Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

A comprehensive collection of IQA papers

ImageBind One Embedding Space to Bind Them All

Visual Instruction Tuning with Polite Flamingo🦩

A large-scale 7B pretraining language model developed by Baichuan

Code for the paper 'Dynamic Multimodal Fusion'

Cross-modal few-shot adaptation with CLIP

食铁兽（feater.top）ffmpeg4入门系列教程代码

使用Bert，ERNIE，进行中文文本分类

VRT: A Video Restoration Transformer (official repository)

RepVGG: Making VGG-style ConvNets Great Again

This is an official implementation for "Video Swin Transformers".

Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(2020) paper

Research Code for NeurIPS 2020 Spotlight paper "Large-Scale Adversarial Training for Vision-and-Language Representation Learning": UNITER adversarial training part

Research code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"

Multi Task Vision and Language

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

[ACL 2020] PyTorch code for MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning

Vision-Language Pre-training for Image Captioning and Question Answering

静默活体检测（Silent-Face-Anti-Spoofing）

Code and information for face image quality assessment with SER-FIQ

Multitask Multilingual Multimodal Pre-training

CVPR 2020 论文开源项目合集

Code voor mijn Master project omtrent VideoBERT

The source code of ACL 2020 paper: "Cross-Modality Relevance for Reasoning on Language and Vision"

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, CVPR, Oral, 2020

Light-LPR是一个瞄准可以在嵌入式设备、手机端和普通的x86平台上运行的车牌识别开源项目，旨在支持各种场景的车牌识别,车牌字符识别准确率超99.95%，综合识别准确率超过99%，支持目前国内所有的车牌识别，觉得好用的一定要加星哦。

An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations.

1M人脸检测模型(含关键点)