Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

This paper proposes a unified vision-language model that combines images and videos into a single feature space, resulting in improved performance on various visual-language tasks compared to models that treat images and videos separately.

https://arxiv.org/abs//2311.10122

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers