X 2 -VLM: All-In-One Pre-trained Model For Vision-Language Tasks
X 2 -VLM: All-In-One Pre-trained Model For Vision-Language Tasks
Yan Zeng,Xinsong Zhang,4 Authors,E. Zurich
2022
84 Citations
TLDR
This paper presents X 2 -VLM, a pre-trained VLM with a modular architecture for both image-text tasks and video-text tasks, and shows that the modular design of X 2 -VLM results in high transferability for X 2 -VLM to be utilized in any language or domain.