Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Learning to Prompt for Vision-Language Models.

PASCAL VOC Object Classification: The goal of this project is to recognize objects from a number of visual object classes in realistic scenes.

Demo code for PVANet

Code to train CLIP model

open Multi-View Stereo reconstruction library

Caffe: a fast open framework for deep learning.