论文 - 开源代码 - 软著 - 专利 - 论著
Stage: Mainly engaged in low-quality multi-scale image quantization convolution and MIPS architecture chip algorithm design, based on RSIC-V architecture(主要从事低质量多尺度图像量化卷积和MIPS架构芯片算法设计:):
The main task of this project is to improve the combination of research and engineering through academic guidance on the notes of systematic problems in experimental engineering, and through the core course of QAS in-depth learning(该项工作主要是提高自己研究中与工程学结合通过学术指导实验工程学上系统问题笔记,通过QAS的深度学习的核心教程):
GMM https://petewarden.com/2015/04/20/why-gemm-is-at-the-heart-of-deep-learning/
Opencv https://docs.opencv.org/3.4.5/d9/df8/tutorial_root.html
Opencv https://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/tutorials.html
目标检测(object detection):https://machinethink.net/blog/object-detection/
国际信息神经处理会议(Conference and Workshop on Neural Information Processing Systems)NIPS :https://papers.nips.cc/book/advances-in-neural-information-processing-systems-31-2018
深度学习研究方向性会议ICLR :https://openreview.net/group?id=ICLR.cc/2019/Conference
国际计算机视觉模式识别CVPR :https://cvpr2019.thecvf.com/
国际计算机视觉会议ICCV :https://iccv2019.thecvf.com/
欧洲计算机视觉会议ECCV :https://eccv2018.org/
国内经典的基础教材南瓜书:https://datawhalechina.github.io/pumpkin-book/#/
https://github.com/Dikea/ML-Weekly-Learning/tree/master/CV
https://github.com/Eric3911/Code-with-Life
https://github.com/Eric3911/Coding-learning
https://github.com/MarkMoHR/Awesome-Edge-Detection-Papers
https://arxiv.org/list/cs.AI/recent
https://github.com/Eric3911/Paper-Sharing
https://github.com/Eric3911/Super-Paper
https://github.com/Eric3911/Engineering-papers
深度学习未来方向之一: 基于非线性动力学结合分数阶非线性方程在群论中模态融合表示,继强化学习之后一种元学习方法及模型安全联邦学习、数据安全区块链。
https://github.com/Eric3911/CDCS
https://github.com/Eric3911/Visual-Science-Competition
https://mmcheng.net/tag/salient-object-detection/
Jim Blinn's Corner: Dirty Pixels
Jim Blinn's Corner: A Trip Down The Graphics Pipeline
Jim Blinn's Corner: Notation, Notation, Notation
光流场和光线追踪在相控矩阵77GHZ的毫米波雷达融合
文字识别使用超分辨和对抗生成宋体后使用FAN/Attention识别最具有工程意义和学术价值,其中金老师做的基于强化学习的模型FOTS模型也是一个很好方向。
https://github.com/chongyangtao/Awesome-Scene-Text-Recognition
https://github.com/Eric3911/icpr2018_ocr_papers
https://github.com/DmitryUlyanov/deep-image-prior
Note:近期不知道什么原因目前github实验结果图没法显示,我正在查找原因解决。 https://opensource.org/licenses/MIT