检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School 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 Department of Computer Science University of Exeter United Kingdom

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 will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Method for Compressed Storage and Retrieval of Triplet Data Based on Cuckoo Hashing

A Method for Compressed Storage and Retrieval of Triplet Dat...

引用

International Conference on Wavelet Active Media Technology and information processing (ICWAMTIP)

作者： Liu Pengcheng Qinzhi Zhang Shibin Chang Yan Yan Lili School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu China SUGON Industrial Control and Security Center Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

This paper proposes a method for compressing and retrieving triple data based on optimized cuckoo hash. Firstly, the optimized cuckoo hash algorithm is utilized to quickly establish node indexes. Then, the relationship information of triples is stored in the form of a sparse matrix according to the relationship type. Finally, the double compression algorithm k 2 -Rel is employed to compress the relationship attribute matrix of stored triple information, aiming to reduce storage space and lower storage costs. Experimental results demonstrate that the optimized cuckoo hash algorithm significantly reduces the time for building node indexes. Furthermore, utilizing the k2-Rel compression algorithm for compressing the relationship information between nodes substantially decreases storage space, ultimately achieving efficient storage and retrieval of triple data.

关键词： Costs Triples (Data structure) Buildings information processing Media Motion pictures Sparse matrices Indexes Compression algorithms

来源：评论

学校读者我要写书评

暂无评论

AQPDCITY dataset: Picture-based PM monitoring in the urban area of big cities

arXiv

引用

arXiv 2020年

作者： Zhang, Yonghui Gu, Ke Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Key Laboratory of Computational Intelligence and Intelligent System China Beijing Artificial Intelligence Institute China Faculty of Information Technology Beijing University of Technology China

Since Particulate Matters (PMs) are closely related to people’s living and health, it has become one of the most important indicator of air quality monitoring around the world. But the existing sensor-based methods for PM monitoring have remarkable disadvantages, such as low-density monitoring stations and high-requirement monitoring conditions. It is highly desired to devise a method that can obtain the PM concentration at any location for the following air quality control in time. The prior works indicate that the PM concentration can be monitored by using ubiquitous photos. To further investigate such issue, we gathered 1,500 photos in big cities to establish a new AQPDCITY dataset. Experiments conducted to check nine state-of-the-art methods on this dataset show that the performance of those above methods perform poorly in the AQPDCITY dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Short-term power load forecasting method based on CNN-SAEDN-Res

arXiv

引用

arXiv 2023年

作者： Cui, Yang Zhu, Han Wang, Yijian Zhang, Lu Li, Yang Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China

In deep learning, the load data with non-temporal factors are difficult to process by sequence models. This problem results in insufficient precision of the prediction. Therefore, a short-term load forecasting method based on convolutional neural network (CNN), self-attention encoder-decoder network (SAEDN) and resi- dual-refinement (Res) is proposed. In this method, feature extraction module is composed of a two-dimensional convolutional neural network, which is used to mine the local correlation between data and obtain high-dimensional data features. The initial load fore-casting module consists of a self-attention encoder-decoder network and a feedforward neural network (FFN). The module utilizes self-attention mechanisms to encode high-dimensional features. This operation can obtain the global correlation between data. Therefore, the model is able to retain important information based on the coupling relationship between the data in data mixed with non-time series factors. Then, self-attention decoding is per-formed and the feedforward neural network is used to regression initial load. This paper introduces the residual mechanism to build the load optimization module. The module generates residual load values to optimize the initial load. The simulation results show that the proposed load forecasting method has advantages in terms of prediction accuracy and prediction stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing

arXiv

引用

arXiv 2024年

作者： Xian, Xiaole He, Xilin Niu, Zenghao Zhang, Junliang Xie, Weicheng Song, Siyang Yu, Zitong Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Great Bay University China

For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternatively, inpainting methods can edit the target image region while preserving external areas. However, current inpainting methods still suffer from the generation misalignment with facial attributes description and the loss of facial skin details. To address these challenges, (i) a novel data utilization strategy is introduced to construct datasets consisting of attribute-text-image triples from a data-driven perspective, (ii) a Causality-Aware Condition Adapter is proposed to enhance the contextual causality modeling of specific details, which encodes the skin details from the original image while preventing conflicts between these cues and textual conditions. In addition, a Skin Transition Frequency Guidance technique is introduced for the local modeling of contextual causality via sampling guidance driven by low-frequency alignment. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in boosting both fidelity and editability for localized attribute editing. The code is available at https://***/connorxian/CA-Edit. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fast Sampling-Based Parallel Dbscan Algorithm for Massive Datasets

A Fast Sampling-Based Parallel Dbscan Algorithm for Massive ...

引用

International Conference on Wavelet Active Media Technology and information processing (ICWAMTIP)

作者： Wang Gefeng Zhang Shibin Yan Lili Lv Zhiying Chang Yan Qin Zhi School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu China SUGON Industrial Control and Security Center Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Clustering is a type of data mining algorithm aimed at discovering hidden patterns in the data, and spatial clustering is an important type of it. Density-based spatial clustering of applications with noise (DBSCAN) is a clustering algorithm that can discover clusters of arbitrary shapes and has robustness to noise. DBSCAN has been widely studied and applied due to its superior clustering quality, but its high complexity limits its performance on massive-scale datasets. This paper proposes a sampling-based grid-structured DBSCAN algorithm with linear complexity that can be processed in parallel. The algorithm first clusters the sampled dataset to discover the main features of the dataset; then it establishes grids and indexes to accelerate neighbor point queries; finally, through specially designed decoupled algorithm structure, it achieves lock-free parallel computation. Experiments show that this algorithm outperforms the state-of-the-art DBSCAN algorithm under various tested datasets and parameter conditions.

关键词： Shape Noise Clustering algorithms information processing Media Spatial databases Robustness Complexity theory Indexes Time complexity

来源：评论

学校读者我要写书评

暂无评论

Recognizing Human-object Interactions for a Home Assistive Robot

Recognizing Human-object Interactions for a Home Assistive R...

引用

Automation, control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Guanglei Huo Xinwei Chen Chengxi Huang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

To enable robots to understand a specific assistive task during human-robot interactions under complex home scenes, at the center is the problem of human-object interaction (HOI) recognition. In particular, aiming at identifying efficiently, this paper proposes a graph convolutional network (GCN) by considering the similarity and proximity of human and object nodes, based on which the geometric positions and morphological relationships are explored. Also, a supplementary convolutional neural network (CNN) is fused to GCN to extract the global semantic features, which also ensures the recognition applicability for the cases where detectors fall into failure. Experiments on V-COCO demonstrate our approach, and results in real-world scenes on our assistive robot – Xiaozhi II verify its robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single-Photon LiDAR Depth Estimation Based on Time Series Correlation

Single-Photon LiDAR Depth Estimation Based on Time Series Co...

引用

Academic International Symposium on Optoelectronics and Microelectronics Technology (AISOMT)

作者： Lin Ruobin Sun Jianfeng Jiang Peng Ma Le Zhou Xin Ren Zhen Ding Ji National Key Laboratory of Laser Spatial Information Harbin Institute of Technology Harbin Heilongjiang China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou Henan China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China Tianjin Jinhang Technical Physics Institute Tianjin China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (数字)9798331542283

ISBN: (纸本)9798331542290

With advancements in science and technology, photon-counting LiDAR applications are growing due to long-range measurement, high-definition imaging, and accuracy. Geiger-mode avalanche photodiodes (Gm-APD) provide single-photon sensitivity and picosecond resolution, but noise in depth estimation affects imaging accuracy. This study introduces a novel depth estimation method using time series correlation to mitigate these noise issues, improving accuracy in LiDAR imaging. Utilizing a photon-counting LiDAR system and time-correlated single photon counting (TCSPC), this study capture target echo photon flight times to maintain depth information. The proposed denoising approach incorporates multiple time series windows and Bayesian estimation to enhance depth accuracy, alongside a pruning algorithm to optimize computational efficiency. Evaluation metrics show significant improvements: RSNR improved by 4% and MAE decreased by 43 % compared to traditional methods. The findings demonstrate the robustness of this method across various scenarios, enhancing depth estimation and noise mitigation in photon-counting LiDAR technology, thereby providing practical improvements for a range of applications.

关键词： Correlation Laser radar Accuracy Filtering Depth measurement Time series analysis Noise reduction Imaging Bayes methods Photonics

来源：评论

学校读者我要写书评

暂无评论

The improved neural network algorithm of license plate recognition

International Journal of Signal Processing, Image Processing...

引用

International Journal of Signal processing, Image processing and Pattern Recognition 2015年第5期8卷 49-54页

作者： Dong, Jingwei Sun, Meiting Liang, Gengrui Jin, Kui School of Measure-Control Technology and Communication Engineering The higher educational key laboratory for Signal and Information Processing of Heilongjiang Province Harbin University of Science and Technology Harbin China School of Electric and Electronic Engineering Harbin University of Science and Technology Harbin China

With high definition cameras are widely used in urban traffic monitoring, the resolution of vehicle and traffic monitoring image rises. As the main component of intelligent traffic system, the vehicle license plate recognition technique faces new challenges and some new demands are put forward. Aiming at the problems of cutting down the time delay and eliminating characters outside of vehicle license plate, a set of license plate recognition algorithm is developed in this paper. The process of recognition in this paper is divided into four parts: image preprocessing, license plate location, license plate segmentation and character recognition. In license plate location, an accelerating matching method based on particle image correlation method is employed. In character recognition, an improved BP neural network algorithm is employed. The principle, procedure and simulation of the algorithm is described in details. High definition images with 2 mega pixels are used as the input of simulation. © 2015 SERSC.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Attractor flow analysis for recurrent neural network with back-to-back memristors

Attractor flow analysis for recurrent neural network with ba...

引用

IEEE Symposium on Foundations of Computational Intelligence, FOCI

作者： Gang Bao Zhigang Zeng School of Automation Huazhong University of Science and Technology Wuhan Hubei China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education Wuhan China college of Electrical Engineering and New Energy China Three Gorges University Yichang China

ISBN: (纸本)9781479944903

Memristor is a nonlinear resistor with the character of memory and is proved to be suitable for simulating synapse of neuron. This paper introduces two memristors in series with the same polarity (back-to-back) as simulator for neuron's synapse and presents the model of recurrent neural networks with such back-to-back memristors. By analysis techniques and fixed point theory, some sufficient conditions are obtained for recurrent neural network having single attractor flow and multiple attractors flow. At last, simulation with numeric examples is presented to illustrate our results.

关键词： Memristors Stability analysis Recurrent neural networks Resistance Numerical models

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：