262 citations · 1.9k across the 68 of their papers we have counts for
7 papers · 1 filter
Cross Modal Compression: Towards Human-comprehensible Semantic Compression
Jiguo Li, Chuanmin Jia, Xinfeng Zhang +2
Traditional image/video compression aims to reduce the transmission/storage cost with signal fidelity as high as possible. However, with the increasing demand for machine analysis…
Towards Hybrid-Optimization Video Coding
Shuai Huo, Dong Liu, Li Li +3
Video coding is a mathematical optimization problem of rate and distortion essentially. To solve this complex optimization problem, two popular video coding frameworks have been de…
Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution
Yuqing Liu, Qi Jia, Xin Fan +3
It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details. Existing deep learning works almost neglect the inherent str…
Rate Distortion Characteristic Modeling for Neural Image Compression
Chuanmin Jia, Ziqing Ge, Shanshe Wang +2
End-to-end optimized neural image compression (NIC) has obtained superior lossy compression performance recently. In this paper, we consider the problem of rate-distortion (R-D) ch…
Assessing the Quality-of-Experience of Adaptive Bitrate Video Streaming
Zhengfang Duanmu, Wentao Liu, Zhuoran Li +4
The diversity of video delivery pipeline poses a grand challenge to the evaluation of adaptive bitrate (ABR) streaming algorithms and objective quality-of-experience (QoE) models.…
Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution
Yuqing Liu, Xinfeng Zhang, Shanshe Wang +2
Multi-scale design has been considered in recent image super-resolution (SR) works to explore the hierarchical feature information. Existing multi-scale networks aim to build elabo…
Iterative Network for Image Super-Resolution
Yuqing Liu, Shiqi Wang, Jian Zhang +3
Single image super-resolution (SISR), as a traditional ill-conditioned inverse problem, has been greatly revitalized by the recent development of convolutional neural networks (CNN…