papers-summary

About

This respository contains a list of papers about computer vision and artificial intellegence. A small summary is written for each paper.

Created on 2016/12/14

• Style Transfer:

  • Optimization-based Method:
    • A Neural Algorithm of Artistic Style
    • Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
    • Fast Patch-based Style Transfer of Arbitrary Style
    • Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork
    • Painting Style Transfer for Head Portraits using Convolutional Neural Networks
  • Feed Forward Method:
    • Perceptual Losses for Real-Time Style Transfer and Super-Resolution
    • Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
    • Texture Synthesis Using Convolutional Neural Networks
    • Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
    • Instance Normalization: The Missing Ingredient for Fast Stylization
  • Analysis
    • Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity
    • Demystifying Neural Style Transfer
    • Exploring the Neural Algorithm of Artistic Style
  • Ehancement
    • Controlling Perceptual Factors in Neural Style Transfer
    • Preserving Color in Neural Artistic Style Transfer
    • A Learned Representation for Artisctic Style
  • Recently Proposed Traditional Method
    • Style Transfer for Headshot Portraits
    • Split and Match: Example-based adaptive Patch Sampling for Unsupervised Style Transfer
  • Videos
    • Artistic style transfer for videos
  • Recent Method
    • Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
    • Deep Photo Style Transfer

• Added on 2017/03/17

  • Wasserstain GAN
  • Loss Sensitive GAN
  • Generative Temporal Models with Memory
  • Playing atari with deep reinforcement learning
  • Human-level control through deep reinforcement learning
  • Continuous control with deep reinforcement learning

• Added on 2017/02/08

  • Generating images with recurrent adversarial networks
  • Deeply-Supervised Nets

• Added on 2016/12/22

  • Visualizing and Understanding Convolutional Networks
  • Pixel Recurrent Neural Networks
  • Sequence to Sequence Learning with Neural Networks
  • Long short-term memory

• Added on 2016/12/14

  • papers about generative adversarial nets
    • Generative Adversarial Nets
    • Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
    • Image-to-Image Translation with Conditional Adversarial Networks
  • papers about encoder-decoder nets
    • Conditional Image Generation with PixelCNN Decoders
    • Context Encoders: Feature Learning by Inpainting
    • SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

• Learning Materials

  • Neural Networks for Machine Learning, taught by Hinton
  • Machine Learning, taught by Andrew Ng, here is the course material
  • Build Intelligent Applications, a more advanced machine learning course
  • CS231n:Convolutional Neural Networks for Visual Recognition, a excellent deep learning course in stanford university
  • Deep Learning, MIT deep learning book
  • Reinforcement Learning, taught by David Silver
  • 2016 NIPS
  • GIT Xiv

• Note: The format of Readme.md is borrowed from aluju/papers

Date	Member	Topic
2017.2.21	SU Jinhai	Visualizing and Understanding Convolutional Networks
2017.2.28	CONG Kai	LSTM
2017.4.4	WANG Xianbo	WGAN