Conference
Learning Based Hybrid No-Reference Video Quality Assessment of Compressed Videos
Abstract
A near real-time no-reference video quality assessment method is proposed for videos encoded by H.264/AVC codec. A fully connected neural network is trained with features extracted from both bit-stream and pixel domains along with their respective subjective quality scores. Feature selection procedure is designed in a manner to address spatial as well as temporal artifacts of the encoded sequences, while minimizing the overall run-time in order …
Authors
Fazliani Y; Andrade E; Shirani S
Pagination
pp. 1-5
Publication Date
May 2019
DOI
10.1109/ISCAS.2019.8702584
Conference proceedings
2019 IEEE International Symposium on Circuits and Systems (ISCAS)