Name: Perseus Xi
Type: User
Company: Honor Device Co., Ltd
Bio: Remote Sensing PHD , graduated from University of Science and Technology of China , interested in Object Decection, Segmentation, Machine Learning, Computer Vis
Location: ShenZhen China
Blog: https://scholar.google.com.hk/citations?hl=zh-CN&tzom=-480&user=O2fKV2cAAAAJ
Perseus Xi's Projects
PyTorch implementation for 3D CNN models for medical image data (1 channel gray scale images).
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
Code for https://arxiv.org/abs/1611.10080
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记
An open autonomous driving platform
Note for Apollo 3.0 perception, prediction and planning modules
a Lightweight Deep Neural Network for Face Alignment and Pose Estimation
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, CVPR, Oral, 2020
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
The bottom layer is Python implementation and the top layer is PyQt. Programming language Python
手写Bundle Adjustment 优化代码,当前版本是没有优化point pose的,即只优化位姿
A paper list of lane detection.
Reinforcement learning resources curated
Curated Reinforcement Learning Resources for Natural Language Processing
Summary of related papers on visual attention. Related code will be released based on Jittor gradually.
[CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427
Learning One Class Representations for Presentation Attack Detection using Multi-channel Convolutional Neural Networks
Character-level Convolutional Networks for Text Classification论文仿真实现
README and scripts for the Cityscapes Dataset
CodaLab Competitions
long way to go
using one commodity image generates a short frames
Corner Proposal Network for Anchor-free, Two-stage Object Detection