Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Yong YinSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works78 from public data
- Human action recognition in immersive virtual reality based on multi‐scale spatio‐temporal attention network73
A novel immersive HAR method called MovPosVR is proposed, which showcases the potential to display user actions and position information in a virtual world, enriching user experiences and interactions across diverse application scenarios.
- 47
- 5 G WiFi Signal-Based Indoor Localization System Using Cluster k-Nearest Neighbor Algorithm47
The proposed cluster k-nearest neighbor (KNN) algorithm with 5 G WiFi signal to reduce the environmental interference and improve the localization performance without additional equipment is proposed and implemented and the performance with existent popular algorithms is evaluated.
- Differential cryptanalysis of image cipher using block-based scrambling and image filtering37
Experimental results show that the improved algorithm proposed not only inherits the merits of the original scheme, but also has stronger security against the differential cryptanalysis.
- Image fusion employing adaptive spectral-spatial gradient sparse regularization in UAV remote sensing37
A multispectral and panchromatic image fusion model employing adaptive spectral-spatial gradient sparse regularization is proposed for UAV remote sensing and it is demonstrated that accurate vegetation indices can be generated by adopting the proposed algorithm.
- A secure image authentication scheme based on dual fragile watermark27
The design aims to enhance the security of fragile watermarking, and the statistical results and security analysis show that this scheme can resist chosen cover-image attacks.
- An Indoor Localization of WiFi Based on Support Vector Machines25
The proposed algorithm based on support vector machines (SVM) algorithm, and comparing with three kernel functions, radial basis function (RBF) performs best of all and leads to improvement on localization accuracy.
- 22
- 22
- An Improved Indoor Localization of WiFiBased on Support Vector Machines22
Experimental results indicate that the proposed algorithm can effectively reduce the calibration effort and exhibit superior performance in terms of localization accuracy and stabilization.
- 22
- 20
- Smoke Detection Algorithm based on Negative Sample Mining19
A novel model based on Faster Region-based Convolutional Network (R-CNN) which utilizes negative sample mining method is proposed which allows the model to learn more negative sample features, thereby reducing false positives in smoke detection.
- DSANet: A lightweight hybrid network for human action recognition in virtual sports17
A hybrid lightweight DSANet network designed to address the challenges of real‐time performance and algorithmic complexity is proposed and presents a novel network for real‐time activity recognition deployment in embedded devices.
- A Novel Endoscope System for Position Detection and Depth Estimation of the Ureter14
Experimental results demonstrate that the proposed endoscope system can extract the position and depth information of ureter and exhibit superior performance in terms of accuracy and stabilization.
- An Augmented Reality Endoscope System for Ureter Position Detection12
An Ureter position detection and display system with the augmented hardware detection method and target detection algorithms is proposed to detect the ureter that is covered by human tissue and Experimental results demonstrate that the proposed endoscope system can identify 92.04% ureters in average.
- VTNCT: an image-based virtual try-on network by combining feature with pixel transformation11
A novel virtual try-on network to generate photo-realistic try-on image while preserving the details of clothes and non-target regions and uses a distillation strategy to solve the degeneration caused by the wrong parsing.
- 11
- EnCaps: Clothing Image Classification Based on Enhanced Capsule Network10
Experimental results indicate that the proposed EnCaps network achieves high performance in terms of classification accuracy and computational efficiency.
- Statistical methods for transmission image reconstruction with nonlocal edge -preserving regularization.10
Statistical Methods for Transmission Image Reconstruction with Nonlocal Edge-Preserving Regularization with nonlocal edge-preserving regularization are presented.
- MHC-Segnet: Mamba–Hadamard collaboration segmentation network for multimodal MRI brain tumor8
MHC-SegNet is proposed, a novel Mamba–Hadamard collaboration segmentation network that aims to more efficiently capture global patterns across modalities and achieves the best performance compared to recent state-of-the-art models in segmentation accuracy.
- UAV-FDN: Forest-fire detection network for unmanned aerial vehicle perspective8
The main concepts of the framework are an efficient attention module that combines channel and spatial dimension information to improve the accuracy and efficiency of model detection under complex backgrounds, and an improved multi-scale fusion module that enhances the network’s ability to learn objects details and semantic features, thus reducing the chances of small objects being false negative during inspection and false positive issues.
- High fidelity virtual try-on network via semantic adaptation and distributed componentization8
A novel high fidelity virtual try-on network that can retain better details of condition information than current methods is proposed and achieves convincing quantitative and qualitative results on existing benchmark datasets.
- Laparoscopic Image-Guided System Based on Multispectral Imaging for the Ureter Detection8
An image-guided endoscope system that includes a novel endoscopic video system with a visible-light camera and an infrared camera, and a self-adaptive threshold segmentation algorithm to extract the real ureter position as accurately as possible to satisfy the clinical demand.
- CAPN: a Combine Attention Partial Network for glove detection7
A real-time glove detection algorithm using video surveillance to address the issue of low accuracy in glove detection with small-scale glove datasets and introduces the Combine Attention Partial Network (CAPN) based on convolutional neural networks.
- Virtual try-on based on attention U-Net7
This work adopts an attention-based U-Net network as the backbone of the cross-domain fusion module and improves the framework of CFM to generate composition mask, adjusted clothes and rendered person, and composite the final try-on result through mask operations.
- 7
- SHC: soft-hard correspondences framework for simplifying point cloud registration6
The soft-hard correspondence (SHC) framework is introduced in the present paper to streamline the registration problem and achieves performance comparable to complex networks using a simple network and can achieve zero error on datasets with perfect correspondence pairs.
- 6
- 6
- 5
- Three stages of 3D virtual try-on network with appearance flow and shape field5
A novel 3D virtual try-on network based on appearance flow and shape field called AFSF-3DVTON is proposed that evaluates the proposed method on the VITON and MPV3D datasets, and several state-of-the-art virtualtry-on algorithms are used as comparisons.
- 5
- 5
- 5
- Redundant same sequence point cloud registration4
Redundant Same Sequence point cloud Registration (RSSR) effectively addresses the challenge of registering point clouds with a limited number of inliers by reconstructing the correspondence relation constraint to allow the discovery of more potential correspondence pairs.
- GSNet: Generating 3D garment animation via graph skinning network4
This work proposes GSNet, a learning-based model that generates realistic garment animations and applies to garment types that do not match the body topology and considers temporal dependency and provides reliable physical constraints to make the generated animations more realistic.
- FFENet: frequency-spatial feature enhancement network for clothing classification4
This work combines the frequency domain information and spatial information to establish a clothing feature extraction clothing classification network without compressed feature map channels, and introduces a clothing dataset in complex scenes (Clothing-8).
- 4
- 4
- 4
- 3
- 2
- PlgFormer: parallel extraction of local-global features for AD diagnosis on sMRI using a unified CNN-transformer architecture2
A computer-aided AD diagnosis method based on sMRI, named PlgFormer, which considers the extraction of both local and global features by using a combination of convolution and self-attention, which demonstrates the high precision and robustness of the method in diagnosing people with different stages of cognitive impairment.
- HTMC: hierarchical tolerance mask correspondence for human body point cloud registration2
A Hierarchical Tolerance Mask Correspondence method to achieve better alignment by tolerating obfuscation of correspondence pairs and acknowledges the presence of similar local geometry in human body point clouds.
- 2
- Perception and Management System for Building Energy Consumption Based on Internet of Things Technology2
A perception, monitoring and management system of building energy consumption based on Internet of Things technology architecture that has been successfully applied to more than 50 large-scale public building to implement energy consumption monitor and management, and the support of the underlying data for building energy efficiency is described.
- 2
- Oil spill visualization based on the numeric simulation of tidal current2
An approach to implement the 3D visualization of oil spill based on tidal hydrodynamic model that simulates tidal current of M2 component tide in Jiaozhou Bay and the dynamic visualization of drift and diffusion course of oil on the sea is satisfactory.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- An Image-guided Endoscope System for the Ureter Detection1
A novel image-guided endoscope system that has both traditional functions of the endoscopeSystem and the additional function of ureter detection is proposed, and the Ureter position can be displayed during the surgery.
- Fingerprint Indoor Localization Algorithm Based on Modified AdaBoost1
In this chapter, a modified AdaBoost algorithm is proposed for localization with received signal strength (RSS) and results indicate that the modified Ada boost algorithm obtains high localization accuracy and stability.
- Study on the Radar Echo Dynamic Image Simulation1
The characteristics of Dalian Maritime University, Transas and Furuno radar simulators are described, to put forward a radar 2D simulation method, including terrene rendering, rain/snow rendering, sea rendering and target ship rendering.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Formation System of Mobile Robot Based on Vision Location–
A formation system of mobile robot based on vision location is designed, which is composed of intelligent mobile robot, vision location computation, wireless communication system and formation control strategy.
- –
- –
- –
- –
- Applying Frequent Episode Algorithm to Masquerade Detection–
This paper presents an effective approach to masquerade detection by using frequent episode algorithm and evaluates the method by performing experiments over UNIX command records from the SEA dataset.
- Joint Distribution-Based Image Representations and Retrieval–
Two histogram models are proposed to refine the description of each pixel by some local features to achieve an increased discriminative power compared to the classical color histogram technique for image retrieval.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.