activity
20192023
most citedAdaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

12 citations · 49 across the 12 of their papers we have counts for

collaborators

12 papers

quant-ph2023★ 4 cited

Quantum Privacy-Preserving Price E-Negotiation

Wen-Jie Liu, Chun-Tang Li, Yu Zheng +2

Privacy-preserving price e-negotiation (3PEN) is an important topic of secure multi-party computation (SMC) in the electronic commerce field, and the key point of its security is t…

cs.CL2023★ 4 cited

AutoHint: Automatic Prompt Optimization with Hint Generation

Hong Sun, Xue Li, Yinchuan Xu +5

This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability i…

cs.CV2023

HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution

Minyi Zhao, Yi Xu, Bingjia Li +3

Scene text image super-resolution (STISR) is an important pre-processing technique for text recognition from low-resolution scene images. Nowadays, various methods have been propos…

cs.CL2022★ 1 cited

EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification

Minyi Zhao, Lu Zhang, Yi Xu +3

Recent works have empirically shown the effectiveness of data augmentation (DA) in NLP tasks, especially for those suffering from data scarcity. Intuitively, given the size of gene…

cs.CV2021★ 6 cited

DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples

Yi Xu, Jiandong Ding, Lu Zhang +1

The scarcity of labeled data is a critical obstacle to deep learning. Semi-supervised learning (SSL) provides a promising way to leverage unlabeled data by pseudo labels. However,…

cs.CL2021★ 1 cited

Weakly-supervised Text Classification Based on Keyword Graph

Lu Zhang, Jiandong Ding, Yi Xu +2

Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven metho…