检索结果-内蒙古大学图书馆

International Conference on Image, Vision and intelligent Systems, ICIVIS 2023

作者： Wang, Kangyi Han, Tianhao Dong, Jiwen Fu, Hanghang Niu, Sijie School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China Shandong Hongye Information Technology Co. Ltd. Jinan250013 China

ISBN: (纸本)9789819708543

Change detection (CD) is used to identify the required significant changes between two-phase images. High-resolution remote sensing image CD plays an important role in land and resources planning, military strategy research, geological exploration research, natural disaster prediction and other fields. Given two identical registration photographs taken at various times, lighting or seasonal changes are frequently present, as well as other issues such significant changes in the image of the real thing. Despite these issues, the real object's small size and its boundary changes are still a concern. Therefore, we propose a Siam network based on UNet to solve some subtle problems in CD for edge information and small object detection. The original convolutional module in our UNet network is improved into an optimization module in the form of jumper connections, a pyramidal pool module is added at the bottom of the encoder to better extract global information, and these changes together create an improved ASPCD-UNet network model. The model training is based on cross-entropy loss function, with a variety of optimization strategies to achieve end-to-end ground object change information extraction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Global Mean Square Error Separation Loss 4

Global Mean Square Error Separation Loss

引用

2022 4th International Conference on Artificial Intelligence and Computer Science, AICS 2022

作者： Hou, Yun Key Laboratory of Agile Intelligent Computing Southwest China Institute of Electronic Technology Sichuan Chengdu China

Class imbalance problem greatly affects the accuracy of deep-learning-based object detectors. To weaken its influence, this paper proposes a global mean square error separation loss (GMSES Loss). GMSES Loss assigns a factor to each example, and then enhances the learning of hard-to-learn examples by reducing the factors of easy-to-learn examples. Meanwhile, the global mean square error separation method is introduced to enhance the learning of foreground classes. To verify the effectiveness of our algorithm, experiments are conducted with YOLOv4 and RetinaNet as the baselines, respectively. The results have shown that our loss function can improve the performance of one-stage object detectors without adding any extra hyperparameters. © 2022 institute of Physics Publishing. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Imagine Before Go: Self-Supervised Generative Map for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinyao Yu Xinhang Song Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The Object Goal navigation (ObjectNav) task requires the agent to navigate to a specified target in an unseen environment. Since the environment layout is unknown, the agent needs to infer the unknown contextual objects from partially observations, thereby deducing the likely location of the target. Previous end-to-end RL methods capture contextual relationships through implicit representations while they lack notion of geometry. Alternatively, modular methods construct local maps for recording the observed geometric structure of unseen environment, however, lacking the reasoning of contextual relation limits the exploration efficiency. In this work, we propose the self-supervised generative map (SGM), a modular method that learns the explicit context relation via self-supervised learning. The SGM is trained to leverage both episodic observations and general knowledge to reconstruct the masked pixels of a cropped global map. During navigation, the agent maintains an incomplete local semantic map, meanwhile, the unknown regions of the local map are generated by the pretrained SGM. Based on the generated map, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson, MP3D and HM3D show the effectiveness of our method. The code is available at https://***/sx-zhang/SGM.

关键词： Training Geometry Navigation Large language models Semantics Layout Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Video Summarization Using Denoising Diffusion Probabilistic Model 39

Video Summarization Using Denoising Diffusion Probabilistic ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Shang, Zirui Zhu, Yubo Li, Hongxi Yang, Shuo Wu, Xinxiao Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

ISBN: (纸本)157735897X

Video summarization aims to eliminate visual redundancy while retaining key parts of video to construct concise and comprehensive synopses. Most existing methods use discriminative models to predict the importance scores of video frames. However, these methods are susceptible to annotation inconsistency caused by the inherent subjectivity of different annotators when annotating the same video. In this paper, we introduce a generative framework for video summarization that learns how to generate summaries from a probability distribution perspective, effectively reducing the interference of subjective annotation noise. Specifically, we propose a novel diffusion summarization method based on the Denoising Diffusion Probabilistic Model (DDPM), which learns the probability distribution of training data through noise prediction, and generates summaries by iterative denoising. Our method is more resistant to subjective annotation noise, and is less prone to overfitting the training data than discriminative methods, with strong generalization ability. Moreover, to facilitate training DDPM with limited data, we employ an unsupervised video summarization model to implement the earlier denoising process. Extensive experiments on various datasets (TVSum, SumMe, and FPVSum) demonstrate the effectiveness of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Enhanced Dcf Tracker Regularized by Reliable Sample Construction 48

Enhanced Dcf Tracker Regularized by Reliable Sample Construc...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Hu, Kun Cao, Mingyu Wang, Mengzhu Lan, Long Yang, Wenjing Tan, Huibin Institute for Quantum Information State Key Laboratory of High Performance Computing China National University of Defense Technology College of Computer Science and Technology Changsha China

ISBN: (纸本)9781728163277

Discriminative correlation filter (DCF) is a highly efficient tracking technique using the circulant shifted samples of search images to update the template, so the reliability of input samples determines template quality. In this paper, we rethink the reliability problem of input samples in advance during template updating and propose an enhanced DCF tracking method regularized by a novel sparse representation based reliable sample construction term, called enhanced sparse correlation filter (ESCF). Specifically, the reconstructed reliable samples are the sparse representation of circulant shifted samples of unfiltered input samples, in which the target will approach the center to preserve target visual cues into the template when using the cosine window. Besides, we jointly perform template learning and reliable sample construction into a unified learning paradigm to benefit from each other, which further can be carried out in the frequency domain without incurring excessive time cost by skillful decomposition. Experiments on several popular visual tracking datasets verify the efficacy of ESCF and show that ESCF performs favorably against several well-established representative counterparts. © 2023 IEEE.

关键词： Correlation filter Reliable sample construction Sparse representation Unfiltered features

来源：评论

学校读者我要写书评

暂无评论

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Dialogue State Tracking

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Di...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Tianhang Song Haolei Hu Xinxin Chen Kangli Zi Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Task-oriented dialogue systems (TOD) aim to help users complete specific tasks through multiple rounds of dialogue, in which Dialogue State Tracking (DST) is a key component. The training of DST models typically necessitates the availability of a substantial corpus of dialogue data with turn-level annotations. However, the collection of such data is both costly and inefficient. Despite the impressive performance of systems based on advanced large language models (LLMs), their closed-source nature restricts the potential for local deployment. To address this challenge, this paper proposes a new zero-shot slot-aware enhanced model (SAE), which introduces a novel coded prompting framework to enhance the DST capability of small parameter models in new domains and task scenarios. In particular, we have devised a prompting framework that employs code to refine task instructions. Furthermore, we have proposed a slot-aware question generation mechanism that generates slot-aware questions based on contextual details in accordance with the dialogue context, thereby enhancing the model's perception and matching capabilities for slots. In order to verify the effectiveness of the model, we conducted experiments on the MultiWOZ dataset. The results show that the SAE model has achieved significant performance improvements in zero-shot DST tasks.

关键词： Training Adaptation models Codes Large language models Computational modeling Termination of employment Predictive models Question generation Data models Context modeling

来源：评论

学校读者我要写书评

暂无评论

An Improved RRT Algorithm Based on Heuristic Function Strategy for Manipulator Path Planning

An Improved RRT Algorithm Based on Heuristic Function Strate...

引用

第43届中国控制会议

作者： Guoyu Zuo Haishan Guan Banggui Zheng Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computing Intelligence and Intelligent Systems

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Manipulator path planning refers to planning the movement trajectory of a manipulator through algorithms and techniques to realize accurate and efficient *** is widely used in industrial production lines,medical surgeries,and other *** sampling-based rapid exploration random tree(RRT) algorithm has been widely used in high-dimensional manipulators due to its probabilistic completeness and outstanding ***,the algorithm is purely random in the sampling session,which leads to the existing RRT planning algorithms still having low planning efficiency and poor path *** solve these problems,this paper proposes a new and improved method,which assigns a cost value to the sampling points and bases the selection of sampling points on the cost value,so that the growth of the path tree can be oriented to the goal point more quickly.A new evaluation metric,i.e.,the average angle of each node in the path,is also designed to evaluate the quality of the path,and the smoother the path is,the more the metric converges to 180°.By comparing our improved RRT algorithm with the original algorithm in several different scenarios,the results show that our improvement possesses shorter running time,shorter path length,and larger average angle of path.

关键词： Path planning RRT algorithm Heuristic function

来源：评论

学校读者我要写书评

暂无评论

Decomposition, Interaction, Reconstruction Meets Global Context Learning In Visual Tracking 48

Decomposition, Interaction, Reconstruction Meets Global Cont...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Tan, Huibin Hu, Kun Cao, Mingyu Wang, Mengzhu Xu, Liyang Yang, Wenjing Institute for Quantum Information State Key Laboratory of High Performance Computing China National University of Defense Technology College of Computer Science and Technology Changsha China

ISBN: (纸本)9781728163277

Tensor decomposition and reconstruction attention is a promising global context learning approach because it can remain efficient while avoiding feature compression. To exploit its potential even further in visual tracking, we redesign a 3D tensor modeling paradigm, namely tensor Decomposition, Interaction, Reconstruction attention (DIR), respectively corresponding to three function components, Tensor Decomposition Module (TDM), Tensor Interaction Module (TIM) and Context Reconstruction Module (CRM). Specifically, TDM decomposes a 3D tensor feature into rank-1 context fragments in different dimension views. The ingenuity here lies in the introduction of Circular Convolution for processing features at arbitrary scales and channel-sharing segments to enhance the interaction of the two branches in the Siamese network architecture. TIM obtains the tensor planes of each dimension by the Cross-Similarity operation of rank-1 tensors and fused cubic features, which brings more interactions between all feature dimensions. CRM reconstructs 3D context representations with the outputs of the above modules. In experiments, DIR is embedded into the tracker to verify its effectiveness. © 2023 IEEE.

关键词： context reconstruction Siamese tracking single object tracking tensor plane

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation

arXiv

引用

arXiv 2025年

作者： Yu, Peilin Wu, Yuwei Gao, Zhi Fan, Xiaomeng Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimization on Riemannian manifolds. However, existing Riemannian meta-optimization methods take up huge memory footprints in large-scale optimization settings, as the learned optimizer can only adapt gradients of a fixed size and thus cannot be shared across different Riemannian parameters. In this paper, we propose an efficient Riemannian meta-optimization method that significantly reduces the memory burden for large-scale optimization via a subspace adaptation scheme. Our method trains neural networks to individually adapt the row and column subspaces of Riemannian gradients, instead of directly adapting the full gradient matrices in existing Riemannian meta-optimization methods. In this case, our learned optimizer can be shared across Riemannian parameters with different sizes. Our method reduces the model memory consumption by six orders of magnitude when optimizing an orthogonal mainstream deep neural network (e.g. ResNet50). Experiments on multiple Riemannian tasks show that our method can not only reduce the memory consumption but also improve the performance of Riemannian meta-optimization. © 2025, CC BY-NC-ND.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Large area crystalline Weyl semimetal with nano Au film based micro-fold line array for THz detector

引用

Science China(Technological Sciences) 2023年第11期66卷 3267-3275页

作者： SONG Qi ZHOU Yu JIA ErSe WANG JiaTong ZHANG Min ZHANG BingYuan Shandong Key Laboratory of Optical Communication Science and Technology School of Physics Science and Information TechnologyLiaocheng UniversityLiaocheng 252059China North China Institute of Computing Technology Beijing 100083China Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province College of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China School of Precision Instrument and Opto-electronics Engineering Tianjin UniversityTianjin 300072China

The advancement of 6G technology relies on the development of high-performance terahertz detectors that can operate at room *** detectors are crucial for Internet of Things(Io T)applications,which require sensitive environmental sensing and efficient reception of 6G *** significant research focus is on detection technology with high responsiveness and low equivalent noise power for 6G signals,which experience high losses in the *** meet the demand for ultra-sensitive detectors in 6G technology,we have employed several ***,we prepared a large area of Weyl-semimetal layer through magnetron ***,we obtained a high-quality Weyl-semimetal active layer by carefully controlling the annealing ***,a thin nano-Au layer was introduced as a micro-cavity reflection layer to enhance the device's detection ***,we incorporated an electromagnetic induction well to improve carrier confinement and enhance the detection *** proposed high-performance terahertz detector,with its potential for industrial production,offers a valuable technical solution for the advancement of 6G technology.

关键词： micro-cavity Weyl semimetal crystalline thin film THz device

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：