Vision CAIR Research Group, KAUST

VisualGPT, CVPR 2022 Proceeding, GPT as a decoder for vision-language models

Vision-CAIR

Vision-CAIR

Vision-CAIR

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

Vision-CAIR

3DCoMPaT++: An improved large-scale 3D vision dataset for compositional recognition

Vision-CAIR

Official code for MiniGPT4-video

Vision-CAIR

Official repository for the 3DCoMPaT dataset (ECCV2022 Oral)

Vision-CAIR