A5013301642- Visual Attention and Saliency Detection
- Image Enhancement Techniques
- Advanced Steganography and Watermarking Techniques
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Advanced Image Fusion Techniques
- Iterative Learning Control Systems
- Chaos-based Image/Signal Encryption
- Image and Video Quality Assessment
- Image Processing Techniques and Applications
- Olfactory and Sensory Function Studies
- Sparse and Compressive Sensing Techniques
- Gait Recognition and Analysis
- Water Systems and Optimization
- Blind Source Separation Techniques
- Advanced Measurement and Metrology Techniques
- Neural Networks and Applications
- Human Pose and Action Recognition
- Control Systems and Identification
- Face Recognition and Perception
- Image and Signal Denoising Methods
- Digital Media Forensic Detection
- Seismic Imaging and Inversion Techniques
- Photoacoustic and Ultrasonic Imaging
- Geophysical Methods and Applications
Northeast Petroleum University
2013-2025
Ocean University of China
2025
China University of Petroleum, Beijing
2025
Quzhou University
2016-2024
National University of Defense Technology
2024
Dalian Maritime University
2023-2024
Daqing Normal University
2008-2023
Harbin Engineering University
2016
University of Waterloo
2016
Zhejiang University of Technology
2011-2014
Camouflaged object detection (COD) is an emerging visual task, which aims to locate and distinguish the disguised target in complex backgrounds by imitating human system. Recently, COD has attracted increasing attention computer vision, a few models of camouflaged have been successfully explored. However, most existing works primarily focus on modeling over in-depth analyzing structures. To best our knowledge, systematic review for not publicly reported, especially recently proposed deep...
In this article, we propose a novel framework for camouflaged object detection (COD), named D <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> C-Net, which contains two new modules: Dual-branch features extraction (DFE) and gradually refined cross fusion (GRCF). Specifically, the DFE simulates two-stage process of human visual mechanisms in observing camouflage scenes. For...
The purpose of co-salient object detection (CoSOD) is to detect the salient objects that co-occur in a group relevant images. CoSOD has been significantly prospered by recent advances convolutional neural networks (CNNs). However, it shows general limitations modeling long-range feature dependencies, which crucial for CoSOD. In vision transformer, self-attention mechanism utilized capture global dependencies but unfortunately destroy local spatial details, are also essential To address above...
Abstract To address the challenge of limited training samples in natural gas pipeline leakage detection, a novel transfer learning framework is proposed, which requires only small amount data from specific leak aperture as source domain set. Additionally, new residual structure, named Dual-Pieces Net, designed. This structure combines cross-layer fusion networks with convolutional fragmenting mechanism. By processing feature maps various ways through fragmentation, it enhances model's...
Giant Dimer (G-Dimer) acceptors have shown their promising ability in the fabrication of high-performance organic solar cells; however, a lack investigation on morphology optimization donor and acceptor (D-A) blends essentially confines potential application. Based typical Y6-analogues-based giant dimeric G-DimerC8C10, this study investigated impact varying processing temperatures behavior with PM6. The result indicated that as temperature increased, aggregation capacity is enhanced. This...
The out-of-plane shape determination in a generalized fringe projection profilometry is presented. proposed technique corrects the problems existing approaches, and it can cope well with divergent illumination encountered profilometry. In addition, automatically detect geometric parameters of experimental setup, which makes simple practical. concept was verified by both computer simulations actual experiments. be easily employed for measurements high accuracies.
Deep-learning techniques have been widely used in pipeline leakage aperture identification. However, most are designed and implemented for offline data, with problems such as large parameters, high memory consumption, poor noise immunity. To solve the problem, this article presents a lightweight residual convolutional neural network (L-Resnet) applied to real-time detection platform achieve identification of apertures. First, based on depth separable technique, two different modules...
In this article, we provide a comprehensive study of new task called collaborative camouflaged object detection (CoCOD), which aims to simultaneously detect objects with the same properties from group relevant images. To end, meticulously construct first large-scale dataset, termed CoCOD8K, consists 8528 high-quality and elaborately selected images mask annotations, covering five superclasses 70 subclasses. The dataset spans wide range natural artificial camouflage scenes diverse appearances...