检索结果-内蒙古大学图书馆

SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Chen Zhao, Liangjin He, Yuanchun Long, Yingxuan Chen, Kaiqiang Wang, Zhirui Hu, Yanfeng Sun, Xian Key Laboratory of Target Cognition and Application Technology Aerospace Information Research Institute Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Semantic segmentation and 3D reconstruction are two fundamental tasks in remote sensing, typically treated as separate or loosely coupled tasks. Despite attempts to integrate them into a unified network, the constraints between the two heterogeneous tasks are not explicitly modeled, since the pioneering studies either utilize a loosely coupled parallel structure or engage in only implicit interactions, failing to capture the inherent connections. In this work, we explore the connections between the two tasks and propose a new network that imposes semantic constraints on the stereo matching task, both implicitly and explicitly. Implicitly, we transform the traditional parallel structure to a new cascade structure termed Semantic-Guided Cascade structure, where the deep features enriched with semantic information are utilized for the computation of initial disparity maps, enhancing semantic guidance. Explicitly, we propose a Semantic Selective Refinement (SSR) module and a Left-Right Semantic Consistency (LRSC) module. The SSR refines the initial disparity map under the guidance of the semantic map. The LRSC ensures semantic consistency between two views via reducing the semantic divergence after transforming the semantic map from one view to the other using the disparity map. Experiments on the US3D and WHU datasets demonstrate that our method achieves state-of-the-art performance for both semantic segmentation and stereo matching. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation 10th

学校读者我要写书评

暂无评论

Exploiting Explicit and Inferred Implicit Personas for Multi...

10th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2021

作者： Wang, Ruifang He, Ruifang Wang, Longbiao Si, Yuke Liu, Huanyu Wang, Haocheng Dang, Jianwu State Key Laboratory of Communication Content Cognition People’s Daily Online Beijing China Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Japan Advanced Institute of Science and Technology Ishikawa Japan

ISBN: (纸本)9783030884796

Learning and utilizing personas in open-domain dialogue have become a hotspot in recent years. The existing methods that only use predefined explicit personas enhance the personality to some extent, however, they cannot easily avoid persona inconsistency and weak diversity responses. To address these problems, this paper proposes an effective model called Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation (EIPD). Specifically, 1) an explicit persona extractor is designed to improve persona consistency;2) Taking advantage of the von Mises-Fisher (vMF) distribution in modeling directional data (e.g., the different persona state), we introduce the implicit persona inference to increase diversity;3) during the generation, the persona response generator fuses the explicit and implicit personas in the response. The experimental results on the ConvAI2 persona-chat dataset demonstrate that our model performs better than commonly used baselines. Further analysis of the ablation experiments shows that EIPD can generate more persona-consistent and diverse responses. © 2021, Springer Nature Switzerland AG.

关键词： Computers

Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Yanan Xie, Ying Chang, Ying Zhang, Benkui Jia, Bo Cao, Lin Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing China Key Laboratory of Target Cognition and Application Technology Aerospace Information Research Institute Beijing China

Novel view synthesis has made significant progress in the field of 3D computer vision. However, the rendering of view-consistent novel views from imperfect camera poses remains challenging. In this paper, we introduce a hybrid bundle-adjusting 3D Gaussians model that enables view-consistent rendering with pose optimization. This model jointly extract image-based and neural 3D representations to simultaneously generate view-consistent images and camera poses within forward-facing scenes. The effective of our model is demonstrated through extensive experiments conducted on both real and synthetic datasets. These experiments clearly illustrate that our model can effectively optimize neural scene representations while simultaneously resolving significant camera pose misalignments. The source code is available at https://***/Bistu3DV/hybridBA. Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

Acute Observational Stimulus of Restrained Mice Induced Anxiolytic Effects in Observer Mice

学校读者我要写书评

暂无评论

Neuroscience Bulletin 2024年第10期40卷 1545-1550页

作者： Chun-Hui Jia Fang-Qi Shu Pak-Ming Lau Hao Wang CAS Key Laboratory of Brain Function and Disease Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230026China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial IntelligenceHefei Comprehensive National Science CenterHefei 230088China Interdisciplinary Center for Brain Information The Brain Cognition and Brain Disease InstituteShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application School of Information Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China

Dear Editor,Ensuring an appropriate response to external stimuli is essential for animals'survival and *** indicates that such stimuli can affect animals'physiological state and hormone levels,including corticosterone(CORT)[1,2].The impact of these stimuli on animals'performance depends on their density and duration,as they can either facilitate or hinder *** chronic and intense stressors can have detrimental effects on animals'physiological health and behavioral performance,leading to psychiatric disorders such as depression,anxiety,and schizophrenia[3],the effects of acute and mild observational stimuli are still unclear.

关键词： evolution. Observation acute

SFD-YOLO: A novel framework for subsidence funnels detection in China based on large-scale SAR interferograms

学校读者我要写书评

暂无评论

International Journal of Applied Earth Observation and Geoinformation 2025年 140卷

作者： Jing Guo Zhengjia Zhang Peifeng Ma Mengmeng Wang Xuefei Zhang Dongdong Li Bing Sui School of Geography and Information Engineering China University of Geosciences 388 Lumo Road Wuhan 430074 China Department of Geography and Resource Management The Chinese University of Hong Kong Shatin Hong Kong Institute of Space and Earth Information Science The Chinese University of Hong Kong Shatin Hong Kong Shenzhen Research Institute The Chinese University of Hong Kong Shenzhen 518063 China Land Satellite Remote Sensing Application Center MNR Beijing China National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha China Hunan Key Laboratory of Meteorological Disaster Prevention and Reduction Changsha China

Accurate identification of subsidence funnels is essential for assessing surface deformation in mining areas, preventing disasters, and optimizing resource management. However, recognizing subsidence funnels of varying sizes in large-scale interferograms poses significant challenges, particularly for small-sized funnels. Their indistinct features and susceptibility to background noise interference often result in suboptimal detection accuracy. To address these challenges, this study proposes a deep learning network based on the YOLO architecture—SFD-YOLO (Sinking Funnel Detection-YOLO). The model incorporates the DWR-C2f module, which enhances multi-scale feature extraction and significantly improves the detection of small-sized subsidence funnels. Additionally, the innovative Inner-WIoU regression loss function improves the localization accuracy of detection boxes while also alleviates the imbalance between hard and easy samples. Experimental results demonstrate that the fully trained SFD-YOLO model achieves an mAP50 accuracy of 92.00% while maintaining high efficiency, significantly outperforming other advanced methods. Applying the SFD-YOLO model to interferograms across China detected a total of 3,842 subsidence funnels, with Shanxi, Inner Mongolia, Shaanxi, and Anhui identified as the four provinces with the highest funnel number. Overall, subsidence funnels are predominantly distributed in northern and northwestern China. Further analysis and experimental evaluation reveal that the SFD-YOLO model exhibits strong generalization capabilities across complex surface environments nationwide and multi-source satellite data.

关键词： Mining subsidence detection National scale Interferograms Deep learning Small-sized funnels

UNetMamba: An Efficient UNet-Like Mamba for Semantic Segmentation of High-Resolution Remote Sensing Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Enze Chen, Zhan Wang, Dingkai Shi, Hanru Liu, Xiaoxuan Wang, Lei Beijing100094 China Key Laboratory of Target Cognition and Application Technology CAS Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Semantic segmentation of high-resolution remote sensing images is vital in downstream applications such as land-cover mapping, urban planning and disaster assessment. Existing Transformer-based methods suffer from the constraint between accuracy and efficiency, while the recently proposed Mamba is renowned for being efficient. Therefore, to overcome the dilemma, we propose UNetMamba, a UNet-like semantic segmentation model based on Mamba. It incorporates a mamba segmentation decoder (MSD) that can efficiently decode the complex information within high-resolution images, and a local supervision module (LSM), which is train-only but can significantly enhance the perception of local contents. Extensive experiments demonstrate that UNetMamba outperforms the state-of-the-art methods with mIoU increased by 0.87% on LoveDA and 0.39% on ISPRS Vaihingen, while achieving high efficiency through the lightweight design, less memory footprint and reduced computational cost. The source code is available at https://***/EnzeZhu2001/UNetMamba. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Brain Systems Underlying Fundamental Motivations of Human Social Conformity

学校读者我要写书评

暂无评论

Neuroscience Bulletin 2023年第2期39卷 328-342页

作者： Xinling Chen Jiaxi Liu Yue-Jia Luo Chunliang Feng Key Laboratory of Brain Cognition and Education Sciences(South China Normal University)Ministry of EducationGuangzhou 510631China School of Psychology South China Normal UniversityGuangzhou 510631China Center for Studies of Psychological Application South China Normal UniversityGuangzhou 510631China Guangdong Key Laboratory of Mental Health and Cognitive Science South China Normal UniversityGuangzhou 510631China Department of Applied Psychology University of Health and Rehabilitation SciencesQingdao 266113China The State Key Lab of Cognitive and Learning Faculty of PsychologyBeijing Normal UniversityBeijing 100875China The Research Center of Brain Science and Visual Cognition Kunming University of Science and TechnologyKunming 650506China College of Teacher Education Qilu Normal UniversityJinan 250200China

From birth to adulthood,we often align our behaviors,attitudes,and opinions with a majority,a phenomenon known as social conformity.A seminal framework has proposed that conformity behaviors are mainly driven by three fundamental motives:a desire to gain more information to be accurate,to obtain social approval from others,and to maintain a favorable *** extensive interest in neuroimaging investigation of social conformity,the relationship between brain systems and these fundamental motivations has yet to be ***,we reviewed brain imaging findings of social conformity with a componential framework,aiming to reveal the neuropsychological substrates underlying different conformity ***,information-seeking engages the evaluation of social information,information integration,and modification of task-related activity,corresponding to brain networks implicated in reward,cognitive control,and tasks at ***,social acceptance involves the anticipation of social acceptance or rejection and mental state attribution,mediated by networks of reward,punishment,and ***,self-enhancement entails the excessive representation of positive self-related information and suppression of negative self-related information,ingroup favoritism and/or outgroup derogation,and elaborated mentalizing processes to the ingroup,supported by brain systems of reward,punishment,and ***,recent brain imaging studies have provided important insights into the fundamental motivations of social conformity in terms of component processes and brain mechanisms.

关键词： Social conformity Motivation Information seeking Social acceptance Positive self-concept Brain mechanisms

Research on the multidimensional educational review strategy Based on MOOCs Integrated by the multidimensional learning theory

学校读者我要写书评

暂无评论

Research on the multidimensional educational review strategy...

2015 World Congress on Engineering and Computer Science, WCECS 2015

作者： Ming, Li Ju, Zhang Jingzhong, Zhang Lian, Chen High Performance Computing Application R and D Center Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Automated Reasoning and Cognition Key Laboratory of Chongqing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Laboratory for Automated Reasoning and Programming Chengdu Institute of Computer Applications Chinese Academy of Sciences Chengdu China

ISBN: (纸本)9789881925367

Through a detailed analysis of the theoretical basis for MOOCs in terms of educational learning theories, this paper attempts at finding the corresponding relationship between the theories and MOOCs, which not only theoretically explains the reasons why MOOCs exceed all the previous education models, but also empirically proves it with voluminous facts and data. The author conducts this research in the hope of enlightening the online education platform of other types. Besides, this paper provides the model framework and strategy to multidimensional educational review based on MOOCs. The model and strategy are applicable not only to MOOCs, the large-scale online education, but also to various online education platforms.

关键词： E-learning

Rethinking the key Factors for the Generalization of Remote Sensing Stereo Matching Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Liting Wang, Feng Zhang, Wenyi Li, Peifeng You, Hongjian Xiang, Yuming Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Stereo matching, a critical step of 3D reconstruction, has fully shifted towards deep learning due to its strong feature representation of remote sensing images. However, ground truth for stereo matching task relies on expensive airborne LiDAR data, thus making it difficult to obtain enough samples for supervised learning. To improve the generalization ability of stereo matching networks on cross-domain data from different sensors and scenarios, in this paper, we dedicate to study key training factors from three perspectives. (1) For the selection of training dataset, it is important to select data with similar regional target distribution as the test set instead of utilizing data from the same sensor. (2) For model structure, cascaded structure that flexibly adapts to different sizes of features is preferred. (3) For training manner, unsupervised methods generalize better than supervised methods, and we design an unsupervised early-stop strategy to help retain the best model with pre-trained weights as the basis. Extensive experiments are conducted to support the previous findings, on the basis of which we present an unsupervised stereo matching network with good generalization performance. We release the source code and the datasets at https://***/Elenairene/RKF_RSSM to reproduce the results and encourage future work. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning