检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xiang, Wenzhao Liu, Chang Yu, Hongyang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Peng Cheng Laboratory China University of Chinese Academy of Sciences China Department of Electronic Engineering Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain abundant redundant information, leading the pixel-based MIM reconstruction process to focus excessively on finer details such as textures, thus prolonging training times unnecessarily. Addressing this challenge requires a shift towards a compact representation of features during MIM reconstruction. Frequency domain analysis provides a promising avenue for achieving compact image feature representation. In contrast to the commonly used Fourier transform, wavelet transform not only offers frequency information but also preserves spatial characteristics and multi-level features of the image. Additionally, the multi-level decomposition process of wavelet transformation aligns well with the hierarchical architecture of modern neural networks. In this study, we leverage wavelet transform as a tool for efficient representation learning to expedite the training process of MIM. Specifically, we conduct multi-level decomposition of images using wavelet transform, utilizing wavelet coefficients from different levels to construct distinct reconstruction targets representing various frequencies and scales. These reconstruction targets are then integrated into the MIM process, with adjustable weights assigned to prioritize the most crucial information. Extensive experiments demonstrate that our method achieves comparable or superior performance across various downstream tasks while exhibiting higher training efficiency. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Thermal constraint control of reversible solid oxide cell for optimal system efficiency

引用

International Journal of Hydrogen Energy 2025年 134卷 198-211页

作者： Xu, Yuanwu Yin, Jie Wang, Jingjing Wu, Xiao-long Peng, Jingxuan Tang, Ruifeng Zou, Suhang Fu, Xiaowei Li, Xi School of Artificial Intelligence and Automation Wuhan University of Science and Technology Hubei Wuhan430081 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China School of Information Engineering Nanchang University Jiangxi Nanchang330031 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore China-Poland Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China

Reversible solid oxide cell (RSOC) demonstrates considerable promise in multimodal energy conversion architectures, particularly as a technology for hydrogen-based energy storage systems. Nevertheless, under dynamic operating regimes with time-varying current inputs, realizing time-efficient and reliable transitions to steady-state operation remains difficult. This difficulty arises from the intricate coupling of thermal, electrical, and gaseous processes within the RSOC system. This study aims to address these challenges by developing a 5 kW mathematical model of the RSOC system. The proposed model enables systematic investigation of thermal safety issues arising during current switching operations while introducing a thermal constraint control strategy to enhance both system efficiency and thermal safety performance. This efficiency-driven study employs the Grid Search algorithm to identify optimal steady-state operating points for the RSOC system, ensuring strict adherence to safety constraints across varying current inputs. Furthermore, by integrating the pre-identified optimal operating points as feedforward control with Model Predictive Control (MPC)-based feedback correction, this hybrid strategy effectively mitigates stack temperature gradient overshoot while synchronously ensuring optimal system efficiency throughout current transition processes. Under simulated variable current inputs, the proposed RSOC system model and control strategy demonstrate the capability to constrain stack temperature gradient overshoot within 2.3K while enhancing transient efficiency by 5 %–8 %, achieving a peak system efficiency of 85 %. It provides a novel methodology for safe and efficient working with intermittent renewable energy. © 2025 Hydrogen Energy Publications LLC

关键词： Thermal variables control

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

arXiv

引用

arXiv 2024年

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Multimodal Knowledge Graph Embeddings via Lorentz-based Contrastive Learning

Multimodal Knowledge Graph Embeddings via Lorentz-based Cont...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ruizhou Liu Zongsheng Cao Zhe Wu Qianqian Xu Qingming Huang School of Computer Science and Technology University of Chinese Academy Sciences Beijing China Department of Networked Intelligence Pengcheng Laboratory Shenzhen China Institute of Information Engineering Chinese Academy Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Multimodal knowledge graph embeddings (MKGE) have recently garnered significant attention. Unlike traditional unimodal knowledge graph embeddings, MKGE integrates both structural and multimodal knowledge to represent entities within a unified framework. However, real-world entities exhibit heterogeneity, often resulting in semantic inconsistencies where structurally similar embeddings may diverge significantly in their multimodal representations. Previous approaches primarily focus on directly fusing structural and multimodal embeddings, thus overlooking the issue of semantic-embedding inconsistency. To tackle this issue, we propose a new multimodal knowledge graph embedding method via Lorentz-based contrastive learning (LCKGE). we firstly introduce a well-designed nearest-neighbor fusion module via contrastive learning for multimodal fusion. Then, an attention-based Lorentz transformation is proposed for capturing more complex geometric information in MKGs. Furthermore, a series of comprehensive experiments are conducted to demonstrate the effectiveness of our model. We provide the code and appendix of LCKGE in https://***/RuizhouLiu/LCKGE

关键词： Codes Semantics Knowledge graphs Contrastive learning Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Koebe Type Theorems and Pre-Schwarzian of Harmonic K-quasiconformal Mappings,and Their Applications

引用

Acta Mathematica Sinica,English Series 2022年第11期38卷 1965-1980页

作者： Shao Lin CHEN Saminathan PONNUSAMY College of Mathematics and Statistics Hengyang Normal UniversityHengyang 421002P.R.China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang 421002P.R.China Department of Mathematics Indian Institute of Technology MadrasChennai-600036India

In this article,we first establish an asymptotically sharp Koebe type covering theorem for harmonic K-quasiconformal *** we use it to obtain an asymptotically Koebe type distortion theorem,a coefficients estimate,a Lipschitz characteristic and a linear measure distortion theorem of harmonic K-quasiconformal *** last,we give some characterizations of the radial John disks with the help of pre-Schwarzian of harmonic mappings.

关键词： Harmonic K-quasiconformal mapping Koebe type covering theorem Koebe type distortion theorem Radial John disk

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

arXiv

引用

arXiv 2025年

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

A SAR Target Recognition Strategy Guided by Electromagnetic Scattering Feature

A SAR Target Recognition Strategy Guided by Electromagnetic ...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yifei Yin Liang Chen Lujiao Liu Yufan Meng Fan Chen Hao Shi Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

SAR target Automatic Target Recognition (ATR) is indispensable in SAR image interpretation. Recently, deep learning technology has been widely used in SAR target recognition tasks. Most networks achieve incremental improvements in target recognition by modifying their structures to extract visual features of targets. However, due to the unique imaging mechanism, relying solely on visual features often leads to the loss of target information. In contrast, the ASC model, which captures the electromagnetic scattering characteristics of the target, plays a crucial role in target recognition tasks. Unfortunately, traditional parameter estimation methods for extracting the ASC model are computationally expensive and time-consuming, making them impractical for real-world applications. To address these issues, we propose a novel target recognition method based on electromagnetic scattering features in this paper. First, a lightweight network-based feature extraction module is designed. Then, the target ASC image is used as the ground truth for guidance, with image intensity and target structure serving as the loss functions during training. Finally, an ASC model-guided feature fusion network is designed, utilizing the fused features for target recognition. On the MSTAR dataset, a visual assessment experiment demonstrated that the proposed feature extraction module effectively extracts electromagnetic scattering features under various operating conditions. Subsequently, in downstream classification tasks, the inclusion of the proposed module resulted in improved accuracy compared to other networks. Additionally, a visualization analysis of the classification network showed that, under the guidance of electromagnetic scattering features, the network achieved good interpretability.

关键词： Training Deep learning Visualization Parameter estimation Target recognition Computational modeling Electromagnetic scattering Imaging Feature extraction Radar polarimetry

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Temporal Modeling for Multi-object Tracking in Satellite Video

Multi-frame Temporal Modeling for Multi-object Tracking in S...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Bingqian Chai Tingting Qiao Baorong Xie Jue Wang Wenchao Liu National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Shanghai Aerospace Electronic Technology Institute Shanghai China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

With the advancement of remote sensing technology, video satellites have played an increasingly important role in both military and civilian domains, and they are widely used in areas such as military guidance, intelligent transportation, and disaster response. Multi-object tracking (MOT) in satellite video is a crucial research topic in these fields and has made certain progress. However, due to the difficulty of tracking objects in complex scene and low resolution, current MOT methods face issues of low accuracy in satellite video. In this work, we propose a joint-detection-and-tracking method called multi-frame temporal MOT (MFT-MOT). Firstly, a heatmap guided multi-frame temporal modeling method is introduced to extract features with temporal semantic information while suppressing background noise. Then, we utilize a weights-shared encoder-decoder network to facilitate interaction of temporal and spatial information and capture inter-frame object motion tracks at low resolution. Experiments on SAT-MTB dataset shows the effectiveness of our method.

关键词： Heating systems Satellites Tracking Semantics Transportation Feature extraction Trajectory Military satellites Spatial resolution Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Novel Gradient Descent Least-Squares (GDLSs) Algorithm for Efficient Gridless Line Spectrum Estimation With Applications in Tomographic SAR Imaging

A Novel Gradient Descent Least-Squares (GDLSs) Algorithm for...

引用

作者： Shi, Ruizhe Zhang, Zhe Qiu, Xiaolan Ding, Chibiao University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100190 China Suzhou Aerospace Information Research Institute Suzhou Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou Jiangsu215123 China CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Beijing100190 China

This article presents a novel efficient method for gridless line spectrum estimation problems with single snapshot and sparse signals, namely the gradient descent least-squares (GDLS) method. Conventional single-snapshot (a.k.a. single-measure vector or SMV) line spectrum estimation methods either rely on smoothing techniques that sacrifice the range and/or azimuth resolution or adopt the sparsity constraint and utilize the compressed sensing (CS) method by defining prior grids and resulting in the off-grid problem. Recently emerged atomic norm minimization (ANM) methods achieved gridless SMV line spectrum estimation, but its computational complexity is extremely high;thus, it is practically infeasible in real applications with large problem scales. Our proposed GDLS method reformulates the line spectrum estimations problem into a least-squares (LSs) estimation problem and solves the corresponding objective function via a gradient descent algorithm in an iterative fashion with efficiency. The convergence guarantee, computational complexity, and performance analysis for evenly distributed antenna array cases are discussed in this article. Numerical simulations show that the proposed GDLS algorithm outperforms the state-of-the-art methods, for example, CS and ANM, in terms of estimation performances. It can completely avoid the off-grid problem, and its computational complexity is significantly lower than ANM. Our method has been tested in tomographic SAR (TomoSAR) imaging applications via simulated and real experimental data. Results show the great potential of the proposed method in terms of better cloud point performance and eliminating the gridding effect. © 1980-2012 IEEE.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

A Helmet-Based Hemispherical-Conformal Wearable Array Antenna with Broad Bandwidth, Wide-Angle Coverage and Reconfigurable Dual Circular Polarizations for WBAN Applications

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Tang, Wenfei Gao, Xiang Ding, Chuanfei Xu, Ziang Guo, Kun Bu, Xiangyuan An, Jianping Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing Institute of Technology School of Cyberspace Science and Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China

This paper presents a helmet-based hemispherical-conformal wearable array antenna with broad bandwidth, wide-angle coverage and reconfigurable dual circular polarizations (CPs) that is suitable for wireless body area network (WBAN) applications. First, a broadband and polarization-reconfigurable conformal radiating element is designed, which features a single-feed reconfigurable crossed dipole incorporated with parasitic patches above a ground plane for attaining unidirectional radiations. By integrating four PIN diodes on four arms of the crossed dipole, the element can flexibly switch its polarization states among two orthogonal CP modes. Four sector-shaped parasitic patches placed in four quadrants of the crossed dipole help to expand the operating bandwidth. Furthermore, we design a 12-element helmet-based hemispherical-conformal polarization-reconfigurable wearable array that is arranged in special configuration for increasing the gain, coverage range and orientation flexibility for WBAN systems. The measured results show the proposed conformal wearable array exhibits an overlapped 3-dB axial-ratio bandwidth of up to 29.6% and -10-dB impedance bandwidth of 69.8% at around 3 GHz for two reconfigurable CP modes. Besides, it has a relatively wide beam coverage range of 110° × 360 ° and a peak measured gain of more than 8 dBi for both polarization modes. © 1963-2012 IEEE.

关键词： Circular polarization

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：