iCNN: A Convolutional Neural Network for Fractional Interpolation in Video Coding

EasyChair Preprint no. 1398, version history

Version	Date	Pages	Version notes
1	August 13, 2019	10	—
2	September 4, 2019	10	Table 1, column Without iCNN/DCTIF selection, the average BD-rate of Class F is -0.4% BD-rate compared to HM. Average all sequences which are calculated based on 20 sequences are correct.

Keyphrases: deep learning, Fractional Interpolation, Motion compensated prediction, Motion Compensated Prediction., video coding

BibTeX entry

BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:

@Booklet{EasyChair:1398,
  author = {Chi Do-Kim Pham and Jinjia Zhou},
  title = {iCNN: A Convolutional Neural Network for Fractional Interpolation in Video Coding},
  howpublished = {EasyChair Preprint no. 1398},

  year = {EasyChair, 2019}}