Search Results for author: Hui Zeng

Found 20 papers, 16 papers with code

Small Model and In-Domain Data Are All You Need

no code implementations WMT (EMNLP) 2021 Hui Zeng

I participated in the WMT shared news translation task and focus on one high resource language pair: English and Chinese (two directions, Chinese to English and English to Chinese).

Language Modelling Translation +1

Enhancing targeted transferability via feature space fine-tuning

2 code implementations5 Jan 2024 Hui Zeng, Biwei Chen, Anjie Peng

Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks.

Guided Image Restoration via Simultaneous Feature and Image Guided Fusion

no code implementations14 Dec 2023 Xinyi Liu, Qian Zhao, Jie Liang, Hui Zeng, Deyu Meng, Lei Zhang

Currently, joint image filtering-inspired deep learning-based methods represent the state-of-the-art for GIR tasks.

Depth Map Super-Resolution Image Restoration

Evaluating the Generation Capabilities of Large Chinese Language Models

2 code implementations9 Aug 2023 Hui Zeng, Jingyuan Xue, Meng Hao, Chen Sun, Bin Ning, Na Zhang

This paper unveils CG-Eval, the first-ever comprehensive and automated evaluation framework designed for assessing the generative capabilities of large Chinese language models across a spectrum of academic disciplines.

Text Generation

Measuring Massive Multitask Chinese Understanding

1 code implementation25 Apr 2023 Hui Zeng

Across the four major domains, the highest average zero-shot accuracy of all models is 0. 512.

Human Guided Ground-truth Generation for Realistic Image Super-resolution

1 code implementation CVPR 2023 Du Chen, Jie Liang, Xindong Zhang, Ming Liu, Hui Zeng, Lei Zhang

A human guided GT image dataset with both positive and negative samples is then constructed, and a loss function is proposed to train the Real-ISR models.

Image Enhancement Image Super-Resolution

Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset

1 code implementation CVPR 2023 Shuaizheng Liu, Xindong Zhang, Lingchen Sun, Zhetong Liang, Hui Zeng, Lei Zhang

In this work, we develop, for the first time to our best knowledge, an HDR image dataset by using mobile phone cameras, namely Mobile-HDR dataset.

Denoising

Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution

1 code implementation27 Mar 2022 Jie Liang, Hui Zeng, Lei Zhang

Specifically, a tiny regression network is employed to predict the degradation parameters of the input image, while several convolutional experts with the same topology are jointly optimized to specify the network parameters via a non-linear mixture of experts.

Image Super-Resolution

Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution

2 code implementations CVPR 2022 Jie Liang, Hui Zeng, Lei Zhang

In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts.

Image Super-Resolution

Efficient Long-Range Attention Network for Image Super-resolution

1 code implementation13 Mar 2022 Xindong Zhang, Hui Zeng, Shi Guo, Lei Zhang

A highly efficient long-range attention block (ELAB) is then built by simply cascading two shift-conv with a GMSA module, which is further accelerated by using a shared attention mechanism.

Image Super-Resolution

A comparison study of CNN denoisers on PRNU extraction

no code implementations6 Dec 2021 Hui Zeng, Morteza Darvish Morshedi Hosseini, Kang Deng, Anjie Peng, Miroslav Goljan

In this paper, a comparative evaluation of such CNN denoisers on SCI performance is carried out on the public "Dresden Image Database".

Image Denoising Quantization

PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency

1 code implementation CVPR 2021 Jie Liang, Hui Zeng, Miaomiao Cui, Xuansong Xie, Lei Zhang

HRP requires that more attention should be paid to human regions, while GLC requires that a group of portrait photos should be retouched to a consistent tone.

Photo Retouching

High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network

1 code implementation CVPR 2021 Jie Liang, Hui Zeng, Lei Zhang

Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps.

Attribute Color Manipulation +3

Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme

1 code implementation ICCV 2021 Xi Yang, Wangmeng Xiang, Hui Zeng, Lei Zhang

Existing VSR methods are mostly trained and evaluated on synthetic datasets, where the LR videos are uniformly downsampled from their high-resolution (HR) counterparts by some simple operators (e. g., bicubic downsampling).

Video Super-Resolution

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

1 code implementation30 Sep 2020 Hui Zeng, Jianrui Cai, Lida Li, Zisheng Cao, Lei Zhang

The small CNN works on the down-sampled version of the input image to predict content-dependent weights to fuse the multiple basis 3D LUTs into an image-adaptive one, which is employed to transform the color and tone of source images efficiently.

Ranked #5 on Image Enhancement on MIT-Adobe 5k (SSIM on proRGB metric)

Image Enhancement Image Retouching +1

Grid Anchor based Image Cropping: A New Benchmark and An Efficient Model

1 code implementation18 Sep 2019 Hui Zeng, Lida Li, Zisheng Cao, Lei Zhang

The employed evaluation metrics such as intersection-over-union cannot reliably reflect the real performance of a cropping model, either.

Image Cropping

Reliable and Efficient Image Cropping: A Grid Anchor based Approach

1 code implementation CVPR 2019 Hui Zeng, Lida Li, Zisheng Cao, Lei Zhang

Consequently, a grid anchor based cropping benchmark is constructed, where all crops of each image are annotated and more reliable evaluation metrics are defined.

Image Cropping

Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model

no code implementations ICCV 2019 Jianrui Cai, Hui Zeng, Hongwei Yong, Zisheng Cao, Lei Zhang

Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i. e., bicubic downsampling) to their high-resolution (HR) counterparts.

Image Registration Image Super-Resolution

A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction

1 code implementation28 Aug 2017 Hui Zeng, Lei Zhang, Alan C. Bovik

Recognizing this, we propose a new representation of perceptual image quality, called probabilistic quality representation (PQR), to describe the image subjective score distribution, whereby a more robust loss function can be employed to train a deep BIQA model.

Blind Image Quality Assessment regression

Cannot find the paper you are looking for? You can Submit a new open access paper.