PAPER

PAPER

2017.03.15

ちょっとしたノイズを加えると…あら不思議 – Adversarial examples in the physical world

  • cnn
  • mobile

PAPER

2017.03.13

CRNNで鳥の声の識別 – Convolutional Recurrent Neural Networks for Bird Audio Detection

  • audio
  • cnn
  • rnn

PAPER

2017.03.12

顔写真から肥満度を推定 – Face-to-BMI: Using Computer Vision to Infer Body Mass Index on Social Media

  • society

PAPER

2017.02.11

ビデオのフレーム補間 – Video Frame Synthesis using Deep Voxel Flow

  • convnet
  • video

PAPER

2017.02.10

音源分離 – Deep Clustering and Conventional Networks for Music Separation: Stronger Together

  • audio
  • music

PAPER

2017.02.05

フォントのStyle Transfer? – Awesome Typography: Statistics-Based Text Effects Transfer

  • image
  • styletransfer

PAPER

2017.01.20

AENet: Learning Deep Audio Features for Video Analysis

  • audio
  • convnet
  • video

PAPER

2017.01.08

Learning to Protect Communications with Adversarial Neural Cryptography

  • adversarial

PAPER

2016.12.19

DeepBach: a Steerable Model for Bach chorales generation by Gaëtan Hadjeres, François Pachet

  • generative
  • LSTM
  • music