检索结果-内蒙古大学图书馆

NID-SLAM: Neural Implicit Representation-based RGB-D SLAM In Dynamic Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Ziheng Niu, Jianwei Li, Qingfeng Ren, Tao Chen, Chen School of Computer Science Beihang University Beijing China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China Big Data and Industrial Intelligent Networking Laboratory Hangzhou Innovation Institute of Beihang University Hangzhou China

Neural implicit representations have been explored to enhance visual SLAM algorithms, especially in providing high-fidelity dense map. Existing methods operate robustly in static scenes but struggle with the disruption caused by moving objects. In this paper we present NID-SLAM, which significantly improves the performance of neural SLAM in dynamic environments. We propose a new approach to enhance inaccurate regions in semantic masks, particularly in marginal areas. Utilizing the geometric information present in depth images, this method enables accurate removal of dynamic objects, thereby reducing the probability of camera drift. Additionally, we introduce a keyframe selection strategy for dynamic scenes, which enhances camera tracking robustness against large-scale objects and improves the efficiency of mapping. Experiments on publicly available RGB-D datasets demonstrate that our method outperforms competitive neural SLAM approaches in tracking accuracy and mapping quality in dynamic environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

NID-SLAM: Neural Implicit Representation-based RGB-D SLAM In Dynamic Environments

学校读者我要写书评

暂无评论

NID-SLAM: Neural Implicit Representation-based RGB-D SLAM In...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ziheng Xu Jianwei Niu Qingfeng Li Tao Ren Chen Chen School of Computer Science Beihang University Beijing China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China Big Data and Industrial Intelligent Networking Laboratory Hangzhou Innovation Institute of Beihang University Hangzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

关键词： Visualization Image segmentation Simultaneous localization and mapping Accuracy Navigation Semantics robot vision systems

Research on Waxiang Dialect Recognition Based on Wav2vec2.0 Pre-Training and Transfer Learning

学校读者我要写书评

暂无评论

Research on Waxiang Dialect Recognition Based on Wav2vec2.0 ...

Computing, robotics and System Sciences (ICRSS), International Conference on

作者： Mixuan Deng Pengju Tang Yanxia Gao Huixuan Li Guodong Zhen Kaifeng Fu Xiaotian Wu College of Computer and Artificial Intelligence(Software College) Huaihua University Huaihua China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua China

ISBN: (数字)9798331511296

ISBN: (纸本)9798331511302

As a unique local dialect, Waxiang dialect carries rich regional culture and historical information. However, with the acceleration of modernization and the increase of population mobility, the inheritance and protection of Waxiang dialect are facing severe challenges. By constructing the ‘Xuewatong’ APP- Waxiang dialect digital protection platform, based on cloud storage technology, digital resource display, multimedia integration and other technologies, and providing learning resources through big data analysis of user needs, it can effectively promote the digital recording and preservation of Waxiang dialect language resources, and significantly improve the dissemination and educational effect of Waxiang dialect culture, showing the great potential of digital technology in dialect protection.

关键词： Technological innovation Cloud computing Transfer learning Media Information age Digital recording Global communication Cultural differences Protection robots

LogADCH: Hyperspheric-Based Log Message Anomaly Detection And Classification

学校读者我要写书评

暂无评论

LogADCH: Hyperspheric-Based Log Message Anomaly Detection An...

Frontiers of robotics and Software Engineering (FRSE), International Conference on

作者： Shiming He Jinpan Xiao Bowen Chen Ying Lei School of Computer and Communication Engineering the Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science & Technology Changsha China

Web services have been integrated with all walks of life in society. Abnormalities in the network and services seriously affect user experience and company revenue. The system log records various information of the system, and the information-rich log messages usually show different anomalies. It is particularly important to accurately and timely identify the anomalies of the log messages and classify the anomalies. In addition, most of the current existing work only detects anomalies and does not classify them, and a few existing works require anomaly labels to classify anomalies. Based on these potential challenges, we propose an unsupervised hypersphere-based log message anomaly detection and classification method, LogADCH. We use the hypersphere loss function to let the BERT model learn compact representations of log messages and perform anomaly detection. Finally, K-Means clustering is performed on the semantic feature vectors detected as anomalies to form clusters of different types of anomalies. Compared with other works, LogADCH further classifies the abnormal types after detecting the abnormal logs, helping the operation and maintenance personnel to quickly locate the fault. We compare our method with other methods on two public datasets, and the experimental results show that LogADCH has superior performance in anomaly detection as well as anomaly classification.

关键词：

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ou, Yixin Yao, Yunzhi Zhang, Ningyu Jin, Hui Sun, Jiacheng Deng, Shumin Li, Zhenguo Chen, Huajun Zhejiang University China Huawei Noah’s Ark Lab Canada National University of Singapore NUS-NCS Joint Lab Singapore Zhejiang Key Laboratory of Big Data Intelligent Computing China

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural computations. We address this issue through the lens of knowledge circuit evolution, identifying computational subgraphs that facilitate knowledge storage and processing. Our systematic analysis of circuit evolution throughout continual pre-training reveals several key findings: (1) the acquisition of new knowledge is influenced by its relevance to preexisting knowledge;(2) the evolution of knowledge circuits exhibits a distinct phase shift from formation to optimization;(3) the evolution of knowledge circuits follows a deep-to-shallow pattern. These insights not only advance our theoretical understanding of the mechanisms of new knowledge acquisition in LLMs, but also provide potential implications for improving continual pre-training strategies to enhance model performance Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge acquisition

Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xia, Shuyin Ma, Xinjun Liu, Zhiyuan Liu, Cheng Zhao, Sen Wang, Guoyin Key Laboratory of Big Data Intelligent Computing China Chongqing Key Laboratory of Computational Intelligence China Chongqing University of Posts and Telecommunications Chongqing China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing401331 China

Graph Neural Networks (GNNs) have demonstrated significant achievements in processing graph data, yet scalability remains a substantial challenge. To address this, numerous graph coarsening methods have been developed. However, most existing coarsening methods are training-dependent, leading to lower efficiency, and they all require a predefined coarsening rate, lacking an adaptive approach. In this paper, we employ granular-ball computing to effectively compress graph data. We construct a coarsened graph network by iteratively splitting the graph into granular-balls based on a purity threshold and using these granular-balls as super vertices. This granulation process significantly reduces the size of the original graph, thereby greatly enhancing the training efficiency and scalability of GNNs. Additionally, our algorithm can adaptively perform splitting without requiring a predefined coarsening rate. Experimental results demonstrate that our method achieves accuracy comparable to training on the original graph. Noise injection experiments further indicate that our method exhibits robust performance. Moreover, our approach can reduce the graph size by up to 20 times without compromising test accuracy, substantially enhancing the scalability of GNNs. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

学校读者我要写书评

暂无评论

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 8559-8572页

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Shenzhen Univ Comp Vis Inst Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Great Bay Univ Sch Comp & Informat Technol Dongguan 523000 Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Shenzhen Univ Comp Vis Inst Coll Comp Sci & Software Engn Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen 518129 Peoples R China Qilu Univ Technol Shandong Artificial Intelligence Inst Shandong Acad Sci Jinan 250014 Peoples R China Tianjin Univ Technol Key Lab Comp Vis & Syst Minist Educ Tianjin 300384 Peoples R China Univ Nottingham Ningbo China UNNC Sch Comp Sci Ningbo Peoples R China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace.

关键词： Forgery Faces Deepfakes Image edge detection Feature extraction Transformers Generators Face forgery benchmark transformer deepfake detection appearance-edge fusion

SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhong, Xiaojing Huang, Xinyi Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China SenseTime Research China

Makeup transfer is a process of transferring the makeup style from a reference image to the source image, while preserving the source image’s identity. In addition to achieving fine-grained control over the makeup transfer, incorporating semantic alignment into the transformation is crucial, as the poses of the reference and source images are often inconsistent. We propose a novel Semantic-guided Alignment and Region-Adaptive normalization framework (SARA) to effectively transfer makeup styles under misaligned poses, offering flexible control to meet the demands of real-world applications, such as partial transfer, intensity adjustment, and makeup removal. Specifically, SARA comprises three modules: Firstly, we propose a semantic-guided alignment module to explicitly construct dense correspondence between the reference image and the target semantic map, employing unbalanced optimal transport matching to handle semantic region mismatches. Secondly, a region-adaptive normalization module is responsible for dynamically combining the warped style features with shape-independent style codes obtained by region-wise average pooling, mitigating feature loss during the alignment. Lastly, a makeup fusion module progressively fuses the identity features with the makeup styles to render the final output image. Furthermore, we combine optimal transport with histogram matching to generate the pseudo ground truth, which is used to facilitate the transfer in terms of both spatial alignment and color distribution. Experimental results show that our proposed SARA outperforms existing methods on two public datasets. © 2023, CC BY.

关键词： Semantics

Wideband High-Selectivity SIW Filtering Antenna with Controllable Radiation Nulls

学校读者我要写书评

暂无评论

Journal of Microwaves, Optoelectronics and Electromagnetic Applications 2024年第1期23卷

作者： Wang, Zhongbao Liu, Xinhong Liu, Hongmei Fang, Shaojun Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Liaoning Technical University Liaoning Huludao125105 China School of Information Science and Technology Dalian Maritime University Liaoning116026 Dalian China

—A novel wideband high-selectivity substrate-integrated-waveguide (SIW) filtering antenna with controllable radiation nulls is proposed. This antenna is composed of a two-layered SIW resonator, two radiating slots on the top layer, and two coupling slots on the middle layer. A vertical SMA connector is located at the bottom and feeds two SIW cavities simultaneously. By adjusting the parameters of these slots, three radiation nulls will be achieved, and two radiation nulls can be easily controlled. For demonstration, one prototype of the filtering antenna is fabricated and measured. Measurement results show that the fractional bandwidth for |S11| © 2024 SBMO/SBMag.

关键词： Substrate integrated waveguides