Multi-Class Ranking Based Most Probable Prediction Unit Selection for HEVC Encoding

Linwei ZHU, Sam KWONG, Yun ZHANG, Xu WANG, Shiqi WANG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

1 Citation (Scopus)


In this paper, an incremental learning based multi-class Prediction Units (PUs) ranking approach is presented for High Efficiency Video Coding (HEVC) Rate-Distortion-Complexity (RDC) optimization. In particular, the process of PUs selection is formulated as a binary classification plus multi-class ranking task, and incremental learning is applied for classifier training to better exploit the information in the emerging training data. Furthermore, the proposed most probable PUs selection scheme is incorporated into a joint RDC optimization framework, where the complexity can be flexibly allocated targeting at minimizing computational cost under a constrained RD performance degradation. Experimental results demonstrate that the proposed approach can reduce 53.7% and 50.4% computational complexity on average under low delay P and random access configurations with ignorable RD performance degradation, which outperforms the state-of-the-art approaches in terms of RDC performance.
Original languageEnglish
Title of host publication2017 IEEE Visual Communications and Image Processing (VCIP)
Number of pages4
ISBN (Electronic)9781538604625
ISBN (Print)9781538604632
Publication statusPublished - Dec 2017
Externally publishedYes
Event2017 IEEE Visual Communications and Image Processing (VCIP 2017) - St. Petersburg, United States
Duration: 10 Dec 201713 Dec 2017


Conference2017 IEEE Visual Communications and Image Processing (VCIP 2017)
Country/TerritoryUnited States
CitySt. Petersburg

Bibliographical note

This work was supported in part by the Natural Science Foundation of China under Grant 61672443, 61501299, and 61471348, in part by Hong Kong RGC General Research Fund 9042322 (CityU 11200116), and 9042489 (CityU 11206317), in part by Guangdong Natural Science Funds for Distinguished Young Scholar under Grant 2016A030306022, and in part by Project for Shenzhen Science and Technology Development under Grant JSGG20160229202345378 and Shen-zhen International Collaborative Research Project under Grant GJHZ20170314155404913.


  • high efficiency video coding
  • incremental learning
  • Multi-class ranking
  • prediction unit


Dive into the research topics of 'Multi-Class Ranking Based Most Probable Prediction Unit Selection for HEVC Encoding'. Together they form a unique fingerprint.

Cite this