检索结果-内蒙古大学图书馆

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Lyu, Youwei Guo, Heng Zhang, Kailong Li, Si Shi, Boxin School of Artificial Intelligence Beijing University of Posts and Telecommunications China State 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

Shape from polarization (SfP) benefits from advancements like polarization cameras for single-shot normal estimation, but its performance heavily relies on light conditions. This paper proposes SfPUEL, an end-to-end SfP method to jointly estimate surface normal and material under unknown environment light. To handle this challenging light condition, we design a transformer-based framework for enhancing the perception of global context features. We further propose to integrate photometric stereo (PS) priors from pretrained models to enrich extracted features for high-quality normal predictions. As metallic and dielectric materials exhibit different BRDFs, SfPUEL additionally predicts dielectric and metallic material segmentation to further boost performance. Experimental results on synthetic and our collected real-world dataset demonstrate that SfPUEL significantly outperforms existing SfP and single-shot normal estimation methods. The code and dataset is available at https://***/YouweiLyu/SfPUEL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-efficiency Brillouin lasing in a planar GeSbS spiral-ring resonator

引用

Chinese Optics Letters 2024年第7期22卷 71-76页

作者： Jingcui Song Yuhang Wei Chunxu Wang Shuixian Yang Yan Li Tianhua Feng Xiaojie Guo Zhaohui Li Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems and School of Electronics and Information Technology Sun Yat-sen UniversityGuangzhou 510006China Peng Cheng Laboratory Shenzhen 518000China Department of Electronic Engineering College of Information Science and TechnologyJinan UniversityGuangzhou 510632China Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications Institute of Photonics TechnologyJinan UniversityGuangzhou 510632China College of Physics and Optoelectronic Engineering Jinan UniversityGuangzhou 510632China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) Zhuhai 519000China

Stimulated Brillouin scattering in planar integrated circuits promises to realize compact and highly coherent *** we report efficient Brillouin lasing at telecommunication wavelength from a planar Ge_(25)Sb_(10)S_(65) chalcogenide(ChG)resonator with a high quality factor above 106.A low lasing threshold of 24.8 mW is achieved with a slope efficiency of 8.3%.An 8-kHz linewidth is measured for 1.56-mW on-chip output *** work offers a good opportunity to enrich the versatility and functionality of the ChG photonics on account of their intrinsic advantages of low loss,high third-order nonlinearity,and potential capacity for wafer-scale fabrication.

关键词： Brillouin lasing chalcogenide photonics planar integrated circuit high-Q resonator

来源：评论

学校读者我要写书评

暂无评论

Fully Hyperbolic Rotation for Knowledge Graph Embedding 27

Fully Hyperbolic Rotation for Knowledge Graph Embedding

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Liang, Qiuyu Wang, Weihua Bao, Feilong Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (纸本)9781643685489

Hyperbolic rotation is commonly used to effectively model knowledge graphs and their inherent ***, existing hyperbolic rotation models rely on logarithmic and exponential mappings for feature *** models only project data features into hyperbolic space for rotation, limiting their ability to fully exploit the hyperbolic *** address this problem, we propose a novel fully hyperbolic model designed for knowledge graph *** of feature mappings, we define the model directly in hyperbolic space with the Lorentz *** model considers each relation in knowledge graphs as a Lorentz rotation from the head entity to the tail *** adopt the Lorentzian version distance as the scoring function for measuring the plausibility of *** results on standard knowledge graph completion benchmarks demonstrated that our model achieves competitive results with fewer *** addition, our model get the state-ofthe-art performance on datasets of CoDEx-s and CoDEx-m, which are more diverse and challenging than *** code is available at https://***/llqy123/FHRE. © 2024 The Authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Efficient Task Offloading in Double Roadside RIS-assisted Vehicular Edge Computing Networks Using Deep Reinforcement Learning

引用

IEEE Transactions on Vehicular technology 2025年

作者： Xie, Yibin Shi, Lei Li, Zhehao Ding, Xu Fan, Yuqi Hefei University of Technology School of Computer Science and Information Engineering Anhui Provincial Key Laboratory of Industry Safety and Emergency Technology Hefei230601 China

The concept of vehicular edge computing (VEC) has recently been envisioned as a promising paradigm to satisfy the quality of service (QoS) requirement of delay-sensitive intelligent applications in future networks. However, the limited radio frequency communication range necessitates the dense deployment of communication infrastructures to accommodate the increasing number of connected vehicles and data traffic. This could lead to growing equipment and energy costs, hindering the full realization of the VEC system. To address such limitations, we introduce a double roadside reconfigurable intelligent surface (RIS) assisted VEC network in this paper, where RISs are deployed inside the coverage gaps between two RSUs to extend the service range. The research goal is to maximize the sum offloading efficiency by jointly optimizing offloading decisions, computation resource allocation, and phase shift vectors of RISs. Since the original problem is a challenging mixed-integer non-linear problem (MINLP), we decompose it into a top-problem for optimizing offloading destinations and phase shift vectors, and a sub-problem for optimizing offloading ratios and computation resources. We propose a deep reinforcement learning (DRL)-based algorithm for quickly obtaining near-optimal offloading decisions and phase shift vectors, alongside a Dinkelbach-based method for obtaining optimal offloading ratios and computation resource allocation. Simulation results demonstrate that our proposed algorithm achieves near-optimal performance compared to other benchmarks and enables real-time decision-making. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Abnormal Crowd Behavior Detection Based on the Fusion of Macro and Micro Features 26

Abnormal Crowd Behavior Detection Based on the Fusion of Mac...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Jiao, Shourong Lu, Dianjie Jia, Chuanhua Liu, Hong Zhang, Guijuan Shandong Normal University School of Information Science and Engineering Jinan250358 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250358 China State Key Laboratory of High-end Server & Storage Technology Jinan250101 China

ISBN: (纸本)9798350331684

There are two types of research on abnormal crowd behavior detection: micro modeling methods (e.g., crowd pose) and macro modeling methods (e.g., optical flow methods). In crowd evacuation, however, micro methods fail to solve the occlusion problem, while macro methods fail to address issues such as poor real-time performance and non-adaptive motion target detection. To address these issues, we propose a method that combines macro and micro methods to detect abnormal crowd behavior. Firstly, we extract the two-dimensional poses of moving people using the human pose estimation algorithm (OpenPose) and get the corresponding micro motion features. Secondly, we create an optical flow map of the video using the dense optical flow algorithm (Farneback) and a scene activity map by comparing the optical flow sizes between two consecutive frames. Then we derive the entropy change curve, which represents the macro motion features. Finally, we fuse micro and macro motion features and put the fused hybrid feature vectors into our classification network to train our model, and then find the transition time from micro to macro abnormal states in crowd evacuation videos. The experimental findings demonstrate that our proposed method can more accurately and quickly identify the abnormal behaviors that appear in evacuation scenes. © 2023 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Randomly coupled trench-assisted multicore fibers with different arrangements for high tolerance of manufacturing errors

引用

Science China(information Sciences) 2023年第11期66卷 260-272页

作者： Yongneng JIANG Jiajing TU Shecheng GAO Weiping LIU Zhaohui LI Department of Electronic Engineering College of Information Science and Technology Jinan University School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-sen University Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)

Randomly coupled multicore fibers(RC-MCFs) are promising candidates for long-haul transmission. However, the degree of coupling between the homogeneous cores of an RC-MCF is weakened if manufacturing errors appear. Therefore, a low-index trench layer is introduced into the coupled cores to investigate the effects of its position and thickness on the group index to enhance the tolerance of manufacturing errors. A depressed region is designed in the center of the core to solve the problem of the effective area decreasing because of the confinement of the low-index trench. Additionally, it is important to study the effective arrangement of the coupled cores to obtain a smaller group delay spread(GDS) within the limited 125-μm cladding; we discuss the single-layer and double-layer arrangements. A moderate range is found for both the bending radius and core pitch to minimize the GDS. For the single-layer arrangement, the degree of mixing is weak, and the degeneracy state does not easily change the bending conditions; thus, it may be a good candidate for designing systemically coupled multicore fibers. For the double-layer arrangement, the bending and twisting factors can induce sufficient mixing among the different modes to reduce GDS; thus,this arrangement is more suitable for the design of RC-MCFs.

关键词： manufacturing errors randomly coupled multicore fibers trench-assisted core single-layer arrangement double-layer arrangement

来源：评论

学校读者我要写书评

暂无评论

A Tolerance Classes Partition-Based Re-Definition of the Rough Approximations for Incomplete information System

A Tolerance Classes Partition-Based Re-Definition of the Rou...

引用

International Conference on Image, Vision and Intelligent Systems, ICIVIS 2021

作者： Wang, Lei Liu, Bin Cai, Xiangxiang Wang, Chong Jiangxi Provincial Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang330099 China College of Information Engineering Nanchang Institute of Technology Nanchang330099 China

ISBN: (纸本)9789811669620

The information with missing attribute value is known as the incomplete information system. In an incomplete information system, there exist tolerance relations satisfying reflexivity and symmetry among objects in the universe of discourse and the tolerance classes for each object can be derived from the tolerance relation directly. Generally speaking, the tolerance classes of all objects can form some coverages of the universe. The research of this paper is based on the tolerance classes of each object in the incomplete information system. Firstly, a method is proposed in which a partition of the universe is constructed by using tolerance classes of objects. Then, the upper and lower approximations of concept, i.e., a subset of universe, is re-defined on the basis of acquisition of the partition of the universe using proposed method and this new definition can improve the approximation accuracy of concept effectively compared to the traditional definition. Finally, an illustrated example is exhibited for demonstrating the method to obtain a partition to universe by tolerance class as well as the calculation of the rough approximations of concept based on the partition of universe by tolerance class. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： information use

来源：评论

学校读者我要写书评

暂无评论

RGR-KBQA: Generating Logical Forms for Question Answering Using Knowledge-Graph-Enhanced Large Language Model 31

RGR-KBQA: Generating Logical Forms for Question Answering Us...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Feng, Tengfei He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9798891761964

In the field of natural language processing, Knowledge Base Question Answering (KBQA) is a challenging task that involves accurately retrieving answers from structured knowledge. Existing methods often face issues when generating query statements using LLMs, as the knowledge introduced may be imprecise and the models themselves may exhibit hallucination problems, leading to low accuracy, particularly when dealing with complex questions. To address these challenges, we introduce a novel semantic parsing approach called RGR-KBQA, which adopts a Retrieve-Generate-Retrieve framework. The first retrieval step introduces factual knowledge from a knowledge graph to enhance the semantic understanding capabilities of LLMs, thereby improving generation accuracy of logical form. The second step uses a fine-tuned model to generate the logical form, and the final step involves unsupervised relation and entity retrieval to further enhance generation accuracy. These two retrieval steps help alleviate the hallucination problems inherent in LLMs. Experimental results show that RGR-KBQA demonstrate promising performance on CWQ and WebQSP datasets. © 2025 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal Consistency based Crowd Emotion Recognition 26

Spatial-temporal Consistency based Crowd Emotion Recognition

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhao, Chuanmiao Zhang, Guijuan Lv, Lei Liu, Hong Lu, Dianjie Shandong Normal University School of Information Science and Engineering Jinan250358 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250358 China State Key Laboratory of High-end Server & Storage Technology Jinan250101 China

ISBN: (纸本)9798350331684

In crowd evacuation scenarios, it is an effective way to ensure evacuation safety by recognizing real crowd emotions and then taking measures such as emotional infection to reduce crowd panic. However, factors such as distance, exposure, angle, and occlusion can lead to incomplete face expression information collection, thus failing to accurately identify crowd emotions. Therefore, it is still a very challenging problem to recognize individual emotions in the case of incomplete face expression information collection, and thus accurately identify crowd emotions during evacuation. To solve this problem, we propose a spatial-temporal consistency-based crowd emotion recognition method to accurately identify the real emotions of the crowd. First, for video frames that can capture the complete facial expression information, we use the residual network to accurately identify the individual emotion values in each frame. For video frames that cannot capture the complete facial expression information, we propose an individual emotion calculation model based on spatial-temporal consistency to calculate the individual emotion values in each frame. Second, we define the crowd panic level and obtain the real crowd emotion by calculation. Finally, we implement an end-to-end crowd panic emotion recognition system to verify our method. The experimental results show that the method can accurately calculate the crowd panic level, which is important for guiding crowd evacuation. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Attention Gate Based U-net for Retinal Vessel Segmentation 12

Multi-Attention Gate Based U-net for Retinal Vessel Segmenta...

引用

12th International Conference on information technology in Medicine and Education, ITME 2022

作者： Zhu, Yu Li, Rui Teng, Shenghua Cao, Xinrong Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China College of Computer and Control Engineering Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9798350310153

Retinal blood vessel segmentation images can be used to detect and evaluate various cardiovascular and ophthalmic diseases. However, due to the intricate vessel structures and blurred boundaries of vessels, it is a huge challenge to efficiently and accurately segment blood vessels. To deal with the above problems, this paper improves on the U-net by firstly using multi-scale feature convolution with kernels of varying size for feature extraction. Second, a non-local attention mechanism is applied to obtain richer global semantic information. Then multi-attention gate is used in the skip connection part by inputting feature maps of various scales and dimensions and selectively learning the interrelated regions, which improves the segmentation ability of the network model for the tiny structure of blood vessels. Quantitative and qualitative experimental results on two public datasets, DRIVE and CHASE-DB1, demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Blood vessels

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：