检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yuan, Li Cai, Yi Ren, Haopeng Wang, Jiexin School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

Generating coherent and credible explanations remains a significant challenge in the field of AI. In recent years, researchers have delved into the utilization of entailment trees to depict explanations, which exhibits a reasoning process of how a hypothesis is deduced from the supporting facts. However, existing models often overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees. To address this limitation, we propose the logical pattern memory pre-trained model (LMPM). LMPM incorporates an external memory structure to learn and store the latent representations of logical patterns, which aids in generating logically consistent conclusions. Furthermore, to mitigate the influence of logically irrelevant domain knowledge in the Wikipedia-based data, we introduce an entity abstraction approach to construct the dataset for pre-training LMPM. The experimental results highlight the effectiveness of our approach in improving the quality of entailment tree generation. By leveraging logical entailment patterns, our model produces more coherent and reasonable conclusions that closely align with the underlying premises. Code and data are released at https://***/YuanLi95/T5-LMPM. © 2024, CC BY-NC-ND.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Spatial-Semantic Collaborative Cropping for User Generated Content

arXiv

引用

arXiv 2024年

作者： Su, Yukun Cao, Yiwen Deng, Jingliang Rao, Fengyun Wu, Qingyao School of Software and Engineering South China University of Technology China WeChat Tencent Inc China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China

A large amount of User Generated Content (UGC) is uploaded to the Internet daily and displayed to people world-widely through the client side (e.g., mobile and PC). This requires the cropping algorithms to produce the aesthetic thumbnail within a specific aspect ratio on different devices. However, existing image cropping works mainly focus on landmark or landscape images, which fail to model the relations among the multi-objects with the complex background in UGC. Besides, previous methods merely consider the aesthetics of the cropped images while ignoring the content integrity, which is crucial for UGC cropping. In this paper, we propose a Spatial-Semantic Collaborative cropping network (S2CNet) for arbitrary user generated content accompanied by a new cropping benchmark. Specifically, we first mine the visual genes of the potential objects. Then, the suggested adaptive attention graph recasts this task as a procedure of information association over visual nodes. The underlying spatial and semantic relations are ultimately centralized to the crop candidate through differentiable message passing, which helps our network efficiently to preserve both the aesthetics and the content integrity. Extensive experiments on the proposed UGCrop5K and other public datasets demonstrate the superiority of our approach over state-of-the-art counterparts. Our project is available at https://***/suyukun666/S2CNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Scene-Text Oriented Referring Expression Comprehension

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2023年 25卷 7208-7221页

作者： Bu, Yuqi Li, Liuwu Xie, Jiayuan Liu, Qiong Cai, Yi Huang, Qingbao Li, Qing South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China Key Lab Big Data & Intelligent Robot SCUT MOE China Guangzhou 510006 Peoples R China Guangxi Univ Inst Artificial Intelligence Sch Elect Engn Nanning 530004 Guangxi Peoples R China Guangxi Key Lab Intelligent Control & Maintenance Nanning 530004 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China

Referring expression comprehension (REC) aims to identify and locate a specific object in visual scenes referred to by a natural language expression. Existing studies of REC only focus on basic visual attributes and neglect scene text. Since scene text has the functions of object identification and disambiguation, it is naturally and frequently used to refer to objects. However, existing methods do not explicitly recognize text in images and fail to align scene text mentioned in expressions with the text shown in images, resulting in object localization errors. This article takes the first step toward addressing these limitations. First, we introduce a new task called scene-text oriented referring expression comprehension, which aims to align visual cues and textual semantics of scene text with referring expressions and visual contents. Second, we propose a scene text awareness network that can bridge the gap between texts from two modalities by grounding visual representations of expression-correlated scene texts. Specifically, we propose a correlated text extraction module to solve the problem of lacking semantic understanding, and a correlated region activation module to address the fixed alignment problem and absent alignment problem. These modules ensure that the proposed method focuses on local regions that are most relevant to scene text, thus mitigating the misalignment of scene text with irrelevant regions. Third, to conduct quantitative evaluations, we establish a new benchmark dataset called RefText. Experimental results demonstrate that the proposed method can effectively comprehend scene-text oriented referring expressions and achieves excellent performance.

关键词： Visualization Task analysis Semantics Text recognition Pain Natural languages Image recognition Referring expression comprehension scene text representation multimodal alignment

来源：评论

学校读者我要写书评

暂无评论

Travel Characteristics and Combination Choice Behavior Modeling of Passengers under the Influence of Epidemic Prevention Policies 24

Travel Characteristics and Combination Choice Behavior Model...

引用

24th COTA International Conference of Transportation Professionals: Resilient, intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Zhang, Yue Dong, Chunjiao Li, Penghui Dong, Qianru Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport School of Traffic and Transportation Beijing Jiaotong Univ. Beijing China State Key Laboratory of Intelligent Vehicle Safety Technology China Automotive Engineering Research Institute Co. Ltd. Chongqing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

The intermodal travel characteristics and combination selection behaviors of passengers are key issues to providing reasonable, efficient, and safe solutions, ensuring the traffic order, and improving quality. With the Beijing Winter Olympics as a background, by combining the Stated Preference and Revealed Preference surveys, the research develops a decision-making behavior model based on nested logit to investigate the passenger travel choices. The impacts of individual attributes, epidemic prevention policies, and preferential measures on the choice of intermodal travel, as well as the combination of departure time and travel mode, are studied. The results show that cultural and creative products have a significant impact on the combined travel choices. The cultural and creative products and consumer vouchers have a significant impact on the choice of intermodal travel. The research results can provide insights into traffic organization and management policies during large-scale events. © ASCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhance Weakly-Supervised Aspect Detection with External Knowledge (Student Abstract) 36

Enhance Weakly-Supervised Aspect Detection with External Kno...

引用

36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Zheng, Zhuoming Cai, Yi Li, Liuwu South China Univ Technol Sch Software & Engn Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Guangzhou Peoples R China

ISBN: (纸本)9781577358763

Aspect detection aims to identify aspects of reviews and is an essential up-stream task of opinion mining and so on. However, existing weakly-supervised methods suffer from lacking the ability of identifying implicit aspects with infrequent aspect terms and "Misc" aspects. To tackle these problems, we propose to enhance the representation of segment with external knowledge by a weakly-supervised method. Experiments demonstrate the effectiveness of our model and the improvement by incorporating external knowledge.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Multimodal image feature fusion for improving medical ultrasound image segmentation

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 89卷

作者： Chen, Jiashuo Chen, Junying South China Univ Technol Sch Software Engn Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Guangzhou Peoples R China

Ultrasound imaging is the most commonly used technique to detect abnormalities of the thyroid and diagnose abnormal breasts. However, due to the inherent characteristics of ultrasound imaging, the contrast of ultrasound images is relatively low, and the tissue boundaries in the image are blurry. This makes it a challenging task to segment thyroid or breast lesions from ultrasound images. In this work, we explore the role of multimodal features at different levels of deep neural network models and their fusion mechanisms for multimodal images generated by ultrasound radio frequency (RF) data. The ultrasound RF data contain information related to the arrangement of scatterers in tissues and organs, which is only partially available in B-mode images. To solve this problem, we use ultrasound RF data to generate parametric images, including Nakagami and entropy images, to illustrate the abundant backscattered statistics contained in RF data. A channel-aware fusion module is proposed to adaptively fuse the features from images of different modalities. Experimental results show that the abundant information contained in RF data can be helpful to identify thyroid glands or breast lesions with low contrast and fuzzy boundaries in B-mode ultrasound images and improve the segmentation performance.

关键词： Medical ultrasound image segmentation Ultrasound parametric imaging Multimodal fusion Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Vision Guided Mobile robot Dual Axis PID Dynamic Real Time Adjustment Following 5

Deep Vision Guided Mobile Robot Dual Axis PID Dynamic Real T...

引用

5th World robot Conference Symposium on Advanced robotics and Automation, WRC SARA 2023

作者： Li, Yang Yang, Guanci He, Ling Zhao, Le Zhao, Tianyi Sun, Haoran Guizhou University Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou Guiyang550025 China Guizhou University Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education State Key Laboratory of Public Big Data Guizhou Provincial Key Laboratory of Internet+' Collaborative Intelligent Manufacturing Guizhou Guiyang550025 China

ISBN: (纸本)9798350307320

The real-time tracking of moving objects by social robots is crucial for ensuring object-oriented services. This paper presents a real-time following algorithm for mobile robots based on deep vision object detection. Firstly, using a binocular depth vision camera, real-time target information from a firstperson perspective is collected, and a lightweight deep learning model is employed to detect the relative position of the human body posture with respect to the social robot. Subsequently, to address the issue of unsmooth trajectory during the tracking process, a dual-axis PID algorithm is developed for cooperative control of the robot's speed and heading angle. Given the inherent randomness in human body movement, target loss can occur during tracking. To enhance the algorithm's robustness, a dynamic tracking mechanism is introduced. Finally, we implement a vision-driven two-wheel differential social robot following algorithm on the ROS system and validate it through three real-world experimental scenarios. The mean values of the target acquisition rate, tracked target position, and angle smoothness are found to be 0.81, 0.46, and 1.02, respectively. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Plasmonic rhenium trioxide self-assembled microtubes for highly sensitive, stable and reproducible surface-enhanced Raman spectroscopy detection

引用

Chinese Chemical Letters 2023年第3期34卷 218-221页

作者： Jingbin Li Zhiwei Jiao Junfang Li Hua Bai Guangcheng Xi College of Sciences China Jiliang UniversityHangzhou 310018China Institute of Industrial and Consumer Product Safety Chinese Academy of Inspection and QuarantineBeijing 100176China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang UniversityHangzhou 310018China

Compared with noble metals, improving the sensitivity of semiconducting surface-enhanced Raman scattering(SERS) substrates is of great significance to their fundamental research and practical application of Raman spectroscopy. Herein, a simple chemical method is developed to synthesize a rhenium trioxide(ReO_(3)) microtubes assembled with highly crystalline nanoparticles. The ReO_(3) microtubes show a strong and well-defined surface plasmon resonance(SPR) behavior in visible region, which is rare for non-noble metals. As a low-cost SERS substrate, the plasmonic ReO_(3) microtubes exhibit a Raman enhancement factor of 8.9×10^(5) and a lowest detection limit of 1.0×10^(-9) mol/L for phenolic pollutants. Moreover, these ReO_(3) microtubule SERS substrates show excellent chemical stability and can resist the corrosion of strong acids and bases.

关键词： SERS ReO_(3) Surface plasmon resonance Microtubes Self assembly

来源：评论

学校读者我要写书评

暂无评论

Cross Dense Feature Learning With Task Guidance for Few-Shot Classification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第4期35卷 3438-3449页

作者： Zhang, Qi Chen, Long Shang, Wanfeng Univ Macau Dept Comp & Informat Sci Macau Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen 518055 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China

Few-shot classification aims to develop a classifier that adapts to new tasks using only a limited number of labeled images. To overcome the limitation of lacking training images in few-shot image classification, dense features have been extensively utilized to represent images by providing more subtle and discriminative clues. However, dense feature based methods are still facing challenges despite leveraging local details in images. Primarily, these methods deal with the support set images in each category independently, which ignores the information across different categories. Furthermore, dense features suffer from background noise, when performing similarity calculations based on a large number of dense feature pairs, these methods are susceptible to interference from task-irrelevant feature pairs. In this paper, we propose a cross dense feature learning with task guidance method to address the aforementioned issues. The key components of our method include two aspects. Firstly, a dense feature extraction approach based on transformer is proposed, aiming to better utilize inter-class information within the support set. We design two types of cross-attention mechanisms to get the across information among different categories for a better representation of dense features, named Support-Support Attention (SSA) and Support-Query Attention (SQA). Secondly, a task-relevant model is trained for dense feature pairs similarity calculating, aiming to filter out feature pairs that contribute more effectively to classification. Then we can get the final similarity to predict the label of query image through summarizing weighted local similarity. The experimental results prove that our method achieves a promising improvement for few-shot classification by taking information across different categories and task attention similarity into consideration.

关键词： Feature extraction Transformers Prototypes Measurement Background noise Image reconstruction Few shot learning Training Representation learning Image representation Few-shot classification dense features transformer

来源：评论

学校读者我要写书评

暂无评论

Power Optimization for Low Transmission Delay in Software Defined data Center Networks

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5716-5730页

作者： Zhao, Yong Cao, Jiannong Wang, Xingwei Li, Fuliang He, Qiang Liu, Xiaojie University of Electronic Science and Technology of China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Laboratory of Intelligent Collaborative Computing Chengdu611731 China Hong Kong Polytechnic University Department of Computing Hung Hom Hong Kong Northeastern University College of Computer Science and Engineering Shenyang110819 China Northeastern University College of Medicine and Biological Information Engineering Shenyang110819 China Pengcheng Laboratory Shenzhen518066 China

Software-Defined data Center Networks (SDDCNs) utilizes Software Defined Networking (SDN) as a network architecture to achieve highly flexible, programmable, and automated management of data Center Networks (DCNs). The high energy consumption of DCNs remains a persistent and significant challenge. Thus, the energy saving is crucial and imperative for DCNs. Current energy-efficient solutions primarily rely on flow consolidation and dynamic device sleeping techniques to reduce energy consumption. However, these approaches often yield long Flow Completion Time (FCT), potentially resulting in violations of service-level agreements, particularly for delay-sensitive applications. In this paper, we formulate the problem of minimizing the power consumption in SDDCNs as key objective while ensuring timely FCT for delay-sensitive applications. To solve this problem, we first introduce the Active Network Generation (ANG) approach, which generates a minimal active subnet with the least number of active devices while meeting the current traffic demand. Subsequently, we propose two algorithms based on the type of applications: the Delay-Tolerant Flow Route (DTFR) algorithm for delay-tolerant applications and the Delay-Sensitive Flow Route (DSFR) algorithm for delay-sensitive applications. Simulation results demonstrate that our propose solution achieves an energy-saving rate of up to 67.77% and significantly reduces FCT compared to benchmark solutions. © 2002-2012 IEEE.

关键词： Energy efficiency

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：