activity
20182022
most citedKernel-Induced Label Propagation by Mapping for Semi-Supervised Classification

34 citations · 66 across the 12 of their papers we have counts for

collaborators

23 papers

cs.CV2022

Long-Range Zero-Shot Generative Deep Network Quantization

Yan Luo, Yangcheng Gao, Zhao Zhang +3

Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers, in order to accelerate inference and reduce computation. Quantizin…

cs.CV2022

Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising

Jiahuan Ren, Zhao Zhang, Richang Hong +3

Low-light image enhancement (LLIE) aims at improving the illumination and visibility of dark images with lighting noise. To handle the real-world low-light images often with heavy…

cs.CV20203 cited

Unsupervised Vehicle Re-identification with Progressive Adaptation

Jinjia Peng, Yang Wang, Huibing Wang +3

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal…

cs.CV20202 cited

Convolutional Dictionary Pair Learning Network for Image Representation Learning

Zhao Zhang, Yulin Sun, Yang Wang +3

Both the Dictionary Learning (DL) and Convolutional Neural Networks (CNN) are powerful image representation learning systems based on different mechanisms and principles, however w…

cs.CV20207 cited

Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery

Xianzhen Li, Zhao Zhang, Yang Wang +3

For subspace recovery, most existing low-rank representation (LRR) models performs in the original space in single-layer mode. As such, the deep hierarchical information cannot be…

cs.CV20207 cited

Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition

Zhao Zhang, Zemin Tang, Zheng Zhang +3

The Deep Convolutional Neural Networks (CNNs) have obtained a great success for pattern recognition, such as recognizing the texts in images. But existing CNNs based frameworks sti…