检索结果-内蒙古大学图书馆

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

Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection

arXiv

引用

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

Multi-Scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

Multi-Scale Dynamic and Hierarchical Relationship Modeling f...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zihan Wang Siyang Song Cheng Luo Songhe Deng Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Universiry of Leicester Monash University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hi-erarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatiotemporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and mag-nitude in different AUs' activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR.

关键词： Gold Adaptation models Computer vision Graphical models Codes Adaptive systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Owl: Differential-Based Side-Channel Leakage Detection for CUDA Applications

Owl: Differential-Based Side-Channel Leakage Detection for C...

引用

International Conference on Dependable systems and Networks (DSN)

作者： Yu Zhao Wenjie Xue Weijie Chen Weizhong Qiang Deqing Zou Hai Jin National Engineering Research Center for Big Data Technology and System Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jinyinhu Laboratory Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350341058

ISBN: (纸本)9798350341065

Over the past decade, various methods for detecting side-channel leakage have been proposed and proven to be effective against CPU side-channel attacks. These methods are valuable in assisting developers to identify and patch side-channel vulnerabilities. Nevertheless, recent research has revealed the feasibility of exploiting side-channel vulnerabilities to steal sensitive information from GPU applications, which are beyond the reach of previous side-channel detection methods. Therefore, in this paper, we conduct an in-depth examination of various GPU features and present Owl, a novel side-channel detection tool targeting CUDA applications on NVIDIA GPUs. Owl is designed to detect and locate side-channel leakage in various types of CUDA applications. When tracking the execution of CUDA applications, we design a hierarchical tracing scheme and extend the A-DCFG (Attributed Dynamic Control Flow Graph) to address the massively parallel execution in CUDA, ensuring Owl's detection scalability. After completing the initial assessment and filtering, we conduct statistical tests on the differences in program traces to determine whether they are indeed caused by input variations, subsequently facilitating the positioning of side-channel leaks. We evaluate Owl's capability to detect side-channel leaks by testing it on Libgpucrypto, PyTorch, and nvJPEG. Meanwhile, we verify that our solution effectively handles a large number of threads. Owl has successfully identified hundreds of leaks within these applications. To the best of our knowledge, we are the first to implement side-channel leakage detection for general CUDA applications.

关键词： Target tracking Statistical analysis Filtering Scalability Graphics processing units Side-channel attacks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph-Based AU Relationship Learning for Facial Action Unit Detection

Spatial-Temporal Graph-Based AU Relationship Learning for Fa...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zihan Wang Siyang Song Cheng Luo Yuzhi Zhou Shiling Wu Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Computing and Mathematical Sciences University of Leicester

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence; (ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation; and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://***/wzh125/ABAW-5.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constructing a Biomass-data Center Nexus for Circular Economy-Based Energy systems Integration

IEEE Open Access Journal of Power and Energy

引用

IEEE Open Access Journal of Power and Energy 2025年 12卷 270-283页

作者： Wang, Pengya Pan, Li He, Guannan Li, Gengyin Song, Jie Zhou, Ming Wang, Jianxiao State Grid Dezhou Power Supply Company Shandong Dezhou253000 China The Chinese University of Hon g Kong School of Science and Engineering Guangdong Shenzhen518000 China Peking University College of Engineering Department of Industrial Engineering and Management Beijing100871 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources Beijing102206 China Peking University National Engineering Laboratory for Big Data Analysis and Applications Beijing100871 China

The dual challenges of energy crises and waste management have spurred interest in a circular economy, where biomass, valued for its carbon neutrality, is crucial. Remote areas, rich in biomass, are also becoming hubs for data center (DC) construction. Despite DCs’ low energy efficiency and production of low-grade waste heat, recovering this heat offers a promising path toward a circular economy. There are few systematic studies on the relationships among DC energy supply, waste heat generation, and renewable energy resources. In this study, we formulate day-ahead, real-time optimal scheduling strategies to provide electricity, heat, and gas using a complementary photovoltaic-biomass system. The biogas production process requires heat to promote the anaerobic reaction, and the adaptation temperature of anaerobic bacteria matches the low-quality waste heat generated from of the DC. We realize a circular economy by coupling a DC and a renewable energy system by directly using the waste heat from the DC and by using the queuing theory of the DC’s delay tolerance workload for partial load response. Moreover, the nonlinearity in the process is linearized by the least squares method. Actual data calculations show that the introduction of biogas can result in a fully renewable energy supply. Based on specific configurations—including a 350 kW PV system, 450 kWh BSS, 250 kW CHP unit, and an AD operating at 20°C to 45°C—the system is tested under 0% and 50% carbon emission scenarios. The DC workload combines delay-tolerant and delay-sensitive tasks, enabling flexible scheduling for energy and heat optimization, the power usage effectiveness (PUE) of the DC decreases from 1.73 to 1.24, operating expenses decrease by 36.06%, and system energy consumption decreases by 44.6%. © 2020 IEEE.

关键词： Waste heat utilization

来源：评论

学校读者我要写书评

暂无评论

big-MOE: BYPASS ISOLATED GATING MOE FOR GENERALIZED MULTIMODAL FACE ANTI-SPOOFING

arXiv

引用

arXiv 2024年

作者： Ma, Yingjie Yu, Zitong Lin, Xun Xie, Weicheng Shen, Linlin Great Bay University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators;(2) Gated networks’ susceptibility to input noise affecting decision-making;(3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (big-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues;(2) An isolation gating mechanism to counteract input noise;(3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/bigMoE. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Graph-Augmented Contrastive Clustering for Time Series

SSRN

引用

SSRN 2023年

作者： Zhang, Qin Liang, Zhuoluo Ngueilbaye, Alladoumbaye Zhang, Peng Chen, Junyang Chen, Xiaojun Huang, Joshua Zhexue Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China

The recent emergence of time series contrastive clustering methods can be broadly categorized into two classes. The first class uses contrastive learning to learn universal representations for time series. Though they perform well in various downstream tasks, such methods disregard the important categorical information and clustering objective, leading to unsuitable representations of clustering tasks. The second class incorporates contrastive learning into the clustering objective. The potential connections and structures between the time series data are not fully explored during contrastive learning. To this end, we propose a graph-augmented contrastive learning framework called the "Time Series Graph-augmented Contrastive Clustering (TSGCC) method." We observed that the original samples should be similar to their augmentations and other samples in the same cluster. Hence, we used a weighted $KNN$ graph to build positive and negative sample pairs for contrastive learning. Subsequently, we projected the instance samples into a feature space with the dimensionality number of clusters and learned cluster-friendly features and cluster assignments by iteratively optimizing the contrastive loss. Experimental results demonstrate that TSGCC outperforms 16 advanced time-series clustering methods on 36 challenging UCR benchmarks, achieving the best clustering results on 12 datasets and the highest average rank (2.83) of RI overall methods. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

GM-DF: Generalized Multi-Scenario Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, 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

Sal-Guide Diffusion: Saliency Maps Guide Emotional Image Generation through Adapter

Sal-Guide Diffusion: Saliency Maps Guide Emotional Image Gen...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiangru Lin Shenghua Zhong Yan Liu Gong Chen College of Computer Science Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China College of Computer Science Shenzhen University Shenzhen China Department of Computer Science The Hong Kong Polytechnic University HK China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

The existing text-to-image generation methods based on stable diffusion yield better results in low-semantic prompt but often neglect the generation quality of high-semantic prompt such as emotional vocabulary, resulting in poor emotional image generation. In order to address this issue, we propose a novel approach called Sal-Guide Diffusion, which leverages saliency maps to guide emotional image generation with the goal of producing superior emotionally expressive images. In order to let the saliency maps guide the diffusion process, we introduce a lightweight adapter to extract emotional information from saliency maps and incorporate it into the diffusion process. Experimental results demonstrate that our proposed method generates higher-quality images across eight emotional dimensions, excelling in both generalization, emotional congruence, and subjective preference compared to stable diffusion or similar methods.

关键词： Vocabulary Image synthesis Buildings Diffusion processes Text to image data mining

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：