检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Shangtong Gui Chenze Shao Zhengrui Ma Xishan Zhang Yunji Chen Yang Feng State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Cambricon Technologies State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https://***/ictnlp/PCFG-NAT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PD-SDF: Dynamic Surface Reconstruction Based on Plane Decomposition for Single View RGB-D Videos

PD-SDF: Dynamic Surface Reconstruction Based on Plane Decomp...

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Li, Jinwen Xie, Weixing Yao, Junfeng Wu, Shaoqi Peng, Youhong Ge, Mengyuan Dong, Xiao Center for Digital Media Computing School of Film School of Informatics Xiamen University China National Institute for Data Science in Health and Medicine Xiamen University China Jiujiang Research Institute of Xiamen University Jiujiang China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism China Guangdong Provincial/Zhuhai Key Laboratory of IRADS BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9798350368741

Surface reconstruction of dynamic scenes from single view videos is a challenging task due to the highly ill-posed and under-constrained nature. Existing single view reconstruction methods suffer from severe quality issues, such as surface distortion and mesh adherison. In this paper, we propose an efficient dynamic representation network, PD-SDF, which consists of a 4D motion field and a 3D geometry field. The explicit disentanglement of motion and geometry based on planar factorization guarantees the mesh consistency across frames. Specifically, to address the mesh adhesion problem, we design a depth-guided sampling strategy to focus on optimizing the SDF field near the object surface. Due to insufficient geometric cues, we design various regularization strategies to constrain smoothness and topological correcness of the scene geometry. Extensive experiments show that our method outperforms existing methods in both appearance and geometry reconstruction. The project page: https://***/. © 2025 IEEE.

关键词： Dynamic Surface Reconstruction Neural SDF Field Single View Reconstruction

来源：评论

学校读者我要写书评

暂无评论

SILTD: Structural Information for LLM-Generated Text Detection

引用

International Journal of Machine Learning and Cybernetics 2025年

作者： Yang, Jing Wang, Shi Zi, Kangli Sun, Yanshun Huang, Yuwei Luo, Tianyu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

The rapid development of large language models (LLMs) has significantly improved the quality and diversity of AI-generated content(AIGC). LLM-Generated text detection plays an important role in preventing the harmful misuse of large language models. Existing approaches primarily analyze texts individually, overlooking the structural relationships between them. This limitation restricts their ability to generalize across diverse LLMs, as they fail to capture the shared statistical patterns inherent in generated texts. To address this, an unsupervised-based structural information for LLM-generated text detection (SILTD) method is proposed. The key insight is that texts from different LLMs exhibit latent similarities in their generative statistical space, which can be modeled to improve cross-model generalization. First, we construct a multi-relational text graph based on the similarity of text features, which aims to model the intricate similarities and correlations between texts. Second, we propose a novel unsupervised graph clustering method. The multi-relational graph is transformed into an encoding tree, which is then optimized based on a two-dimensional structure entropy minimization algorithm to achieve hierarchical clustering of texts. Structural entropy minimization enables achieving high-quality clusters, by measuring the uncertainty of random walks within the graph. Finally, we introduce a new method that measures text similarity and computes the intensity of text aggregation within each cluster, to perform in-cluster label inference. Extensive experiments show that, compared to baseline methods, our approach is more effective and generalizable in detecting six popular LLMs across five datasets. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Clustering LLM-generated text detection Multi-relational graph Structural information

来源：评论

学校读者我要写书评

暂无评论

Temporal Feature Aggregation for Efficient 2D Video Grounding

Temporal Feature Aggregation for Efficient 2D Video Groundin...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Mohan Chen Yiren Zhang Jueqi Wei Yuejie Zhang Rui Feng Tao Zhang Shang Gao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics School of Information Technology Deakin University

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Video grounding aims to locate the target video moment in an untrimmed video based on a text query. Most existing methods employ 3D CNNs as the video feature extractor, incurring substantial computational costs. Only a few methods use 2D backbones for video feature extraction, and they suffer from diminished accuracy due to the inherent lack of temporal information within 2D features. To address this problem, we propose a novel 2D video grounding method called TFA that improves accuracy while minimizing computational costs. Our approach involves a query-guided temporal feature aggregation module designed to explicitly capture temporal information. We disentangle time intervals of input video frames and prediction spans to reduce computational overhead. Additionally, we introduce deformable attention into the multi-modal encoder for further enhancement. Extensive experiments on two public datasets demonstrate that our method outperforms previous 2D video grounding methods and achieves competitive results with most 3D methods at significantly reduced costs.

关键词： Three-dimensional displays Accuracy Costs Grounding Streaming media Feature extraction Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A Passive Mixed Loaded Over-Hundred-Octave Miniaturized Super-Wideband Antenna

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Xia, Yinfeng Li, Yingsong Xue, Wei Elsherbeni, Atef Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Hefei230601 China Colorado School of Mines GoldenCO United States

An over-hundred-octave miniaturized super- wideband antenna based on passive elements mixed loading is proposed and analyzed in this paper. The proposed antenna is composed of inversed E-radiation patch, feeding line, several passive mixed loaded elements. The entire size of the proposed antenna is 0.012λ×0.01λ×0.00005λ (where λ is the lowest frequency of realized bandwidth). Derived from the analysis of impedance and equivalent circuit, by properly adjusting the inversed E-radiation patch and loading 5 passive elements into the construction of the antenna in position, the bandwidth is greatly improved. The simulated and measured results show that a -10dB fractional bandwidth of 196.2% is realized. Moreover, good omni-directional radiation patterns within the operating frequency band have been achieved from 10MHz to 1051MHz for HF, VHF and UHF applications. © 2002-2011 IEEE.

关键词： Antenna feeders

来源：评论

学校读者我要写书评

暂无评论

Fast Near-field Computational Imaging with Deep Neural Networks

Fast Near-field Computational Imaging with Deep Neural Netwo...

引用

IEEE International Conference on Radar

作者： Fafa Zhao Zhenhua Wu Xueli Pan Lixia Yang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education East China Research Institute of Electronic Engineering Hefei China

ISBN: (纸本)9781665468893

With the capability to sculpt complex radiative wavefronts and couple energy from the reference wave to the desired radiation pattern, metasurface antennas have gained tremendous progress in recent years. The flexibility in antenna design gives rise to a bunch of metasurface antennas, while there is still a comprise between the needed operation band and radiation field pattern coherence. Furthermore, the relatively low sampling ratio and overlap between frequency measurement modes would inevitably pose a great challenge for matched filter and other advanced sparsity-driven post-processing imaging algorithms. In this paper, we design a deep neural network to achieve fast scene image reconstruction. The trained network could fastly reconstruct the imaged object in both low scene compressed ratio and high coherence of the measurement modes. The imaging experiments with measured radiation field data are conducted to verify the effectiveness of our method.

关键词： Antenna measurements Deep learning Neural networks Imaging Coherence Radar imaging Radar antennas

来源：评论

学校读者我要写书评

暂无评论

BTC-Shadow: an analysis and visualization system for exposing implicit behaviors in Bitcoin transaction graphs

引用

Frontiers of Computer Science 2023年第6期17卷 167-169页

作者： Ding BAO Wei REN Yuexin XIANG Weimao LIU Tianqing ZHU Yi REN Kim-Kwang Raymond CHOO School of Computer Science China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Intelligent Geo-Information Processing Wuhan 430074China NSFOCUS Technologies Group Co. Ltd.Beijing 100089China School of Computing Sciences University of East AngliaNorwich NR47TJUK Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX 78249-0631USA

1 Introduction A Bitcoin ledger comprises a sizable number of transaction records,which can be utilized to make it easier to track and analyze the traits and patterns of cryptocurrency-related *** facilitate the visual analysis of Bitcoin,numerous tools with various aims have been *** example,MiningVis[1]and SuPoolVisor[2]are the analytics systems for Bitcoin mining pools,as well as[3-5]focus on the Bitcoin transaction graphs ***,due to our previous research requirements for Bitcoin transaction graphs,none of the available tools can provide exploring the features of connection related to the address and observe significant visual ***,using these tools is challenging to navigate to abnormal node clusters effortlessly from large node groups and then analyze the local interlink characteristics between transaction nodes with interactive analytics.

关键词： analytic implicit utilized

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithms for Minimizing the Kirchhoff Index via Adding Edges

arXiv

引用

arXiv 2025年

作者： Zhou, Xiaotian Zehmakan, Ahad N. Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China School of Computing Australian National University Canberra Australia

The Kirchhoff index, which is the sum of the resistance distance between every pair of nodes in a network, is a key metric for gauging network performance, where lower values signify enhanced performance. In this paper, we study the problem of minimizing the Kirchhoff index by adding edges. We first provide a greedy algorithm for solving this problem and give an analysis of its quality based on the bounds of the submodularity ratio and the curvature. Then, we introduce a gradient-based greedy algorithm as a new paradigm to solve this problem. To accelerate the computation cost, we leverage geometric properties, convex hull approximation, and approximation of the projected coordinate of each point. To further improve this algorithm, we use pre-pruning and fast update techniques, making it particularly suitable for large networks. Our proposed algorithms have nearly-linear time complexity. We provide extensive experiments on ten real networks to evaluate the quality of our algorithms. The results demonstrate that our proposed algorithms outperform the state-of-the-art methods in terms of efficiency and effectiveness. Moreover, our algorithms are scalable to large graphs with over 5 million nodes and 12 million edges. Copyright © 2025, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

A Cell Condition-Sensitive Frequency Segmentation Method Based on the Sub-Band Instantaneous Energy Spectrum of Aluminum Electrolysis Cell Voltage

引用

Engineering 2021年第9期7卷 1282-1292页

作者： Zhaohui Zeng Weihua Gui Xiaofang Chen Yongfang Xie Hongliang Zhang Yubo Sun School of Automation Central South UniversityChangsha 410083China Key Laboratory of Intelligent Computing&Information Processing Ministry of EducationXiangtan UniversityXiangtan 411105China School of Metallurgy and Environment Central South UniversityChangsha 410083China

Cell voltage is a widely used signal that can be measured online from an industrial aluminum electrolysis cell.A variety of parameters for the analysis and control of industrial cells are calculated using the cell *** this paper,the frequency segmentation of cell voltage is used as the basis for designing filters to obtain these *** on the qualitative analysis of the cell voltage,the sub-band instantaneous energy spectrum(SIEP)is first proposed,which is then used to quantitatively represent the characteristics of the designated frequency bands of the cell voltage under various cell ***,a cell condition-sensitive frequency segmentation method is *** proposed frequency segmentation method divides the effective frequency band into the[0,0.001]Hz band of lowfrequency signals and the[0.001,0.050]Hz band of low-frequency noise,and subdivides the lowfrequency noise into the[0.001,0.010]Hz band of metal pad abnormal rolling and the[0.01,0.05]Hz band of sub-low-frequency *** with the instantaneous energy spectrum based on empirical mode decomposition,the SIEP more finely represents the law of energy change with time in any designated frequency band within the effective frequency band of the cell *** proposed frequency segmentation method is more sensitive to cell condition changes and can obtain more elaborate details of online cell condition information,thus providing a more reliable and accurate online basis for cell condition monitoring and control decisions.

关键词： Sub-band instantaneous energy spectrum Cell condition-sensitive frequency band Frequency segmentation Metal pad abnormal rolling Aluminum electrolysis

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification 39

Bidirectional Logits Tree: Pursuing Granularity Reconcilemen...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lu, Zhiguang Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

ISBN: (纸本)157735897X

This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

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：