no code implementations • 19 Aug 2023 • Yuanchao Ding, Hua Guo, Yewei Guan, Weixin Liu, Jiarong Huo, Zhenyu Guan, Xiyong Zhang
Secure protocols for non-linear functions are crucial in privacy-preserving Transformer inference, which are not well studied.
1 code implementation • ICCV 2021 • Junpeng Jing, Xin Deng, Mai Xu, Jianyi Wang, Zhenyu Guan
Capacity, invisibility and security are three primary challenges in image hiding task.
1 code implementation • ECCV 2020 • Qunliang Xing, Mai Xu, Tianyi Li, Zhenyu Guan
Recently, extensive approaches have been proposed to reduce image compression artifacts at the decoder side; however, they require a series of architecture-identical models to process images with different quality, which are inefficient and resource-consuming.
1 code implementation • 26 Feb 2019 • Qunliang Xing, Zhenyu Guan, Mai Xu, Ren Yang, Tie Liu, Zulin Wang
Finally, experiments validate the effectiveness and generalization ability of our MFQE approach in advancing the state-of-the-art quality enhancement of compressed video.
Ranked #5 on Video Enhancement on MFQE v2
no code implementations • 20 Sep 2017 • Ren Yang, Mai Xu, Tie Liu, Zulin Wang, Zhenyu Guan
Our experimental results validate that our QE-CNN method is effective in enhancing quality for both I and P frames of HEVC videos.
Multimedia
1 code implementation • 19 Sep 2017 • Mai Xu, Tianyi Li, Zulin Wang, Xin Deng, Ren Yang, Zhenyu Guan
Therefore, this paper proposes a deep learning approach to predict the CU partition for reducing the HEVC complexity at both intra- and inter-modes, which is based on convolutional neural network (CNN) and long- and short-term memory (LSTM) network.