).