检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Wang, Yanzi Xiong, Jianyu Zha, Yaohua Xia, Shu-Tao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China

ISBN: (纸本)157735897X

Sampling strategy (e.g., fixed farthest point sampling) of point cloud has been an essential step for developing practical solutions in 3D computer vision tasks. Previous fixed sampling is simple, but suffer from suboptimal performance for downstream tasks. To adapt to target networks properly, adaptive sampling methods with trainable parameters have been recently developed to enhance the performance. However, existing adaptive sampling methods still suffer from the over-coupling problem of target network, and thus become model-specific, which limits their practical applications. To address this issue, we propose a novel general cross-scale decoupled sampling method (GCD-sampling) for point cloud, which consists of original feature cache, cross-scale feature fusion and convex combination learning for better feature extraction. To reduce the coupling relationship with the target task network, our method only utilizes the point cloud coordinates as the input and output of itself. Besides, we introduce an arbitrary scale structure to enable parameter sharing across multi-scale sampling in point cloud networks. Extensive experiments on different architectures demonstrate the effectiveness of our method over other existing adaptive sampling methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Small sets of genuinely nonlocal GHZ states in multipartite systems

arXiv

引用

arXiv 2023年

作者： Xiong, Zong-Xing Zhang, Yongli Li, Mao-Sheng Li, Lvzhou Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China School of Mathematics and Systems Science Guangdong Polytechnic Normal University Guangzhou510665 China School of Mathematics South China University of Technology Guangzhou510641 China

A set of orthogonal multipartite quantum states are called (distinguishability-based) genuinely nonlocal if they are locally indistinguishable across any bipartition of the subsystems. In this work, we consider the problem of constructing small genuinely nonlocal sets consisting of generalized GHZ states in multipartite systems. For system (C2) ⊗ N where N is large, using the language of group theory, we show that a tiny proportion Θ(1/√2N) of states among the N-qubit GHZ basis suffice to exhibit genuine nonlocality. Similar arguments also hold for the canonical generalized GHZ bases in systems (Cd) ⊗ N, wherever d is even and N is large. What is more, moving to the condition that any fixed N is given, we show that d + 1 genuinely nonlocal generalized GHZ states exist in (Cd) ⊗ N, provided the local dimension d is sufficiently large. As an additional merit, within and beyond an asymptotic sense, the latter result also indicates some evident limitations of the "trivial othogonality-preserving local measurements" (TOPLM) technique that has been utilized frequently for detecting genuine nonlocality. © 2023, CC BY.

关键词： Group theory

来源：评论

学校读者我要写书评

暂无评论

Test Sequence Generation Based on Chain Unique Input-Output Sequence in FSM Conformance Testing

Test Sequence Generation Based on Chain Unique Input-Output ...

引用

作者： Weiwei Lin Hongwei Zeng School of Computer Engineering and Science Shanghai UniversityShanghai Key Laboratory of Computer Software Evaluating &Testing School of Computer Engineering and Science Shanghai University

This paper introduces a test method based on chain unique input/output(CUIO) sequence in finite state machine(FSM) conformance testing. For FSMs with UIO for each state, the test sequence based on CUIO can identify all the states and verify all the transitions. For FSMs without UIO for some states, the test sequence based on CUIO can identify as many states and verify as many transitions as possible. Meanwhile, W method is introduced to deal with the unidentified states and the unverified transitions. For FSMs without UIO for each state, the method completely degenerates to W method. It is proved by experiment that the average and maximum reduction rate are 45.5% and 63.2% comparing with UIO ***, the method is always feasible even when UIO method fails.

关键词： Test Sequence Generation Based on Chain Unique Input-Output Sequence in FSM Conformance Testing

来源：评论

学校读者我要写书评

暂无评论

Multicast Source Routing based on Bloomed Link Identifiers for LEO Satellite Network

Multicast Source Routing based on Bloomed Link Identifiers f...

引用

Satellite Computing (Satellite), IEEE International Conference on

作者： Peng Lian Fei Yan Hongbin Luo Zhiyuan Wang Shan Zhang School of Computer Science and Engineering Beihang University Beijing China National Laboratory for Software Developmnet Environment Beihang University Beijing China

The low earth orbit (LEO) satellite network has the potential to provide low-latency transmission for global Internet services. Due to the mobility of LEO satellites, the frequent handover between a ground station (GS) and satellites will significantly affect the quality of content delivery. To overcome this challenge, we propose a multicast source routing mechanism for large-scale LEO satellite networks. This mechanism enables the source satellite to flexibly select the routes towards multiple satellites covering the same GS, thus ensures seamless satellite handover. Different from IP-based multicast, our approach assigns link identifiers for each unidirectional inter-satellite link, which can enable us to achieve reliable and efficient packet forwarding. Specifically, we design the equivalent virtual links based on the link identifiers, which can mitigate the impact of occasional link failures by forwarding the packets via the alternative route. Moreover, we use two bloom filters to encode the route (i.e., physical and virtual link identifiers) into the packet header. This way, the intermediate satellites could efficiently forward the packet according to its link identifier table. We evaluate the performance of the proposed mechanism via packet-level simulation on OMNeT++. Results show that our proposed method outperforms IP-based routing in terms of end-to-end delay and delivery ratio.

关键词： Satellites Virtual links Web and internet services Low earth orbit satellites Handover Routing Delays

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

arXiv

引用

arXiv 2023年

作者： Jiang, Ding Ye, Mang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

A Low Self-Noise Fiber Optic Gyroscope Based on Dual-polarization Configuration for Geophysical Rotation Sensing

A Low Self-Noise Fiber Optic Gyroscope Based on Dual-polariz...

引用

2021 Asia Communications and Photonics Conference, ACP 2021

作者： Chen, Yanjun Cao, Yuwen Wang, Wenbo He, Yan Zhou, Tong Li, Zhengbin State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing100871 China School of Software and Microelectronics Peking University Beijing102600 China

A fiber optic gyroscope based on dual-polarization configuration_is designed and realized. The 24-hour stability test shows aself-noise level of 3 × 10−9 rad/s/√Hz within the frequency range of 0.001Hz to 1Hz. &... 详细信息

ISBN: (纸本)9781957171005

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Multi-Swarm Genetic Gray Wolf Optimizer with Embedded Autoencoders for High-Dimensional Expensive Problems

SSRN

引用

SSRN 2023年

作者： Zhai, Jiahui Bi, Jing Yuan, Haitao Zhou, Mengchu School of Software Engineering Faculty of Information Technology Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

High-dimensional expensive problems are often encountered in the design and optimization of complex robotic and automated systems and distributed computing systems, and they suffer from a time-consuming fitness evaluation process. It is extremely challenging and difficult to produce promising solutions in high-dimensional search space. This work proposes an evolutionary optimization framework with embedded autoencoders that effectively solve optimization problems with high-dimensional search spaces. Autoencoders provide strong dimension reduction and feature extraction abilities that compress a high-dimensional space to an informative low-dimensional one. Search operations are performed in a low-dimensional space, thereby guiding a whole population to converge to the optimal solution more efficiently. Multiple subpopulations coevolve iteratively in a distributed manner. One subpopulation is embedded by an autoencoder, and the other one is guided by a proposed Multi-swarm Gray wolf optimizer based on Genetic learning (MGG). Thus, the proposed multi-swarm framework is named Autoencoder-based MGG (AMGG). AMGG consists of three proposed strategies that well balance exploration and exploitation abilities, i.e., a Dynamic subgroup Number Strategy for reducing the number of subpopulations, a Subpopulation Reorganization Strategy for sharing useful information about each subpopulation, and a Purposeful Detection Strategy for jumping out of local optima and improving exploration ability. AMGG is compared with several widely used algorithms by using typical benchmark functions and a real-life optimization problem. Extensive experimental results prove that AMGG outperforms its peers in terms of search accuracy and convergence efficiency. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on Retentive Network

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on ...

引用

computer Information science and Application Technology (CISAT), International Conference on

作者： Ruilin Su Wanshan Zhang Dunhui Yu Hubei University Wuhan China Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. Aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model’s memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model’s own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing.

关键词： Training Knowledge engineering Accuracy Spread spectrum communication Knowledge graphs Transformers Sampling methods Cognition Natural language processing Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

arXiv

引用

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Illuminate Low-Light Image via Coarse-to-fine Multi-level Network 27th

Illuminate Low-Light Image via Coarse-to-fine Multi-level Ne...

引用

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Qiu, Yansheng Chen, Jun Wang, Xiao Jang, Kui National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China

ISBN: (纸本)9783030678319

Images under low light or against light are of low readability and visibility which in turn cause performance degradation of many computer vision tasks. As the crucial research objects for low-brightness image enhancement, reflectance as an invariant has color information, and illuminance as a variable has brightness information. Existing technologies prefer to represent the reflectance and illumination in the same network depth directly, which ignores the internal discrepancy and correlation of these two components, further causing the details vanished and artifacts noises. Consequently, we propose coarse-to-fine multi-level decouple and fusion network (CMDFN) to decompose the restoration tasks into two sub-tasks, and use decouple network (CMDN) to learn the joint features of reflectance and illumination at different network depths. To refine the joint representation and revise color information, fusion network (CMFN) is applied to promote the illuminations map by extracting the complementary and redundant information from the reflectance map. Finally, we integrate the refined illumination and reflectance to reproduce the predicted image. Especially, in CMFN, we introduce a process based on discriminate attention mechanism to balance the noise. Experimental results have demonstrated that our proposed network is superior other state of the art methods, both visually and quantitatively. © 2021, Springer Nature Switzerland AG.

关键词： Reflection

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：