activity
20162023
most citedLearning Pixel-Distribution Prior with Wider Convolution for Image Denoising

16 citations · 72 across the 25 of their papers we have counts for

collaborators

33 papers

cs.CL20221 cited

Quantifying syntax similarity with a polynomial representation of dependency trees

Pengyu Liu, Tinghao Feng, Rui Liu

We introduce a graph polynomial that distinguishes tree structures to represent dependency grammar and a measure based on the polynomial representation to quantify syntax similarit…

cs.CR20221 cited

Remapped Cache Layout: Thwarting Cache-Based Side-Channel Attacks with a Hardware Defense

Wei Song, Rui Hou, Peng Liu +6

As cache-based side-channel attacks become serious security problems, various defenses have been proposed and deployed in both software and hardware. Consequently, cache-based side…

cs.LG20223 cited

Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples

Hui Liu, Bo Zhao, Kehuan Zhang +1

Although deep neural networks (DNNs) have shown impressive performance on many perceptual tasks, they are vulnerable to adversarial examples that are generated by adding slight but…

cs.CL20227 cited

Towards a Unified Multi-Dimensional Evaluator for Text Generation

Ming Zhong, Yang Liu, Da Yin +6

Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimen…

gr-qc20224 cited

Dynamical descalarization in Einstein-Maxwell-scalar theory

Chao Niu, Wei Xiong, Peng Liu +2

For an asymptotically flat hairy black hole in the Einstein-Maxwell-scalar (EMS) theory, we study the possibility of shedding off its scalar hair via nonlinear scalar perturbation…

eess.IV20221 cited

KiPA22 Report: U-Net with Contour Regularization for Renal Structures Segmentation

Kangqing Ye, Peng Liu, Xiaoyang Zou +2

Three-dimensional (3D) integrated renal structures (IRS) segmentation is important in clinical practice. With the advancement of deep learning techniques, many powerful frameworks…