CVPRAAAIECCV顶会论⽂代码
⼀,CVPR/AAAI/ECCV顶会论⽂/代码
本页⾯是⾃⼰学习时候,觉得有⽤的⼀些⽂章,暂时MARK⼀下,⽤得着的地⽅就再细看。⽬标检测、 图像分割、⼈脸识别、 ⽬标跟踪、三维点云、 图像处理、 图像分类、 姿态估计、 视频分析、 OCR
、GAN、⼩样本&零样本、 弱监督&⽆监督、神经⽹络、 模型压缩、NAS、 视觉常识
1.cvpr20200
1. 压缩⽅⾯
2. NAS⽅⾯
A Semi-Supervid Asssor of Neural Architectures
3. ⽬标检测
排⾏榜:
4. ⼈脸识别
摆姿势英语怎么说
Towards Universal Reprentation Learning for Deep Face Recognition
collision cour
论⽂地址:arxiv/abs/2002.11841
论⽂分析:
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
论⽂地址:arxiv/abs/2002.10392
代码:/kaiwang960112/Self-Cure-Network
Face X-ray for More General Face Forgery Detection
论⽂地址:arxiv/pdf/1912.13458.pdf
基于元学习的泛化⼈脸识别(CVPR2020 oral)
Learning Meta Face Recognition in Unen Domains
论⽂地址
5. ⽆监督学习
A Simple Framework for Contrastive Learning of Visual Reprentation()
论⽂地址:arxiv/pdf/2002.05709.pdf
代码:
永别了武器
Kaiming He的Momentum Contrast for Unsupervid?何凯明的⽆监督⽅⾯2篇
a.
代码地址:
b.
6. OCR识别
match pointABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
论⽂地址:
报纸平面广告代码地址:
carry是什么意思英语7. 图像和谐化
“DoveNet: Deep Image Harmonization via Domain Verification”
⽂章地址:
代码地址:
8.迁移
Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations(CVPR oral)
论⽂地址:
cet6真题代码地址:/cuishuhao/BNM
9.视觉常识
Visual Commonn R-CN
论⽂地址:
代码地址:
神谴10.Gradient 优化
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
论⽂地址:
代码地址:
大连日语翻译
奥克利论⽂解读:
Reference