检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liang, Hanzhe Zhou, Jie Chen, Xuanxin Dai, Tao Wang, Jinbao Gao, Can College of Computer Science and Software Engineering Shenzhen University China Shenzhen Audencia Financial Technology Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Faculty of Education Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgements to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Semantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem’s causal logic. Copyright © 2025, The Authors. All rights reserved.

关键词： Fences

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

Leveraging Semisupervised Hierarchical Stacking Temporal Convolutional Network for Anomaly Detection in iot Communication

Leveraging Semisupervised Hierarchical Stacking Temporal Con...

引用

作者： Cheng, Yongliang Xu, Yan Zhong, Hong Liu, Yi Anhui Engineering Laboratory of IoT Security Technologies Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Shenzhen Key Laboratory of Intelligent Media and Speech Peking University Shenzhen Institute Shenzhen China

The rapid development of the Internet of Things (iot) accumulates a large number of communication records, which are utilized for anomaly detection in iot communication. However, only a small part of these records can be labeled, which increases the difficulty in anomaly detection. This article proposes a semisupervised hierarchical stacking temporal convolutional network (HS-TCN), which is the first semisupervised model for anomaly detection in iot communication, and it can train unlabeled data based on a small number of labeled data. Furthermore, HS-TCN fully considers the features of streaming data in iot communication and can weed out uncertain records. Finally, the experimental results demonstrate that HS-TCN promotes the performance of anomaly detection and attains better efficiency. © 2014 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment

arXiv

引用

arXiv 2023年

作者： Xu, Xiaoxu Yuan, Yitian Zhang, Qiudan Wu, Wenhui Jie, Zequn Ma, Lin Wang, Xu College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Meituan Inc. China College of Electronics and Information Engineering Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China

Learning to ground natural language queries to target objects or regions in 3D point clouds is quite essential for 3D scene understanding. Nevertheless, existing 3D visual grounding approaches require a substantial number of bounding box annotations for text queries, which is time-consuming and labor-intensive to obtain. In this paper, we propose 3D-VLA, a weakly supervised approach for 3D visual grounding based on Visual Language Alignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models (VLMs) on aligning the semantics between texts and 2D images, as well as the naturally existing correspondences between 2D images and 3D point clouds, and thus implicitly constructs correspondences between texts and 3D point clouds with no need for fine-grained box annotations in the training procedure. During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images. To the best of our knowledge, this is the first work to investigate 3D visual grounding in a weakly supervised manner by involving large scale vision-language models, and extensive experiments on ReferIt3D and ScanRefer datasets demonstrate that our 3D-VLA achieves comparable and even superior results over the fully supervised *** code will be available at https://***/xuxiaoxxxx/3D-VLA. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Low-rank matrix recovery with total generalized variation for defending adversarial examples

引用

Frontiers of information Technology & Electronic engineering 2024年第3期25卷 432-445页

作者： Wen LI Hengyou WANG Lianzhi HUO Qiang HE Linlin CHEN Zhiquan HE Wing W.Y.Ng School of Science Beijing University of Civil Engineering and ArchitectureBeijing 100044China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen 518060China Institute of Big Data Modeling and Technology Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Low-rank matrix decomposition with first-order total variation(TV)regularization exhibits excellent performance in exploration of image *** advantage of its excellent performance in image denoising,we apply it to improve the robustness of deep neural ***,although TV regularization can improve the robustness of the model,it reduces the accuracy of normal samples due to its *** our work,we develop a new low-rank matrix recovery model,called LRTGV,which incorporates total generalized variation(TGV)regularization into the reweighted low-rank matrix recovery *** the proposed model,TGV is used to better reconstruct texture information without *** reweighted nuclear norm and Li-norm can enhance the global structure ***,the proposed LRTGV can destroy the structure of adversarial noise while re-enhancing the global structure and local texture of the *** solve the challenging optimal model issue,we propose an algorithm based on the alternating direction method of *** results show that the proposed algorithm has a certain defense capability against black-box attacks,and outperforms state-of-the-art low-rank matrix recovery methods in image restoration.

关键词： Total generalized variation Low-rank matrix Alternating direction method of multipliers Adversarial example

来源：评论

学校读者我要写书评

暂无评论

An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation

arXiv

引用

arXiv 2024年

作者： Lin, Dongdong Li, Yue Tondi, Benedetta Li, Bin Barni, Mauro Guangdong Provincial Key Laboratory of Intelligent Information Processing The Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Huaqiao University China Xiamen Key Laboratory of Data Security and Blockchain Technology Xiamen361021 China Department of Information Engineering and Mathematics The University of Siena Italy

The rapid proliferation of deep neural networks (DNNs) is driving a surge in model watermarking technologies, as the trained deep models themselves serve as intellectual properties. The core of existing model watermarking techniques involves modifying or tuning the models’ weights. However, with the emergence of increasingly complex models, ensuring the efficiency of watermarking process is essential to manage the growing computational demands. Prioritizing efficiency not only optimizes resource utilization, making the watermarking process more applicable, but also minimizes potential impacts on model performance. In this letter, we propose an efficient watermarking method for latent diffusion models (LDMs) which is based on Low-Rank Adaptation (LoRA). We specifically choose to add trainable low-rank matrices to the existing weight matrices of the models to embed watermark, while keeping the original weights frozen. Moreover, we also propose a dynamic loss weight tuning algorithm to balance the generative task with the watermark embedding task, ensuring that the model can be watermarked with a limited impact on the quality of the generated images. Experimental results show that the proposed method ensures fast watermark embedding and maintains a very low bit error rate of the watermark, a high-quality of the generated image, and a zero false negative rate (FNR) for verification. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling 39

GeCC: Generalized Contrastive Clustering with Domain Shifts ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Yujie Wu, Wenhui Ou-Yang, Le Wang, Ran Wang, Debby D. College of Electronics and Information Engineering Shenzhen University Shenzhen 518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen 518060 China Faculty of Engineering Shenzhen MSU-BIT University Shenzhen 518116 China College of Mathematics and Statistics Shenzhen University Shenzhen 518060 China School of Science and Technology Hong Kong Metropolitan University Hong Kong

ISBN: (纸本)157735897X

Contrastive clustering performs clustering and data representation in a unified model, where instance- and cluster-level constrastive learning are conducted simultaneously. However, commonly-used data augmentation methods make contrastive mechanism effect but may cause representation learning getting stuck in domain-specific information, which further deteriorates clustering performance and limits generalization ability. To this end, we propose a new framework, named Generalized Contrastive Clustering with domain shifts modeling (GeCC), which can integrate diverse domain knowledge to improve the clustering performance. Specifically, we first design a cluster-guided domain shifts modeling module to synthesize a reference view with diverse domain information. Then, we introduce instance representation and cluster assignment contrastive modules with well-designed attention weights to guide the representation learning and clustering. In this way, our method can maximize the extraction of cluster-related information and avoid over-fitting domain-specific features. Experimental results on four benchmark datasets demonstrate that our proposed method consistently outperforms other state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transmit Sequence Design for Dual-Function Radar-Communication System with One-Bit DACs

Transmit Sequence Design for Dual-Function Radar-Communicati...

引用

作者： Cheng, Ziyang Shi, Shengnan He, Zishu Liao, Bin School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China

In this paper, the problem of transmit sequence design for a dual-function radar-communication (DFRC) system equipped with one-bit digital-to-analog converters (DACs) is investigated. More specifically, a nonconvex problem is formulated by minimizing the symbol mean-square error, while ensuring the target localization performance for radar. A direct one-bit sequence design tackled by an alternating minimization (AM) approach, which involves a simple unconstrained quadratic sub-problem with closed-form solution and a quadratically constrained nonconvex sub-problem tackled by the alternating direction method of multipliers (ADMM) algorithm, is developed. The solutions of primal variables under the ADMM framework are provided and the convergence is discussed. Additionally, an indirect but computationally more efficient design, which is realized by transmit beamforming based on an accelerated primal gradient (APG) method, is presented. For better understanding of this design, both the Cramér-Rao Bound (CRB) and symbol error probability of the resulting beamformer with one-bit quantization using the Bussgang theorem are analyzed. Numerical simulations are provided to demonstrate the effectiveness of the proposed schemes. © 2002-2012 IEEE.

关键词： Digital to analog conversion

来源：评论

学校读者我要写书评

暂无评论

An Unmanned Aerial Vehicle Swarm System for Tunnel Inspection Problems

An Unmanned Aerial Vehicle Swarm System for Tunnel Inspectio...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Zhihong Chen Jun Gao Hao Wu Xia Li Dept. College of Electronics and Information Engineering Shenzhen University Shenzhen P.R. China Dept. Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen P.R. China

Unmanned aerial vehicles (UAVs) have shown great significance for multiple industries in recent years, including photographing, agriculture, delivering, and transportation. The development of UAV has replaced and upgraded these applications due to the flexibility and intelligence. However, most of the current UAVs can only accomplish simple tasks, where the UAVs cannot change their operation mode in a single task. In this paper, a UAV swarm system is proposed to solve some complicated tasks, and the UAVs in the swarm can change their modes by the optimal decision from our swarm intelligent collaborative system (SICS). Additionally, we illustrate the complicated task of UAV-based tunnel inspection problems, where the UAVs can optimize and change their operation modes to maximize inspected distance. Some case studies have been worked out to show the viability of the proposed UAV swarm system, along with the performance of the proposed SICS for determining the optimal solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Speech-Noise-Equilibrium Loss Function for Deep Learning-Based Speech Enhancement

A Speech-Noise-Equilibrium Loss Function for Deep Learning-B...

引用

International Symposium on Chinese Spoken Language processing

作者： Weitong Zhao Fushi Xie Kang Ouyang Nengheng Zheng The Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen Guangdong China

ISBN: (纸本)9798350397970

The deep learning (DL)-based speech enhancement (SE) has demonstrated its advantage over the classical methods. In most DL-based SEs, however, the systems are optimized based on the minimum mean squared error (MSE), which could result in poor performance in severe noise conditions, e.g., very low signal-to-noise ratios. This paper presents a speech-noise-equilibrium loss function, i.e., a weighted combination of the speech distortion and the noise residue, for network training. Furthermore, based on the observation of the non-Gaussian distribution of the prediction error, a mean absolute error (MAE) criterion is adopted for speech distortion, and hybrid training, i.e., MSE followed by MAE, is proposed for network optimization. Experiment results demonstrate that long-short term memory networks (LSTM)-based SE systems with the proposed loss function achieve better performance than the baselines, particularly, improving both speech quality and intelligibility at low signal-to-noise ratios.

关键词： Training Deep learning Noise reduction Speech enhancement Distortion Optimization Signal to noise ratio

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：