activity
20152021
most citedDomain Adaptation Extreme Learning Machines for Drift Compensation in E-nose Systems

362 citations · 554 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

24 papers · 1 filter

cs.CV2021

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting

Binghui Chen, Zhaoyi Yan, Ke Li +4

In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity…

cs.CV20198 cited

Reliable and Efficient Image Cropping: A Grid Anchor based Approach

Hui Zeng, Lida Li, Zisheng Cao +1

Image cropping aims to improve the composition as well as aesthetic quality of an image by removing extraneous content from it. Existing image cropping databases provide only one o…

cs.CV201992 cited

A Benchmark for Edge-Preserving Image Smoothing

Feida Zhu, Zhetong Liang, Xixi Jia +2

Edge-preserving image smoothing is an important step for many low-level vision problems. Though many algorithms have been proposed, there are several difficulties hindering its fur…

cs.CV2019

Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization

Qilong Wang, Jiangtao Xie, Wangmeng Zuo +2

Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potenti…

cs.CV201952 cited

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

Jianrui Cai, Hui Zeng, Hongwei Yong +2

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…

cs.CV201919 cited

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels

Kai Zhang, Wangmeng Zuo, Lei Zhang

While deep neural networks (DNN) based single image super-resolution (SISR) methods are rapidly gaining popularity, they are mainly designed for the widely-used bicubic degradation…