检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Yang, Junpeng Li, Qiufu Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Guangdong Shenzhen518172 China

3D face recognition performs better than 2D face recognition, in terms of robustness against lighting and digital attacks. Compared to 2D data, the rich geometric information in 3D data could be very useful to improve the performance of 3D face recognition. This paper introduces PointSurFace, a surface feature extraction integrated model tailored for point cloud based 3D face recognition. PointSurFace adopts a specially designed surface feature extraction module, which explores information about the position and normals of the 3D face surface to explicitly extract local discriminative features from 3D point cloud faces. Subsequently, it alternates between set abstraction (SA) layers and Inverted Residual MLP (InvResMLP) modules to effectively extract features from the point cloud data. To better handle the spatial relationships in the point cloud data, PointSurFace integrates coordinate and feature data within each SA layer and InvResMLP module. It also applies channel fusion operations to align these different types of data, thereby more effectively extracts point cloud features. Experimental results in 3D facial recognition and verification across multiple datasets demonstrate that PointSurFace achieves the best 3D face recognition performance to date. For example, on Lock3DFace, it achieves the state-of-the-art recognition and verification accuracy of 90.03% and 80.01%, respectively, surpassing previous methods by 2.02% and 3.19%. Results on cross-quality datasets also affirm PointSurFace’s strong generalization capabilities. Ablation experiments validate the effectiveness of each module within PointSurFace, which suggests that the proposed surface feature extraction module significantly enhances the point cloud based 3D facial recognition performance. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2024年

作者： Lin, Zhenchao He, Li Yang, Hongqiang Sun, Xiaoqun Zhang, Guojin Chen, Weinan Guan, Yisheng Zhang, Hong School of Electromechanical Engineering Guangdong University of Technology Guangzhou China Department of Electronic and Electrical Engineering Southern University of Science and Technology China Shenzhen Key Laboratory of Robotics and Computer Vision China Meituan Technology Co. Ltd Shenzhen China

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local features without giving due consideration to global ones, thus failing to leverage semantic context. In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features. We propose a Similarity-Weighted Convolution (SWConv) to effectively extract local features, where similarity weights are incorporated into the convolution operation to enhance the generalization capabilities. Then, we employ a downsampling operation on the K and V channels within the attention module, thereby reducing the quadratic complexity to linear, enabling Transformer to deal with large-scale point cloud. At last, orthogonal components are extracted in the global features and then aggregated with local features, thereby eliminating redundant information between local and global features and consequently promoting efficiency. We evaluate SWCF-Net on large-scale outdoor datasets SemanticKITTI and Toronto3D. Our experimental results demonstrate the effectiveness of the proposed network. Our method achieves a competitive result with less computational cost, and is able to handle large-scale point clouds efficiently. The code is available at https://***/Sylva-Lin/SWCF-Net Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Shearlet-Based Structure-Aware Filtering for Hyperspectral and LiDAR Data Classification

引用

Journal of Remote Sensing 2021年第1期2021卷 237-261页

作者： Sen Jia Zhangwei Zhan Meng Xu College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the Ministry of Natural Resources Shenzhen UniversityShenzhenChina SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhenChina

The joint interpretation of hyperspectral images(HSIs)and light detection and ranging(LiDAR)data has developed rapidly in recent years due to continuously evolving image processing ***,most feature extraction methods are carried out by convolving the raw data with fixed-size filters,whereas the structural and texture information of objects in multiple scales cannot be sufficiently *** this article,a shearlet-based structure-aware filtering approach,abbreviated as ShearSAF,is proposed for HSI and LiDAR feature extraction and ***,superpixel-guided kernel principal component analysis(KPCA)is firstly adopted on raw HSIs to reduce the ***,the KPCA-reduced HSI and LiDAR data are converted to the shearlet domain for texture and area feature *** contrast,superpixel segmentation algorithm utilizes the raw HSI data to obtain the initial oversegmentation ***,by utilizing a well-designed minimum merging cost that fully considers spectral(HSI and LiDAR data),texture,and area features,a region merging procedure is gradually conducted to produce a final merging ***,a scale map that locally indicates the filter size is achieved by calculating the edge ***,the KPCA-reduced HSI and LiDAR data are convolved with the locally adaptive filters for feature extraction,and a random forest(RF)classifier is thus adopted for *** effectiveness of our ShearSAF approach is verified on three real-world datasets,and the results show that the performance of ShearSAF can achieve an accuracy higher than that of comparison methods when exploiting small-size training sample *** codes of this work will be available at http://***/papers/for the sake of reproducibility.

关键词： LiDAR Shear utilize

来源：评论

学校读者我要写书评

暂无评论

Perspective Phase Angle Model for Polarimetric 3D Reconstruction

arXiv

引用

arXiv 2022年

作者： Chen, Guangcheng He, Li Guan, Yisheng Zhang, Hong Guangdong University of Technology Guangzhou China Southern University of Science and Technology Shenzhen China Shenzhen Key Laboratory of Robotics and Computer Vision China

Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption. In the case of a large field of view, however, this assumption does not hold and may result in significant reconstruction errors in methods that make this assumption. To address this problem, we present the perspective phase angle (PPA) model that is applicable to perspective cameras. Compared with the orthographic model, the proposed PPA model accurately describes the relationship between polarization phase angle and surface normal under perspective projection. In addition, the PPA model makes it possible to estimate surface normals from only one single-view phase angle map and does not suffer from the so-called π-ambiguity problem. Experiments on real data show that the PPA model is more accurate for surface normal estimation with a perspective camera than the orthographic model. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Aeroengine remaining useful life prediction via integrating enhanced inverted transformer and spatiotemporal graph learning

引用

ISA Transactions 2025年

作者： Sun, Shilong Ding, Hao Zhao, Zida Zhou, Yu Wang, Dong Xu, Wenfu School of Robotics and Advanced Manufacturing College of Artificial Intelligence Harbin Institute of Technology Shenzhen China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China

Accurate prediction of aeroengine Remaining Useful Life (RUL) is critical for ensuring flight safety, minimizing maintenance costs, and improving operational efficiency. This study proposes a novel model, the Fourier-Enhanced Inverted Transformer with Graph-Augmented Spatiotemporal Modeling (FIT-GSTM), to enhance RUL prediction performance. FIT-GSTM combines an inverted Transformer with a Spatiotemporal Graph Convolutional Network (STGCN) to effectively capture global spatiotemporal dependencies across multi-sensor data. To further enrich feature representation, the model incorporates Fast Fourier Transform (FFT) to extract frequency-domain information and fuses it with time-domain features, enhancing robustness to noise. Additionally, the integration of Memory Tokens and Reversible Instance Normalization (RevIN) strengthens the model's ability to retain long-term dependencies and adapt to heterogeneous data distributions. Experimental evaluations on the C-MAPSS dataset demonstrate that FIT-GSTM achieves superior RUL prediction accuracy and generalization compared to existing methods, highlighting its potential for real-world deployment in aeroengine health management. © 2025 ISA

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Poster: Towards Accurate and Fast Federated Learning in End-Edge-Cloud Orchestrated Networks 43

Poster: Towards Accurate and Fast Federated Learning in End-...

引用

43rd IEEE International Conference on Distributed Computing Systems, ICDCS 2023

作者： Li, Mingze Sun, Peng Zhou, Huan Zhao, Liang Liu, Xuxun Leung, Victor C. M. College of Computer and Information Technology China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yichang China College of Computer Science and Electronic Engineering Hunan University Changsha China College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350339864

This work proposes a novel three-layer federated learning (FL) framework with parameter selection and pre-synchronization (PSPFL) to achieve fast and accurate model training. The basic idea of PSPFL is that clients select partial model parameters for transmission and then base stations aggregate them cooperatively (i.e., pre-synchronization) and send the aggregated results to the server for global model update periodically. However, there is an intrinsic trade-off between parameter transmission overhead and model training loss. To strike a desirable balance between them, we investigate the optimal parameter pre-synchronization round and local training round under PSPFL. Specifically, we propose a Deep Q-Network (DQN)-based method to obtain the local training round and parameter pre-synchronization round. Finally, extensive experiments are conducted to evaluate the performance of the proposed method on commonly used datasets. The results show that the proposed method can reduce the sum of FL completion time and training loss by an average of 8.17%-18.82% compared to benchmarks. © 2023 IEEE.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

arXiv

引用

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based BERT Model for Automated Information Extraction from Geological Hazard Reports

引用

Journal of Earth Science 2023年第5期34卷 1390-1405页

作者： Kai Ma Miao Tian Yongjian Tan Qinjun Qiu Zhong Xie Rong Huang Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang 443002China College of Computer and Information Technology China Three Gorges UniversityYichang 443002China Hubei Engineering Technology Research Center for Farmland Environment Monitoring China Three Gorges UniversityYichang 443002China School of Computer Science China University of GeosciencesWuhan 430074China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen 518034China Beijing Key Laboratory of Urban Spatial Information Engineering Beijing 100045China College of Economics and Management China Three Gorges UniversityYichang 443002China

Geological knowledge can provide support for knowledge discovery, knowledge inference and mineralization predictions of geological big data. Entity identification and relationship extraction from geological data description text are the key links for constructing knowledge graphs. Given the lack of publicly annotated datasets in the geology domain, this paper illustrates the construction process of geological entity datasets, defines the types of entities and interconceptual relationships by using the geological entity concept system, and completes the construction of the geological corpus. To address the shortcomings of existing language models(such as Word2vec and Glove) that cannot solve polysemous words and have a poor ability to fuse contexts, we propose a geological named entity recognition and relationship extraction model jointly with Bidirectional Encoder Representation from Transformers(BERT) pretrained language model. To effectively represent the text features, we construct a BERT-bidirectional gated recurrent unit network(BiGRU)-conditional random field(CRF)-based architecture to extract the named entities and the BERT-BiGRU-Attention-based architecture to extract the entity relations. The results show that the F1-score of the BERT-BiGRU-CRF named entity recognition model is 0.91 and the F1-score of the BERT-BiGRU-Attention relationship extraction model is 0.84, which are significant performance improvements when compared to classic language models(e.g., word2vec and Embedding from Language Models(ELMo)).

关键词： ontology BERT model name entity recognition relation extraction knowledge graph

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：