检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Cheng, Yean Wan, Renjie Weng, Shuchen Zhu, Chengxuan Chang, Yakun Shi, Boxin National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China AI Innovation Center School of Computer Science Peking University China Department of Computer Science Hong Kong Baptist University Hong Kong National Key Lab of General AI School of Intelligence Science and Technology Peking University China

Though Neural Radiance Fields (NeRF) can produce colorful 3D representations of the world by using a set of 2D images, such ability becomes non-existent when only monochromatic images are provided. Since color is necessary in representing the world, reproducing color from monochromatic radiance fields becomes crucial. To achieve this goal, instead of manipulating the monochromatic radiance fields directly, we consider it as a representation-prediction task in the Lab color space. By first constructing the luminance and density representation using monochromatic images, our prediction stage can recreate color representation on the basis of an image colorization module. We then reproduce a colorful implicit model through the representation of luminance, density, and color. Extensive experiments have been conducted to validate the effectiveness of our approaches. Our project page: https://***/color-nerf. Copyright © 2024, The Authors. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images

arXiv

引用

arXiv 2024年

作者： Han, Yufei Guo, Heng Fukai, Koki Santo, Hiroaki Shi, Boxin Okura, Fumio Ma, Zhanyu Jia, Yunpeng Beijing University of Posts and Telecommunications China Graduate School of Information Science and Technology Osaka University Japan National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

We present NeRSP, a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. Reflective surface reconstruction is extremely challenging as specular reflections are view-dependent and thus violate the multiview consistency for multiview stereo. On the other hand, sparse image inputs, as a practical capture setting, commonly cause incomplete or distorted results due to the lack of correspondence matching. This paper jointly handles the challenges from sparse inputs and reflective surfaces by leveraging polarized images. We derive photometric and geometric cues from the polarimetric image formation model and multiview azimuth consistency, which jointly optimize the surface geometry modeled via implicit neural representation. Based on the experiments on our synthetic and real datasets, we achieve the state-of-the-art surface reconstruction results with only 6 views as input. Copyright © 2024, The Authors. All rights reserved.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability

arXiv

引用

arXiv 2024年

作者： Luo, Zihan Song, Xiran Huang, Hong Lian, Jianxun Zhang, Chenhao Jiang, Jinqi Xie, Xing Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China The National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

Evaluating and enhancing the general capabilities of large language models (LLMs) has been an important research topic. Graph is a common data structure in the real world, and understanding graph data is a crucial part for advancing general intelligence. To evaluate and enhance the graph understanding abilities of LLMs, in this paper, we propose a benchmark named GraphInstruct, which comprehensively includes 21 classical graph reasoning tasks, providing diverse graph generation pipelines and detailed reasoning steps. Based on GraphInstruct, we further construct GraphLM through efficient instruction-tuning, which shows prominent graph understanding capability. In order to enhance the LLM with graph reasoning capability as well, we propose a step mask training strategy, and construct a model named GraphLM+. As one of the pioneering efforts to enhance the graph understanding and reasoning abilities of LLMs, extensive experiments have demonstrated the superiority of GraphLM and GraphLM+ over other LLMs. We look forward to more researchers exploring the potential of LLMs in the graph data mining domain through GraphInstruct. Our code for generating GraphInstruct is released publicly at: https://***/CGCL-codes/GraphInstruct. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Managing prosumer exports in distribution networks through participatory export limits

Managing prosumer exports in distribution networks through p...

引用

CIRED 2024 Vienna Workshop

作者： Ashish Kumar Karmaker Sam Behrens Bjorn Sturmberg Hemanshu Pota School of Engineering and Technology University of New South Wales Canberra Australia Energy Center Commonwealth Scientific and Industrial Research Organization Newcastle Australia College of Engineering and Computer Science Australian National University Canberra Australia

ISBN: (数字)9781837241224

This paper proposes an innovative stakeholder-centric approach for managing prosumer exports in distribution networks ensuring stakeholder benefits. The rapid inclusion of photovoltaic (PV) systems leads to excessive exports, affecting the stability and performance of the distribution networks and fostering effective export management. In addition, the emergence of vehicle-to-grid (V2G) services presents challenges that may exacerbate export-related issues. Several distribution companies use fixed export limits for PV prosumers without looking at network performance. Current studies suggest dynamic limits to unlock export capabilities, providing variable export opportunities while neglecting diverse capabilities and nodal disparities of prosumers. By amalgamating dynamic export limits and prosumer priority indexing, this paper endeavours to derive individualized export limits in distribution networks. This research examined dynamic export capabilities on a real Australian suburban distribution feeder with 966 customers utilizing diverse capacities, nodal situations, and network uncertainties. The prosumer priority ranking is based on nodal constraints, time, and individual capabilities. The paper highlights participatory export limits, utilizing dynamic export limits and individual rankings, to offer enhanced export flexibility, benefiting stakeholders both distribution network operators and prosumers. These stakeholder-centric export limits provide a promising avenue for seamless PV and V2G integration toward a sustainable and resilient energy ecosystem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor Movement Orchestration in Multi-GPU Training Systems

Tensor Movement Orchestration in Multi-GPU Training Systems

引用

IEEE Symposium on High-Performance computer Architecture

作者： Shao-Fu Lin Yi-Jung Chen Hsiang-Yun Cheng Chia-Lin Yang Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Computer Science and Information Engineering National Chi Nan University Nantou Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan

As deep neural network (DNN) models grow deeper and wider, one of the main challenges for training large-scale neural networks is overcoming limited GPU memory capacity. One common solution is to utilize the host memory as the external memory for swapping tensors in and out of GPU memory. However, the effectiveness of such tensor swapping can be impaired in data-parallel training systems due to contention on the shared PCIe channel to the host. In this paper, we propose the first large-model support framework that coordinates tensor movements among GPUs to alleviate PCIe channel contention. We design two types of coordination mechanisms. In the first mechanism, PCIe channel accesses from different GPUs are interleaved by selecting disjoint swapped-out tensors for each GPU. In the second method, swap commands are orchestrated to avoid contention. The effectiveness of these two methods depends on the model size and how often the GPUs synchronize on gradients. Experimental results show that compared to large-model support that is oblivious to channel contention, the proposed solution achieves average speedups of 38.3% to 31.8% when the memory footprint size is 1.33 to 2 times the GPU memory size.

关键词： Training Deep learning Tensors Computational modeling Neural networks Graphics processing units Full-duplex system

来源：评论

学校读者我要写书评

暂无评论

Applying 3D Human Hand Pose Estimation to Teleoperation

Applying 3D Human Hand Pose Estimation to Teleoperation

引用

Robotics and computer Vision (ICRCV), International Conference on

作者： Rui Li Haopeng Lu Siwei Ma Chen Cui National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China Cooperative Medianet Innovation Center Shanghai Jiaotong University Shanghai China

3D human hand pose estimation from visual data has received an increasing amount of attention, and the availability of low-cost depth cameras gives a great impetus to the development of this field. Nearly all recent hand pose estimation methods are oriented towards unified evaluation criteria defined by popular public benchmark datasets: the ultimate goal is to reduce the estimation error. However, the fact is that there exists a gap between human hand pose estimation and its applications. It is unclear how to recover global and local degrees of freedom from a set of structural hand joints, which is a necessary condition to apply human hand pose estimation to teleoperation, i.e., mapping estimated human hand poses at the master side to robotic hand poses at the slave side. Conventional teleoperation systems are implemented with the aid of a data glove or essentially built on gesture recognition. These solutions are inferior to vision-based hand pose estimation in offering an easy-to-use and natural human-robot interaction interface. In this paper, we propose three methods to teleoperate robotic hands by 3D vision-based human hand pose estimation. The feasibility of the three methods is tested in a simulated environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Self-Localization of Wireless Acoustic Sensor Networks

引用

IEEE Internet of Things Journal 2025年第12期12卷 21646-21661页

作者： Wang, Xu Hu, De Liu, Rui Bao, Feilong Inner Mongolia University College of Computer Science Hohhot010021 China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot 010021 China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot 010021 China

Wireless acoustic sensor networks (WASNs), or the so-called internet of audio things (IoAuTs), have attracted increasing attention in the IoT community. As the geometry structure of WASNs is required in audio/speech processing tasks like source localization or acoustic beamforming, automatic self-localization of sensors is necessary. However, most of the existing approaches suffer from poor stability, as their constructed cost functions involve non-convex programming. To address this issue, we investigate the robust self-localization (or geometry calibration) of WASNs in this paper. Specifically, a rough self-localization (RSL) method is first presented based on measurements including time-difference-of-arrivals (TDoAs), direction-of-arrivals (DoA), and energy-rates (ERs), and its closed-form solution is further derived. As ER estimates are sensitive to acoustic environments, the performance of the RSL method is somewhat limited. Therefore, a precise self-localization (PSL) method is then developed by building a weighted (and non-convex) TDoA-DoA cost function, after regarding the RSL approach as an initialization step. As the RSL offers better initial values compared with existing initialization strategies, the combination of RSL and PSL methods (named as RSL-PSL method) shows stronger robustness and stability. In addition, computational complexity of both RSL and PSL methods are analyzed in details. Finally, the Cramér-Rao Bound (CRB) of the PSL method is derived to show its theoretical lower bound. The proposed RSL-PSL method outperforms the state-of-the-arts in terms of stability and accuracy, which is confirmed by numerical real-world and simulation experiments. © 2014 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature 39

Breaking Barriers in Physical-World Adversarial Examples: Im...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China

ISBN: (纸本)157735897X

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method's superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method's effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

research on single cell membrane algorithm and engineering application based on membrane computing theory 2

Research on single cell membrane algorithm and engineering a...

引用

2nd International Conference on Electronics, Electrical and Information engineering, ICEEIE 2022

作者： Song, Qi Huang, Yourui Xu, Jiachang Lai, Wenhao Xu, Shanyong Han, Tao Rong, Xue School of Electrical and Information Engineering Anhui University of Science and Technology Anhui Province Huainan232000 China Joint National-Local Engineering Research Center for Safe and Precise Coal Mining Anhui University of Science and Technology Anhui Province Huainan232000 China School of Computer Science and Engineering Anhui University of Science and Technology Anhui Province Huainan232000 China

Membrane computing is a new computing paradigm with great significance in the field of computer science. The Multi-membrane search algorithm (MSA) is proposed based on the membrane computational population optimization theory. It showed excellent performance in the test. This paper further studies the performance characteristics of a single individual (Single Cell Membrane Algorithm, SCA) of MSA. SCA can generate adaptive solution sets for problems of different dimensions. Through transcription and reprocessing rules, new weakly correlated feasible solutions are formed for global search and local exploration. This paper is based on the unimodal Sphere function and the multimodal Rastrigr function, at dim=3, 5, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 300, 500, 1000 and Q=1.00, 0.75, 0.50, 0.40, 0.30, 0.20, 0.10, 0.005, 0.025, 0.010, the SCA was optimized for 1000 iterations. Analyze the impact of the key parameter Q of SCA on the search performance of the algorithm in problems of different dimensions. The results show that under the set conditions, SCA has better performance when Q is 0.010 and 0.025 in the unimodal function test. In the multimodal function test, SCA has better performance when dim≤100 and Q≤0.200, and when dim>100 and Q≥0.200. In addition, this paper employs one engineering problem: I-beams to perform engineering tests on SCA and obtain results superior to other algorithms participating in the comparison. The test and comparison results show that SCA can also be used as a derivative algorithm of MSA, and has good performance. © Published under licence by IOP Publishing Ltd.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

research of Virtual Simulation Experiment Course Resource Intelligent Information System Construction 2

Research of Virtual Simulation Experiment Course Resource In...

引用

2nd IEEE International Conference on Power, Electronics and computer Applications, ICPECA 2022

作者： Wang, Yangping Dang, Jianwu Yong, Jiu Wang, Wenrun Yue, Biao Jin, Fangrui Computer Science and Technology Experimental Teaching Demonstration Center of National Lanzhou Jiaotong University National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University Gansu Prov. Eng. Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou730070 China National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University College of Intelligence and Computing Tianjin University Computer Science and Technology Experimental Teaching Demonstration Center of National Lanzhou Jiaotong University Gansu Prov. Eng. Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou730070 China College of Electronic and Information Engineering Lanzhou Jiaotong University Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou730070 China

ISBN: (纸本)9781665442763

In order to enable the construction of virtual simulation experiment resources in colleges and universities to keep up with the development of professional technology, this paper proposes to build a 'diversified virtual simulation experiment teaching resource construction system' through exploration and research. With the help of virtual reality, AR, panoramic roaming, video and other technologies, it provides a unified development framework, development documents and case templates for professional teachers to independently develop virtual simulation experiment teaching resources in line with undergraduate teaching, and helps teachers quickly build virtual simulation experiment resources in accordance with unified standards. It effectively solves the problems that it is difficult for college teachers to independently develop virtual simulation courseware and the technology is not unified. © 2022 IEEE.

关键词： Virtual reality

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：