8 citations · 12 across the 5 of their papers we have counts for
10 papers
Self-Calibrated Efficient Transformer for Lightweight Super-Resolution
Wenbin Zou, Tian Ye, Weixin Zheng +3
Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance. However, most existing methods focus on building a mo…
SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring
Wenbin Zou, Mingchao Jiang, Yunchen Zhang +3
Image deblurring is a classical computer vision problem that aims to recover a sharp image from a blurred image. To solve this problem, existing methods apply the Encode-Decode arc…
DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing
Canqun Xiang, Zhennan Wang, Wenbin Zou +1
Parsing an image into a hierarchy of objects, parts, and relations is important and also challenging in many computer vision tasks. This paper proposes a simple and effective capsu…
Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision
Rongqin Liang, Yuanman Li, Xia Li +3
Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video…
MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles
Zhennan Wang, Canqun Xiang, Wenbin Zou +1
The strong correlation between neurons or filters can significantly weaken the generalization ability of neural networks. Inspired by the well-known Tammes problem, we propose a no…
SAIS: Single-stage Anchor-free Instance Segmentation
Canqun Xiang, Shishun Tian, Wenbin Zou +1
In this paper, we propose a simple yet efficientinstance segmentation approach based on the single-stage anchor-free detector, termed SAIS. In our approach, the instancesegmentatio…