检索结果-内蒙古大学图书馆

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Fan, Yihao Siyu, E. Guo, Yuyao Li, Xinhang Lu, Liangjun Wang, Shuxiao Cai, Yan Chen, Jianping Zhou, Linjie State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai200050 China Shanghai Industrial μTechnology Research Institute Shanghai201800 China

We realize a hybrid integrated self-injection locking laser (SIL) with an ultra-narrow intrinsic linewidth of 5 Hz. With heterodyne synthesis using a pair of SILs, a microwave signal with a 4-kHz linewidth is achieved... 详细信息

ISBN: (纸本)9781957171395

关键词： Linewidth

来源：评论

学校读者我要写书评

暂无评论

FOUNDATION PIT DEFORMATION MEASUREMENT TECHNIQUE BASED ON GROUND-BASED INTERFEROMETRIC RADAR

FOUNDATION PIT DEFORMATION MEASUREMENT TECHNIQUE BASED ON GR...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wang, Changjun Zhou, Hanpu Wang, Jian Gao, Jiake Deng, Yunkai Tian, Weiming Beijing Building Research Institute Co. Ltd. CSCEC Beijing100076 China Radar Research Lab School of Information and Electronics Bejing Institute of Technology Bejing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology China Advanced Technology Research Institute Beijing Institute of Technology Jinan250300 China

ISBN: (纸本)9781839539954

The deformation monitoring data of foundation pit is an important criterion for forecasting and strengthening measures in the field of building safety. During the construction period, the foundation pit will be affected by load, temperature change, random disturbance and other effects to produce deformation. Due to the complex deformation process of foundation pit, it is hard to accurately describe and separate the load trend deformation and elastic thermal deformation by mathematical expression. Excessive thermal deformation may cause cracks in the surrounding pavement and affect the judgment of load deformation. This paper first introduces the deformation measurement method of foundation pit based on differential interferometry technology using ground-based interferometric radar. Based on the obtained deformation type, the simulation verifies the separation effect of wavelet transform on different deformation trends and periodic components. Through the foundation pit deformation monitoring experiment of Tongzhou infrastructure project, the wavelet transform method is used to decompose the foundation pit deformation curve, and the extracted periodic component has good consistency with the temperature information. © The Institution of Engineering & Technology 2023.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition

CoSign: Exploring Co-occurrence Signals in Skeleton-based Co...

引用

International Conference on Computer Vision (ICCV)

作者： Peiqi Jiao Yuecong Min Yanan Li Xiaotao Wang Lei Lei Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Xiaomi Inc. China

The co-occurrence signals (e.g., hand shape, facial expression, and lip pattern) play a critical role in Continuous Sign Language Recognition (CSLR). Compared to RGB data, skeleton data provide a more efficient and concise option, and lay a good foundation for the co-occurrence exploration in CSLR. However, skeleton data are often used as a tool to assist visual grounding and have not attracted sufficient attention. In this paper, we propose a simple yet effective GCN-based approach, named CoSign, to incorporate Co-occurrence Signals and explore the potential of skeleton data in CSLR. Specifically, we propose a group-specific GCN to better exploit the knowledge of each signal and a complementary regularization to prevent complex co-adaptation across signals. Furthermore, we propose a two-stream framework that gradually fuses both static and dynamic information in skeleton data. Experimental results on three public CSLR datasets (PHOENIX14, PHOENIX14-T and CSL-Daily) show that the proposed CoSign achieves competitive performance with recent video-based approaches while reducing the computation cost during training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Embedding Based Graph Convolutional Network for Link Prediction

Knowledge Graph Embedding Based Graph Convolutional Network ...

引用

International Conference on advanced Cloud and Big Data (CBD)

作者： Qiang Wu Qing He Henan Institute of Advanced Technology Zhengzhou University Zhengzhou P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Science (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Science Beijing China

Knowledge Graph Embedding (KGE) aims to capture the inherent structural information within knowledge graphs (KGs) by means of representation learning. This is of paramount importance for various downstream tasks, including personalized recommendations, intelligent search, and relation extraction. Graph Convolutional Networks (GCNs), a type of neural network, have recently demonstrated significant success in modeling data structured as graphs. However, these models often overlook the intricate interrelation information between neighboring nodes, which can offer valuable insights for enhancing node embeddings. In this article, we present a knowledge graph embedding based graph convolutional network for link prediction. First, we utilize embeddings to represent entities and relations. Second, we perform circular correlation on subject embedding and relation embedding to generate two matrix and achieve full fusion of embedding at the element level. Third, we generate self-attention vectors using one of the matrices and perform the Hadamard product with the other matrix. Thereafter, new node features are generated through graph convolutional networks and residual unit. Finally, we use the scoring function to score the candidate triples. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-noise Microwave Signal Generation by Heterodyning Two Narrow-linewidth Self-injection Locked Lasers

Low-noise Microwave Signal Generation by Heterodyning Two Na...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

关键词： Linewidth

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Anomize: Better Open Vocabulary Video Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China

Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-CRIME and XD-VIOLENCE datasets, demonstrating its effectiveness in OVVAD. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OmniViD: A Generative Framework for Universal Video Understanding

OmniViD: A Generative Framework for Universal Video Understa...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junke Wang Dongdong Chen Chong Luo Bo He Lu Yuan Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Cloud + AI Microsoft Research Asia University of Maryland College Park

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically de-tect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely on distinct model architectures and annotation formats. In contrast, natural language processing benefits from a unified output space, i.e., text sequences, which simplifies the training of powerful foundational language models, such as GPT-3, with extensive training cor-pora. Inspired by this, we seek to unify the output space of video understanding tasks by using languages as labels and additionally introducing time and box tokens. In this way, a variety of video tasks could be formulated as video-grounded token generation. This enables us to address var-ious types of video tasks, including classification (such as action recognition), captioning (covering clip captioning, video question answering, and dense video captioning), and localization tasks (such as visual object tracking) within a fully shared encoder-decoder architecture, following a generative framework. Through comprehensive experiments, we demonstrate such a simple and straightforward idea is quite effective and can achieve state-of-the-art or compet-itive results on seven video benchmarks, providing a novel perspective for more universal video understanding. Code is available at https://***/wangjk666/OmniVid.

关键词： Training Location awareness Visualization Vocabulary Computer architecture Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation

KERM: Knowledge Enhanced Reasoning for Vision-and-Language N...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiangyang Li Zihan Wang Jiahao Yang Yaowei Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing China University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Vision-and-language navigation (VLN) is the task to enable an embodied agent to navigate to a remote location following the natural language instruction in real scenes. Most of the previous approaches utilize the entire features or object-centric features to represent navigable candidates. However, these representations are not efficient enough for an agent to perform actions to arrive the target location. As knowledge provides crucial information which is complementary to visible content, in this paper, we propose a Knowledge Enhanced Reasoning Model (KERM) to leverage knowledge to improve agent navigation ability. Specifically, we first retrieve facts (i.e., knowledge described by language descriptions) for the navigation views based on local regions from the constructed knowledge base. The re-trieved facts range from properties of a single object (e.g., color, shape) to relationships between objects (e.g., action, spatial position), providing crucial information for VLN. We further present the KERM which contains the purification, fact-aware interaction, and instruction-guided aggregation modules to integrate visual, history, instruction, and fact features. The proposed KERM can automatically select and gather crucial and relevant cues, obtaining more accurate action prediction. Experimental results on the REVERIE, R2R, and SOON datasets demonstrate the effectiveness of the proposed method. The source code is available at https://***/XiangyangLi20/KERM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection

arXiv

引用

arXiv 2023年

作者： Hu, Beizhe Sheng, Qiang Cao, Juan Zhu, Yongchun Wang, Danding Wang, Zhengjia Jin, Zhiwei Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China ZhongKeRuijian Technology Co. Ltd China

Fake news detection has been a critical task for maintaining the health of the online news ecosystem. However, very few existing works consider the temporal shift issue caused by the rapidly-evolving nature of news data in practice, resulting in significant performance degradation when training on past data and testing on future data. In this paper, we observe that the appearances of news events on the same topic may display discernible patterns over time, and posit that such patterns can assist in selecting training instances that could make the model adapt better to future data. Specifically, we design an effective framework FTT (Forecasting Temporal Trends), which could forecast the temporal distribution patterns of news data and then guide the detector to fast adapt to future distribution. Experiments on the real-world temporally split dataset demonstrate the superiority of our proposed framework. The code is available at https://***/ICTMCG/FTTACL23. © 2023, CC BY-NC-SA.

关键词： Forecasting

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：