Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

A Simple Framwork for CV Pre-training Model (SOCO, VirTex, BEiT)

[CVPR2022 Oral] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

[ICCV2021] 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

[ICCV 2019] FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos