几篇有趣的DL文章

1. Fashion Landmark Detection in the Wild
   
   • 研究基于CNN的Visual Fashion analysis
   • http://arxiv.org/abs/1608.03049
   • ECCV 2016
2. Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics
   
   • 研究基于CNN显微观察下的病情诊断
   • http://arxiv.org/abs/1608.02989
   • MLHC 2016
3. 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
   
   • 研究基于CNN的在二维图像上进行三维姿态估计
   • http://arxiv.org/abs/1608.03075
   • Submitted to ECCV 2016 workshop
4. DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
   
   • 基于CNN识别人体动作(Action)
   • http://arxiv.org/abs/1608.03217
   • CVPR 2016
5. Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation
   
   • 研究基于CNN的在放射图像上的病情诊断
   • http://arxiv.org/abs/1608.03235
   • MICCAI-Medical Computer Vision 2016
6. A Dataset for Real Low-Light Image Noise Reduction
   
   • 介绍无压缩的彩色图片集，图片的噪声都是在弱光条件下自然的产生的。
   • http://arxiv.org/abs/1409.8230
7. Robust Object Tracking with a Hierarchical Ensemble Framework
   
   • 多层级架构的目标跟踪检测，实验效果不错
   • http://arxiv.org/abs/1509.06925
8. A 58.6mW Real-Time Programmable Object Detector with Multi-Scale Multi-Object
   Support Using Deformable Parts Model on 1920x1080 Video at 30fps
   
   • 高效目标检测，可编程的加速器
   • http://arxiv.org/abs/1607.08635
9. Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
   
   • 基于CNN的手绘图案识别
   • http://arxiv.org/abs/1608.03369
   • Accepted at ACMMM 2016
   • Code and models https://github.com/val-iisc/sketch-object-recognition