检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Xiong, Zeyu Liu, Daizong Zhou, Pan Zhu, Jiahao Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Peking University Wangxuan Institute of Computer Technology China

ISBN: (纸本)9781728163277

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets' behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Detecting DTI Using Graph Embedding and Multi-Head Attention Mechanism

Detecting DTI Using Graph Embedding and Multi-Head Attention...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xiaoli Chen, Yaoyu Yang, Wenli Yu, HaiPing Wu, Zimo Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China China Graphics Society School of Information Wuhan Vocational College Professional Committee of Graphics and Big Data Wuhan China

ISBN: (纸本)9798350386226

Drug-target interaction (DTI) prediction has an important role in drug discovery, significantly expediting the drug design and development process. This paper proposes a new model, ERW-BiAN, that seamlessly integrates graph embedding representations with deep learning network. Specifically, we utilize an improved graph embedding model, ERW, to generate comprehensive feature vectors for each node within the knowledge graph. Subsequently, these feature vectors are fed into the BiAN model, which leverages an attention mechanism to assign precise weights to sequences. Experimental results demonstrate the superior accuracy and predictive prowess of ERW-BiAN in DTI prediction tasks. Furthermore, the case about COVID-19 shows that ERW-BiAN has the better application potential for predicting drug-target interactions. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation

arXiv

引用

arXiv 2025年

作者： Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W.B. Zhang, Ziyao Liang, Xiaohui B. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science University of Durham United Kingdom Zhongguancun Laboratory Beijing China

We address the challenging problem of fine-grained text-driven human motion generation. Existing works generate imprecise motions that fail to accurately capture relationships specified in text due to: (1) lack of effective text parsing for detailed semantic cues regarding body parts, (2) not fully modeling linguistic structures between words to comprehend text comprehensively. To tackle these limitations, we propose a novel fine-grained framework Fg-T2M++ that consists of: (1) an LLMs semantic parsing module to extract body part descriptions and semantics from text, (2) a hyperbolic text representation module to encode relational information between text units by embedding the syntactic dependency graph into hyperbolic space, and (3) a multi-modal fusion module to hierarchically fuse text and motion features. Extensive experiments on HumanML3D and KIT-ML datasets demonstrate that Fg-T2M++ outperforms SOTA methods, validating its ability to accurately generate motions adhering to comprehensive text semantics. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping

arXiv

引用

arXiv 2024年

作者： Wang, Meng Wang, Junyi Xia, Changqun Wang, Chen Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems Beihang University China PengCheng Laboratory China School of Computer Science and Technology Shandong University China Beijing Technology and Business University China

3D Gaussian splatting (3DGS) has recently demonstrated promising advancements in RGB-D online dense mapping. Nevertheless, existing methods excessively rely on per-pixel depth cues to perform map densification, which leads to significant redundancy and increased sensitivity to depth noise. Additionally, explicitly storing 3D Gaussian parameters of room-scale scene poses a significant storage challenge. In this paper, we introduce OG-Mapping, which leverages the robust scene structural representation capability of sparse octrees, combined with structured 3D Gaussian representations, to achieve efficient and robust online dense mapping. Moreover, OG-Mapping employs an anchor-based progressive map refinement strategy to recover the scene structures at multiple levels of detail. Instead of maintaining a small number of active keyframes with a fixed keyframe window as previous approaches do, a dynamic keyframe window is employed to allow OG-Mapping to better tackle false local minima and forgetting issues. Experimental results demonstrate that OG-Mapping delivers more robust and superior realism mapping results than existing Gaussian-based RGB-D online mapping methods with a compact model, and no additional post-processing is required. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology SydneyNSW2007 Australia Institute of Software Chinese Academy of Sciences Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 1982-2012 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

High-integrated photonic tensor core utilizing high-dimensional lightwave and microwave multidomain multiplexing

引用

Light(Science & Applications) 2025年第1期14卷 227-237页

作者： Xiangyan Meng Nuannuan Shi Guojie Zhang Junshen Li Ye Jin Shiyou Sun Yichen Shen Wei Li Ninghua Zhu Ming Li Key Laboratory of Optoelectronic Materials and Devices Institute of SemiconductorsChinese Academy of SciencesBeijing100083China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of SciencesBeijing100049China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing100049China China Academy of Space Technology(Xi’an) Xi’anShaanxi710100China WeChat Pay Lab 33 Shenzhen Tencent Computer System Co.Ltd.Shenzhen518054China Lightelligence Group Hangzhou311121China

The burgeoning volume of parameters in artificial neural network models has posed substantial challenges to conventional tensor computing *** from the available optical multidimensional information entropy,optical intelligent computing is used as an alternative solution to address the emerging challenges of electrical *** limitations,in terms of device size and photonic integration scale,have hindered the performance of optical ***,an ultrahigh computing density optical tensor processing unit(OTPU),which is grounded in an individual microring resonator(MRR),is introduced to respond to these *** the independent tuning of multiwavelength lasers,the operational capabilities of an MRR are orchestrated,culminating in the formation of an optical tensor *** design facilitates the execution of tensor convolution operations via the lightwave and microwave multidomain hybrid multiplexing in terms of the time,wavelength,and frequency of *** experimental results for the MRR-based OTPU show an extraordinary computing density of 34.04 TOPS/***,the achieved accuracy rate in recognizing MNIST handwritten digits was 96.41%.These outcomes signify a significant advancement toward the realization of high-performance optical tensor processing chips.

关键词： tuning resonator tensor

来源：评论

学校读者我要写书评

暂无评论

Why go full? elevating federated learning through partial network updates 24

Why go full? elevating federated learning through partial ne...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Haolin Wang Xuefeng Liu Jianwei Niu Wenkai Guo Shaojie Tang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China and Zhongguancun Laboratory Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo Buffalo New York

ISBN: (纸本)9798331314385

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction 29

CETA: A Consensus Enhanced Training Approach for Denoising i...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Liu, Ruri Mo, Shasha Niu, Jianwei Fan, Shengda School of Cyber Science and Technology Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China

Distantly supervised relation extraction aims to extract relational facts from texts but suffers from noisy instances. Existing methods usually select reliable sentences that rely on potential noisy labels, resulting in wrongly selecting many noisy training instances or underutilizing a large amount of valuable training data. This paper proposes a sentence-level DSRE method beyond typical instance selection approaches by preventing samples from falling into the wrong classification space on the feature space. Specifically, a theorem for denoising and the corresponding implementation, named Consensus Enhanced Training Approach (CETA), are proposed in this paper. By training the model with CETA, samples of different classes are separated, and samples of the same class are closely clustered in the feature space. Thus the model can easily establish the robust classification boundary to prevent noisy labels from biasing wrongly labeled samples into the wrong classification space. This process is achieved by enhancing the classification consensus between two discrepant classifiers and does not depend on any potential noisy labels, thus avoiding the above two limitations. Extensive experiments on widely-used benchmarks have demonstrated that CETA significantly outperforms the previous methods and achieves new state-of-the-art results. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

key Mention Pairs Guided Document-Level Relation Extraction 29

Key Mention Pairs Guided Document-Level Relation Extraction

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Jiang, Feng Niu, Jianwei Mo, Shasha Fan, Shengda State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Cyber Science and Technology Beihang University Beijing100191 China

Document-level Relation Extraction (DocRE) aims at extracting relations between entities in a given document. Since different mention pairs may express different relations or even no relation, it is crucial to identify key mention pairs responsible for the entity-level relation labels. However, most recent studies treat different mentions equally while predicting the relations between entities, leading to sub-optimal performance. To this end, we propose a novel DocRE model called key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier. These two modules could be iteratively optimized with an EM-based algorithm to enhance each other. We also propose a new method to solve the multi-label problem in optimizing the mention-level relation extractor. Experimental results on two public DocRE datasets demonstrate that the proposed model is effective and outperforms previous state-of-the-art models. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Physically Based Bidirectional Path Tacing Algorithm on the Tianhe-2 Supercomputer 25

Physically Based Bidirectional Path Tacing Algorithm on the ...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data Science and systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Wu, Yijia Zhang, Congpin Xu, Zhengwei Li, Ligang Chinese Academy of Sciences National Space Science Center Key Laboratory of Electronics and Information Technology for Space System Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences China School of Computer and Information Engineering Henan Normal University Henan Xinxiang China

ISBN: (纸本)9798350330014

Physically based ray tracing is a technique that involves creating a photo-realistic image from a 3D scene description by utilizing the laws of physics to simulate the behavior of light and matter. However, due to the random length of light samples and irregular memory access patterns, it can suffer from low scalability and severe load imbalance. As a result, the development of a framework for multi-node parallelism algorithm in physically based ray tracing is a significant challenge. To tackle these issues, this paper introduces a novel algorithm named distributed parallel physically based bidirectional path tacing algorithm (DP-BDPT). Through analyzing the physical essence of bidirectional path tracing algorithm and the light transport equation, we have devised a framework that carefully divides tasks between inter-compute nodes and intra-compute nodes. To support high scalability, we have developed a physically based architecture. Additionally, we have proposed a hybrid scheduling method to achieve load balancing. To further enhance performance, we have analyzed several key factors that affect rendering performance and implemented adaptive optimization techniques. The experiments conducted on the Tianhe-2 Supercomputer involving typical and challenging 3D scenes, namely the Cornell-box, Veach-bidir, and Teapot-full experiments, have illustrated that DP-BDPT demonstrate near-linear speedups as the number of CPU cores scales from 1200 to 9600, thereby demonstrating their efficiency when operating on a ten-thousand-core system. © 2023 IEEE.

关键词： Ray tracing

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：