Search Results for author:
Found 6 papers, 4 papers with code
East: Efficient and Accurate Secure Transformer Framework for Inference
Secure protocols for non-linear functions are crucial in privacy-preserving Transformer inference, which are not well studied.
HiNet: Deep Image Hiding by Invertible Network
Capacity, invisibility and security are three primary challenges in image hiding task.
Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images
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.
MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video
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
Enhancing Quality for HEVC Compressed Videos
Our experimental results validate that our QE-CNN method is effective in enhancing quality for both I and P frames of HEVC videos.
Multimedia
Reducing Complexity of HEVC: A Deep Learning Approach
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.
