ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision | Neural Imaging Computation and Analysis Group (NICA)

Topic: ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Speaker: Cheng Xinyu
Date: 9:00 A.M., Friday, Sep 17, 2021
Place: The Fourth Meeting Room in Intelligent Building

Abstract

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

PreviewTips

Download

To download attachments, please log in.

Last Modified: 2021/11/30 11:06 | Author: Cheng Xinyu