检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiao, Xianhe Lv, Chenlei Zhao, Junli Yi, Ran Wen, Yu-Hui Pan, Zhenkuan Wu, Zhongke Liu, Yong-Jin College of Computer Science and Technology Qingdao University China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science and Engineering Shanghai Jiao Tong University China School of Computer Science & Technology Beijing Jiaotong University China School of Artificial Intelligence Beijing Normal University China Department of Computer Science and Technology MOE-Key Laboratory of Pervasive Computing Tsinghua University China

For large-scale point cloud processing, resampling takes the important role of controlling the point number and density while keeping the geometric consistency. However, current methods cannot balance such different requirements. Particularly with large-scale point clouds, classical methods often struggle with decreased efficiency and accuracy. To address such issues, we propose a weighted Poisson-disk (WPD) resampling method to improve the usability and efficiency for the processing. We first design an initial Poisson resampling with a voxel-based estimation strategy. It is able to estimate a more accurate radius of the Poisson-disk while maintaining high efficiency. Then, we design a weighted tangent smoothing step to further optimize the Voronoi diagram for each point. At the same time, sharp features are detected and kept in the optimized results with isotropic property. Finally, we achieve a resampling copy from the original point cloud with the specified point number, uniform density, and high-quality geometric consistency. Experiments show that our method significantly improves the performance of large-scale point cloud resampling for different applications, and provides a highly practical solution. Copyright © 2024, The Authors. All rights reserved.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description

arXiv

引用

arXiv 2024年

作者： Jin, Zeyu Jia, Jia Wang, Qixin Li, Kehan Zhou, Shuoyi Zhou, Songtao Qin, Xiaoyu Wu, Zhiyong Department of Computer Science and Technology Tsinghua University Beijing China BNRist Tsinghua University Key Laboratory of Pervasive Computing Ministry of Education Beijing China Shenzhen International Graduate School Tsinghua University Shenzhen China

Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LLaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft1, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

SCENEHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry

arXiv

引用

arXiv 2023年

作者： Gao, Lin Sun, Jia-Mu Mo, Kaichun Lai, Yu-Kun Guibas, Leonidas J. Yang, Jie The Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China Stanford University United States The School of Computer Science & Informatics Cardiff University United Kingdom

3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. They also contain rich information, including room layout, as well as furniture type, geometry, and placement. High-quality 3D indoor scenes are highly demanded while it requires expertise and is time-consuming to design high-quality 3D indoor scenes manually. Existing research only addresses partial problems: some works learn to generate room layout, and other works focus on generating detailed structure and geometry of individual furniture objects. However, these partial steps are related and should be addressed together for optimal synthesis. We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level. Therefore for the first time, our method is able to directly generate plausible 3D room content, including furniture objects with fine-grained geometry, and their layout. To address the challenge, we introduce functional regions as intermediate proxies between the room and object levels to make learning more manageable. To ensure plausibility, our graph-based representation incorporates both vertical edges connecting child nodes with parent nodes from different levels, and horizontal edges encoding relationships between nodes at the same level. Our generation network is a conditional recursive neural network (RvNN) based variational autoencoder (VAE) that learns to generate detailed content with fine-grained geometry for a room, given the room boundary as the condition. Extensive experiments demonstrate that our method produces superior generation results, even when comparing results of partial steps with alternative methods that can only achieve these. We also demonstrate that our method is effective for various applications such as part-level room editing, room interpolation, and room gene

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Explainable-AI-based two-stage solution for WSN object localization using zero-touch mobile transceivers

引用

science China(Information sciences) 2024年第7期67卷 27-45页

作者： Kai FANG Junxin CHEN Han ZHU Thippa Reddy GADEKALLU Xiaoping WU Wei WANG School of Mathematics and Computer Science Zhejiang A&F University School of Software Dalian University of Technology Faculty of Applied Sciences Macao Polytechnic University Department of Electrical and Computer Engineering Lebanese American University School of Information Engineering Huzhou University Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University

Artificial intelligence technology is widely used in the field of wireless sensor networks(WSN).Due to its inexplicability, the interference factors in the process of WSN object localization cannot be effectively eliminated. In this paper, an explainable-AI-based two-stage solution is proposed for WSN object localization. In this solution, mobile transceivers are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable,and the localization problem is highly nonlinear with respect to the unknown parameters. To address this,an explainable AI model is proposed to solve the localization problem. Since the relationship among the variables is difficult to fully include in the first-stage traditional model, we develop a two-stage explainable AI solution for this localization problem. The two-stage solution is actually a comprehensive consideration of the relationship between variables. The solution can continue to use the constraints unused in the firststage during the second-stage, thereby improving the performance of the solution. Therefore, the two-stage solution has stronger robustness compared to the closed-form solution. Experimental results show that the performance of both the two-stage solution and the traditional solution will be affected by numerical changes in unknown parameters. However, the two-stage solution performs better than the traditional solution, especially with a small number of mobile transceivers and sensors or in the presence of high noise. Furthermore,we have also verified the feasibility of the proposed explainable-AI-based two-stage solution.

关键词： explainable AI object localization semidefinite relaxation mobile transceiver two-stage solution closed-form solution

来源：评论

学校读者我要写书评

暂无评论

Buffer Awareness Neural Adaptive Video Streaming for Avoiding Extra Buffer Consumption

Buffer Awareness Neural Adaptive Video Streaming for Avoidin...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Tianchi Huang Chao Zhou Rui-Xiao Zhang Chenglei Wu Lifeng Sun Department of Computer Science and Technology Tsinghua University Beijing Kuaishou Technology Co. Ltd. BNRist Ministry of Education Key Laboratory of Pervasive Computing (Tsinghua University) China

Adaptive video streaming has already been a major scheme to transmit videos with high quality of experience (QoE). However, the improvement of network traffics and the high compression efficiency of videos enable clients to accumulate too much buffer, which might cause colossal data waste if users close the session early before the session ends. In this paper, we consider buffer-aware adaptive bitrate (ABR) mechanisms to overcome the above concerns. Formulating the buffer-aware rate adaptation problem as multi-objective optimization, we propose DeepBuffer, a deep reinforcement learning-based approach that jointly takes proper bitrate and controls the maximum buffer. To deal with the challenges of learning-based buffer-aware ABR composition, such as infinite possible plans, multiple bitrate levels, and complex action space, we design adequate preference-driven inputs, separate action outputs, and invent high sample-efficiency training methodologies. We train DeepBuffer with a broad set of real-world network traces and provide a comprehensive evaluation in terms of various network scenarios and different video types. Experimental results indicate that DeepBuffer rivals or outperforms recent heuristics and learning-based ABR schemes in terms of QoE while heavily reducing the average buffer consumption by up to 90%. Extensive real-world experiments further demonstrate the substantial superiority of DeepBuffer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RDladder: Resolution-Duration Ladder for VBR-encoded Videos via Imitation Learning

RDladder: Resolution-Duration Ladder for VBR-encoded Videos ...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Lianchen Jia Chao Zhou Tianchi Huang Chaoyang Li Lifeng Sun Department of Computer Science and Technology Tsinghua University Beijing Kuaishou Technology Co. Ltd. BNRist Ministry of Education Key Laboratory of Pervasive Computing Tsinghua University China

With the rapid development of the streaming system, a large number of videos need to be transcoded to multiple copies according to the encoding ladder, which significantly increases the storage overhead than before. This scenario demonstrates the prosperity of streaming media but also presents new challenges about achieving the balance between better quality for users and less storage cost. In our work, we observe two significant points. The first one is selecting proper resolutions under certain network conditions can reduce storage costs while maintaining a great quality of experience. The second one is the segment duration is critical, especially in VBR-encoded videos. Considering these points, we propose RDladder, a resolution-duration ladder for VBR-encoded videos via imitation learning. We jointly optimize resolutions and duration using neural networks to determine the combination of these two metrics considering network capacity, video information, and storage cost. To get more faithful results, we use over 500 videos, encoded to over 2,000,000 chunks, and collect real-world network traces for more than 50 hours. We test RDladder in simulation, emulation, and real-world environments under various network conditions, and our method can achieve near-optimal performance. Furthermore, we discuss the influence between the RDladder and ABR algorithms and summarize some characteristics of RDladder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection and Characterization of Human Veins Using Infra-Red Image Processing

引用

Journal of computer and Communications 2024年第9期12卷 141-159页

作者： Jean Ndoumbe Brice Ekobo Akoa Gaelle Patricia Talotsing Frederic Franck Kounga Samuel Kaissassou Bertin Chouanmo Njo Laboratory of Computer Engineering Data Science and Artificial Intelligence Department of Computer & Telecommunications Engineering National Higher Polytechnic School Douala Cameroon Laboratory of Electrical Engineering Mechatronics and Signal Processing Department of Electrical & Telecommunications Engineering National Advanced School of Engineering Yaound Cameroon Mobile Computing and Networking Research Laboratory Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada DigiPlus SARL Bonamoussadi Douala Cameroon

The detection and characterization of human veins using infrared (IR) image processing have gained significant attention due to its potential applications in biometric identification, medical diagnostics, and vein-based authentication systems. This paper presents a low-cost approach for automatic detection and characterization of human veins from IR images. The proposed method uses image processing techniques including segmentation, feature extraction, and, pattern recognition algorithms. Initially, the IR images are preprocessed to enhance vein structures and reduce noise. Subsequently, a CLAHE algorithm is employed to extract vein regions based on their unique IR absorption properties. Features such as vein thickness, orientation, and branching patterns are extracted using mathematical morphology and directional filters. Finally, a classification framework is implemented to categorize veins and distinguish them from surrounding tissues or artifacts. A setup based on Raspberry Pi was used. Experimental results of IR images demonstrate the effectiveness and robustness of the proposed approach in accurately detecting and characterizing human. The developed system shows promising for integration into applications requiring reliable and secure identification based on vein patterns. Our work provides an effective and low-cost solution for nursing staff in low and middle-income countries to perform a safe and accurate venipuncture.

关键词： Vein Detection Blood Radiation Infrared Image CLAHE Algorithm Raspberry Pi

来源：评论

学校读者我要写书评

暂无评论

Real-Time 3D-Aware Portrait Video Relighting

Real-Time 3D-Aware Portrait Video Relighting

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Ziqi Cai Kaiwen Jiang Shu-Yu Chen Yu-Kun Lai Hongbo Fu Boxin Shi Lin Gao Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing Jiaotong University University of California San Diego Cardiff University City University of Hong Kong The Hong Kong University of Science and Technology National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University University of Chinese Academy of Sciences

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However, most existing relighting methods are either time-consuming or unable to adjust the viewpoints. In this paper, we present the first real-time 3D-aware method for relighting in-the-wild videos of talking faces based on Neural Radiance Fields (NeRF). Given an input portrait video, our method can synthesize talking faces under both novel views and novel lighting conditions with a photo-realistic and disentangled 3D representation. Specifically, we infer an albedo tri-plane, as well as a shading tri-plane based on a desired lighting condition for each video frame with fast dual-encoders. We also leverage a temporal consistency network to ensure smooth transitions and reduce flickering artifacts. Our method runs at 32.98 fps on consumer-level hardware and achieves state-of-the-art results in terms of reconstruction quality, lighting error, lighting instability, temporal consistency and inference speed. We demonstrate the effectiveness and interactivity of our method on various portrait videos with diverse lighting and viewing conditions.

关键词： computer vision Three-dimensional displays Lighting Neural radiance field Real-time systems Hardware Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction

MonoPlane: Exploiting Monocular Geometric Cues for Generaliz...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Wang Zhao Jiachen Liu Sheng Zhang Yishu Li Sili Chen Sharon X Huang Yong-Jin Liu Hengkai Guo Department of Computer Science and Technology BNRist MOEKey Laboratory of Pervasive Computing Tsinghua University Beijing China College of Information Sciences and Technology Pennsylvania State University University Park PA USA Bytedance Inc. Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper presents a generalizable 3D plane detection and reconstruction framework named MonoPlane. Unlike previous robust estimator-based works (which require multiple images or RGB-D input) and learning-based works (which suffer from domain shift), MonoPlane combines the best of two worlds and establishes a plane reconstruction pipeline based on monocular geometric cues, resulting in accurate, robust and scalable 3D plane detection and reconstruction in the wild. Specifically, we first leverage large-scale pre-trained neural networks to obtain the depth and surface normals from a single image. These monocular geometric cues are then incorporated into a proximity-guided RANSAC framework to sequentially fit each plane instance. We exploit effective 3D point proximity and model such proximity via a graph within RANSAC to guide the plane fitting from noisy monocular depths, followed by image-level multi-plane joint optimization to improve the consistency among all plane instances. We further design a simple but effective pipeline to extend this single-view solution to sparse-view 3D plane reconstruction. Extensive experiments on a list of datasets demonstrate our superior zero-shot generalizability over baselines, achieving state-of-the-art plane reconstruction performance in a transferring setting. Our code is available at https://***/thuzhaowang/MonoPlane.

关键词： Surface reconstruction Solid modeling Three-dimensional displays Pipelines Fitting Neural networks Surface fitting Noise measurement Image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images

arXiv

引用

arXiv 2024年

作者： Zou, Xuechao Zhang, Shun Li, Kai Wang, Shiying Xing, Junliang Jin, Lei Lang, Congyan Tao, Pin School of Computer Science & Technology Beijing Jiaotong University Beijing China The Department of Computer Science and Technology Tsinghua University Beijing China The Key Laboratory of Pervasive Computing Ministry of Education China The School of Computer Technology and Application Qinghai University Xining China The School of Electronic Engineering Beijing University of Posts and Telecommunications Beijing China

Cloud segmentation is a critical challenge in remote sensing image interpretation, as its accuracy directly impacts the effectiveness of subsequent data processing and analysis. Recently, vision foundation models (VFM) have demonstrated powerful generalization capabilities across various visual tasks. In this paper, we present a parameter-efficient adaptive approach, termed Cloud-Adapter, designed to enhance the accuracy and robustness of cloud segmentation. Our method leverages a VFM pretrained on general domain data, which remains frozen, eliminating the need for additional training. Cloud-Adapter incorporates a lightweight spatial perception module that initially utilizes a convolutional neural network (ConvNet) to extract dense spatial representations. These multi-scale features are then aggregated and serve as contextual inputs to an adapting module, which modulates the frozen transformer layers within the VFM. Experimental results demonstrate that the Cloud-Adapter approach, utilizing only 0.6% of the trainable parameters of the frozen backbone, achieves substantial performance gains. Cloud-Adapter consistently achieves state-of-the-art performance across various cloud segmentation datasets from multiple satellite sources, sensor series, data processing levels, land cover scenarios, and annotation granularities. We have released the code and model checkpoints at https://***/Cloud-Adapter/ to support further research. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

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：