检索结果-内蒙古大学图书馆

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

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

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

Integrating Velox into TinkerPop for Graph Queries on Vectorized Engine 3

Integrating Velox into TinkerPop for Graph Queries on Vector...

引用

3rd International Conference on Electronic information Engineering and Computer, EIECT 2023

作者： Li, Zihao Xu, Liyang Jin, Ruochun Chen, Huan Tang, Yuhua National University of Defense Technology Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology Changsha410073 China

ISBN: (纸本)9798350357707

To enhance the query efficiency of relational databases and build a unified computing backend, Meta has developed Velox, a vectorized execution engine library based on columnar storage, Currently, there is no standardized specification for computation engine, and storage in graph databases, leading to failed to effectively utilize the vectorized processing capability of modern CPU. In this paper, we propose a middleware that primarily focuses on (1) non-invasively integrating Velox into the TinkerPop framework to provide unified vectorized engine acceleration for all graph databases supporting the TinkerPop specification;(2) conducting graph queries based on the relational data storage model, eliminating the overhead of transforming the storage model into a graph storage model;(3) validating the acceleration effect of the vectorized engine on interactive workload of graph queries under a single-node environment. © 2023 IEEE.

关键词： Engines

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

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

Multi-Label Stereo Matching for Transparent Scene Depth Estimation

arXiv

引用

arXiv 2025年

作者： Liu, Zhidan Yao, Chengtang Zeng, Jiaxi Wu, Yuwei 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

In this paper, we present a multi-label stereo matching method to simultaneously estimate the depth of the transparent objects and the occluded background in transparent scenes. Unlike previous methods that assume a unimodal distribution along the disparity dimension and formulate the matching as a single-label regression problem, we propose a multi-label regression formulation to estimate multiple depth values at the same pixel in transparent scenes. To resolve the multi-label regression problem, we introduce a pixel-wise multivariate Gaussian representation, where the mean vector encodes multiple depth values at the same pixel, and the covariance matrix determines whether a multi-label representation is necessary for a given pixel. The representation is iteratively predicted within a GRU framework. In each iteration, we first predict the update step for the mean parameters and then use both the update step and the updated mean parameters to estimate the covariance matrix. We also synthesize a dataset containing 10 scenes and 89 objects to validate the performance of transparent scene depth estimation. The experiments show that our method greatly improves the performance on transparent surfaces while preserving the background information for scene reconstruction. Code is available at https://***/BFZD233/TranScene. © 2025, CC BY.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

CAMG: Context-Aware Moment Graph Network for Multimodal Temporal Activity Localization via Language 12th

CAMG: Context-Aware Moment Graph Network for Multimodal Tem...

引用

12th National CCF Conference on Natural Language Processing and Chinese computing, NLPCC 2023

作者： Hu, Yuelin Xu, Yuanwu Zhang, Yuejie Feng, Rui Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai200433 China School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics Shanghai200433 China School of Information Technology Deakin University Waurn PondsVIC3216 Australia

ISBN: (纸本)9783031446924

Temporal Activity Localization via Language (TALL) is a challenging task for language based video understanding, especially when a video contains multiple moments of interest and the language query has words describing complex context dependencies between the moments. Latest studies have proposed various ways to exploit the temporal context of adjacent moments, but two apparent limitations remained. First, only limited context information was encoded based on RNNs or 2-D convolutions, which highly depended on the pre-sorting of proposals and lacked flexibility. Second, semantically correlated content in different moments was ignored, i.e., semantic context. To address these limitations, we propose a novel GCN-based framework, i.e., Context-Aware Moment Graph (CAMG) network, to jointly model the temporal context and semantic context. Also, we design a multi-step fusion scheme to aggregate object, motion and textual features. A Query-Gated Integration Module is further designed to select queried objects and filter out noisy ones. Our model achieves superior performance to state-of-the-art methods on two widely-used benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu Asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

来源：评论

学校读者我要写书评

暂无评论

Difference-Beam-Pattern Synthesis of Radome-Enclosed Linear Array Using Convex Optimization

Difference-Beam-Pattern Synthesis of Radome-Enclosed Linear ...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Li, Weizong Jiao, Yongchang Hu, Hao Yan, Yangdong Pu, Xifeng Zhang, Yixuan Xidian University Shaanxi Key Laboratory of Large Scale Electromagnetic Computing Xi'an China Beijing Institute of Control and Electronic Technology Beijing China Xi'an Insitute of Electromechanical Information Technology Xi'an China

ISBN: (纸本)9798350355581

To correct the influence of radome on the radiation pattern of array antenna, the difference-beam-pattern synthesis method of radome-enclosed array antenna based on convex optimization is proposed, which takes radome-enclosed array antenna system as a whole to synthesize difference-beam-pattern. Through fixing the slope phase of the difference beam, the non-convex quadratic objective function which maximizes the difference beam slop is transformed into a convex optimization objective function which minimizes a linear function. Moreover, to accurately consider the interaction between array and radome, active element patterns are used to ensure the accuracy and reliability of the optimization results. Finally, the difference beam-pattern for a 40-element radome-enclosed array with - 30dB sidelobe and -70 dB null depth are achieved, and the validity and efficiency of the proposed method are verified. © 2024 IEEE.

关键词： Radomes

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：