检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhao, Tianxin Liu, Yingxin Su, Xiangdong Li, Jiang Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology China

ISBN: (纸本)9782493814104

The mainstream approaches view the knowledge graph-to-text (KG-to-text) generation as a sequence-to-sequence task and fine-tune the pre-trained model (PLM) to generate the target text from the linearized knowledge graph. However, the linearization of knowledge graphs and the structure of PLMs lead to the loss of a large amount of graph structure information. Moreover, PLMs lack an explicit graph-text alignment strategy because of the discrepancy between structural and textual information. To solve these two problems, we propose a synergetic KG-to-text model with a dual-path encoder, an alignment module, and a guidance module. The dual-path encoder consists of a graph structure encoder and a text encoder, which can better encode the structure and text information of the knowledge graph. The alignment module contains a two-layer Transformer block and an MLP block, which aligns and integrates the information from the dual encoder. The guidance module combines an improved pointer network and an MLP block to avoid error-generated entities and ensures the fluency and accuracy of the generated text. Our approach obtains very competitive performance on three benchmark datasets. Our code is available from https://***/IMU-MachineLearningSXD/G2T. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Joint state-sharing and truncation BCJR for power-efficient coherent optical interconnections utilizing symbol-rate sampling DSP over a hollow-core fiber

引用

Optics Letters 2025年第10期50卷 3461-3464页

作者： Wang, Chenchen Li, Zhipei Dong, Ze Gao, Ran Song, Junyuan Mai, Tianle Guo, Dong Chang, Huan Pan, Xiaolong Zhu, Lei Xin, Xiangjun School of Information and Electronics Beijing Institute of Technology Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China School of Integrated Circuits Beijing University of Posts and Telecommunications Beijing100876 China

Power-efficient digital signal processing (DSP) architectures are indispensable for enabling the sustainable scalability of optical networks in next-generation data center interconnects (DCIs). This paper introduces a minimalist symbol-rate sampling (SRS) DSP framework for coherent optical systems, seamlessly integrated with a hollow-core fiber (HCF) to enable ultra-low-complexity signal processing. The core of this framework is the joint state-sharing and truncation Bahl–Cocke–Jelinek–Raviv (JSST-BCJR) algorithm, which enhances hardware efficiency by eliminating up to 91% of state-space computations, significantly reducing computational complexity while maintaining negligible performance degradation. Experimental validation confirms the feasibility of the proposed minimalist SRS-DSP framework through the successful transmission of a 100-Gbaud 16QAM signal over 20.6 km of HCF. This work underscores the viability of SRS-DSP in power-constrained DCIs and highlights the synergistic integration of low-complexity DSP and HCF, offering a pathway toward power-efficient, high-throughput optical networks. © 2025 Optica Publishing Group. All rights are reserved.

关键词： Network coding

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 2

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

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

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

ISBN: (纸本)9798331515669

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. © 2024 IEEE.

关键词： Object tracking

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 2

A SAR Target Recognition Strategy Guided by Electromagnetic ...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

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

ISBN: (纸本)9798331515669

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. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

EpLSA: Synergy of Expert-prefix Mixtures and Task-Oriented Latent Space Adaptation for Diverse Generative Reasoning 30

EpLSA: Synergy of Expert-prefix Mixtures and Task-Oriented L...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Fujun Su, Xiangdong Li, Jiang Yan, Rong Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology China

ISBN: (纸本)9782493814104

Existing models for diverse generative reasoning still struggle to generate multiple unique and plausible results. Through an in-depth examination, we argue that it is critical to leverage a mixture of experts as prefixes to enhance the diversity of generated results and make task-oriented adaptation in the latent space of the generation models to improve the quality of the responses. At this point, we propose EpLSA, an innovative model based on the synergy of expert-prefix mixtures and task-oriented latent space adaptation for diverse generative reasoning. Specifically, we use expert-prefixes mixtures to encourage the model to create multiple responses with different semantics and design a loss function to address the problem that the semantics is interfered by the expert-prefixes. Meanwhile, we design a task-oriented adaptation block to make the pre-trained encoder within the generation model more effectively adapted to the pre-trained decoder in the latent space, thus further improving the quality of the generated text. Extensive experiments on three different types of generative reasoning tasks demonstrate that EpLSA outperforms existing baseline models in terms of both the quality and diversity of the generated outputs. Our code is publicly available at https://***/IMU-MachineLearningSXD/EpLSA. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Van der Waals epitaxial growth of single-crystal molecular film

引用

National Science Review 2024年第11期11卷 194-202页

作者： Lixin Liu Penglai Gong Kailang Liu Bingrong Huang Zhihao Zhang Yingshuang Fu Yu Wu Yinghe Zhao Meihui Wang Yongshan Xu Huiqiao Li Tianyou Zhai State Key Laboratory of Materials Processing and Die &Mould Technology School of Materials Science and EngineeringHuazhong University of Science and Technology Key Laboratory of Optic-Electronic Information and Materials of Hebei Province College of Physics Science and Technology Hebei University Wuhan National High Magnetic Field Center School of Physics Huazhong University of Science and Technology

Epitaxy is the cornerstone of semiconductor technology, enabling the fabrication of single-crystal *** advancements in van der Waals（vd W） epitaxy have opened new avenues for producing wafer-scale single-crystal 2D atomic crystals. However, when it comes to molecular crystals, the overall weak vd W force means that it is a significant challenge for small molecules to form a well-ordered structure during *** we demonstrate that the vd W epitaxy of Sb2O3molecular crystal, where the whole growth process is governed by vd W interactions, can be precisely controlled. The nucleation is deterministically modulated by epilayer–substrate interactions and unidirectional nuclei are realized through designing the lattice and symmetry matching between epilayer and substrate. Moreover, the growth and coalescence of nuclei as well as the layer-by-layer growth mode are kinetically realized via tackling the Schwoebel-Ehrlich barrier. Such precise control of vd W epitaxy enables the growth of single-crystal Sb2O3molecular film with desirable thickness. Using the ultrathin highly oriented Sb2O3film as a gate dielectric, we fabricated MoS2-based field-effect transistors that exhibit superior device performance. The results substantiate the viability of precisely managing molecule alignment in vd W epitaxy, paving the way for large-scale synthesis of single-crystal 2D molecular crystals.

关键词： van der Waals epitaxy inorganic molecular crystal layer-by-layer growth single-crystal film dielectric

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph-Enhanced Recommendation with Box Embeddings 23rd

Knowledge Graph-Enhanced Recommendation with Box Embeddings

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Liang, Qiuyu Wang, Weihua Lv, Lei Bao, Feilong 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 Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9789819783663

Knowledge graphs are used to alleviate the problems of data sparsity and cold starts in recommendation systems. However, most existing approaches ignore the hierarchical structure of the knowledge graph. In this paper, we propose a box embedding method for knowledge graph-enhanced recommendation system. Specifically, the box embedding represents not only the interaction between the user and the item, but also the head entity, the tail entity and the relation between them in the knowledge graph. Then the interaction between the item and the corresponding entity is calculated by the multi-task attention unit. Experimental results show that our method provides a large improvement over previous models in terms of Area Under Curve (AUC) and accuracy in publicly available recommendation datasets with three different domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Prototype Enhancement-Based Incremental Evolution Learning for Urban Garbage Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 398-411页

作者： Han, Honggui Fan, Xiaoye Li, Fangyu Beijing University of Technology Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Institute of Artificial Intelligence Beijing100124 China

Deep neural network (DNN) based on incremental learning provides support for efficient garbage classification tasks. However, it is always challenging to accurately learn and preserve the information of known classes for updating DNN while new tasks are continuously emerging, which also affects the generalization performance of the model. To solve these issues, an incremental evolution learning (IEL) method based on prototype enhancement is proposed to accurately preserve data and improve the model generalization ability. First, a prototype enhancement method based on multidimensional Gaussian kernel density estimation is designed, which extends the prototype of each sample based on high-dimensional nonlinear data distribution. Then, the prototype enhancement accurately represents the known class data. Second, a contrastive feature method is proposed to constrain the consistency of features between tasks, which reduces the deviation between different tasks. Then, the extraction preference caused by the class sample imbalance is balanced and the generalization ability is improved. Third, the proposed IEL is used for garbage classification with imbalanced class samples. IEL implements garbage classification by effectively adapting to the differences between known classes and new classes. Finally, experiments on four standard datasets and one public garbage dataset verify that IEL has a strong classification ability in the learning tasks with the increasing number of classes. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Representations for Prompt Learning 30

Hyperbolic Representations for Prompt Learning

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Chen, Nan Su, Xiangdong Bao, Feilong College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology China

ISBN: (纸本)9782493814104

Continuous prompt tuning has gained significant attention for its ability to train only continuous prompts while freezing the language model. This approach greatly reduces the training time and storage for downstream tasks. In this work, we delve into the hierarchical relationship between the prompts and downstream text inputs. In prompt learning, the prefix prompt acts as a module to guide the downstream language model, establishing a hierarchical relationship between the prefix prompt and subsequent inputs. Furthermore, we explore the benefits of leveraging hyperbolic space for modeling hierarchical structures. We project representations of pre-trained models from Euclidean space into hyperbolic space using the Poincaré disk which effectively captures the hierarchical relationship between the prompt and input text. The experiments on natural language understanding (NLU) tasks illustrate that hyperbolic space can model the hierarchical relationship between prompt and text input. We release our code at https://***/myaxxxxx/Hyperbolic-Prompt-Learning. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Computed Tomography Image Segmentation of Renal Tumors based on Deep Learning 5

Computed Tomography Image Segmentation of Renal Tumors based...

引用

5th International Conference on Image, Video processing, and Artificial Intelligence, IVPAI 2023

作者： Kang, Li Song, Xinxin Gao, Zhijian The College of Electronics and Information Engineering Shenzhen University 518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9781510674660

The incidence of renal tumors continues to rise each year, posing a serious threat to human health. Accurate segmentation of lesions is crucial for effective treatment. To enhance the segmentation performance of kidneys and renal tumors in CT images, this paper proposes a deep learning-based segmentation framework. The framework adopts a two-stage approach, starting from rough segmentation and progressing to fine segmentation, utilizing deep learning techniques. In the rough segmentation stage, a prior contour-assisted training technique is employed to extract the region of interest, namely kidneys and renal tumors. In the fine segmentation stage, an improved 3D convolution-based U-net model is proposed. Additionally, a novel loss function incorporating the mean and variance of pixel values of kidneys and renal tumors is introduced for fine-tuning. Given the limited data available, abdominal dataset images are used for pre-training the model. Through transfer learning, the model can learn common features from abdominal images. © 2024 SPIE. All rights reserved.

关键词： Tumors

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：