A5100420874- Advanced Image Processing Techniques
- Video Surveillance and Tracking Methods
- Generative Adversarial Networks and Image Synthesis
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Image Processing Techniques and Applications
- Autonomous Vehicle Technology and Safety
- Advanced Image and Video Retrieval Techniques
- Advanced Image Fusion Techniques
- Image and Signal Denoising Methods
- Image Enhancement Techniques
- Remote-Sensing Image Classification
- Traffic and Road Safety
- Robotic Path Planning Algorithms
- Infrared Target Detection Methodologies
- Fire Detection and Safety Systems
- Human Pose and Action Recognition
- Industrial Vision Systems and Defect Detection
- Domain Adaptation and Few-Shot Learning
- Anomaly Detection Techniques and Applications
- Advanced Measurement and Detection Methods
- 3D Shape Modeling and Analysis
- Advanced Algorithms and Applications
- Visual Attention and Saliency Detection
- Smart Agriculture and AI
University of Chinese Academy of Sciences
2015-2024
Xi'an Institute of Optics and Precision Mechanics
2024
Wuhan University of Technology
2022-2024
Shandong University of Traditional Chinese Medicine
2014-2024
Sanya University
2022-2024
Zoomlion (China)
2018-2024
China Academy of Space Technology
2024
China Jiliang University
2024
Nanjing Tech University
2024
Xijing University
2024
Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works built cost volumes with cross-correlation or concatenation left right features across all levels, then 2D 3D convolutional neural network utilized regress maps. In this paper, we propose construct volume by group-wise correlation. The are divided into groups along channel dimension, correlation maps computed among...
To solving the problems that existing image inpainting methods lack authenticity, do not deal with information of missing and non-missing regions flexibly, feature on different stages effectively, we propose an restoration method combining Semantic Priors Deep Attention Residual Group. The mainly consists Network, Group, Full-scale Skip Connection. Network learns complete semantic prior visual elements in completes learned information. deep attention residual set allows generator to focus...
This work studies the problem of few-shot object counting, which counts number exemplar objects (i.e., described by one or several support images) occurring in query image. The major challenge lies that target can be densely packed image, making it hard to recognize every single one. To tackle obstacle, we propose a novel learning block, equipped with similarity comparison module and feature enhancement module. Concretely, given image first derive score map comparing their projected features...
Notice of Violation IEEE Publication Principles <br><br>"Single-Image Super-Resolution Algorithm Based on Structural Self-Similarity and Deformation Block Features" <br> by Yuantao Chen, Jin Wang, Xi Mingwei Zhu, Kai Yang, Zhi Runlong Xia in Access, April 2019 <br><br>After careful considered review the content authorship this paper a duly constituted expert committee, has been found to be violation IEEE's Principles. <br><br>This is translation duplication from cited below. The original was...
Crowd counting has important applications in the environments of smart cities, such as intelligent surveillance. In this paper, we propose a novel convolutional neural network (CNN) framework for crowd with mixed ground-truth, called top- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> relation-based (TKRNet). Specifically, estimated density maps generated coarse-to-fine...
Summary Retraction: Multiscale fast correlation filtering tracking algorithm based on a feature fusion model Yuantao Chen, Jin Wang, Songjie Liu, Xi Jie Xiong, Jingbo Xie, Kai Yang, 2021, 33 (15), ( https://doi.org/10.1002/cpe.5533
Aiming at the problems of intensive background noise, low accuracy, and high computational complexity current significant object detection methods, visual saliency algorithm based on Hierarchical Principal Component Analysis (HPCA) has been proposed in paper. Firstly, original RGB image converted to a grayscale image, divided into eight layers by bit surface stratification technique. Each layer contains information matching features. Secondly, taking color structure as reference is...