检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xiang, Wenzhao Liu, Chang Yu, Hongyang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Peng Cheng Laboratory China University of Chinese Academy of Sciences China Department of Electronic Engineering Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain abundant redundant information, leading the pixel-based MIM reconstruction process to focus excessively on finer details such as textures, thus prolonging training times unnecessarily. Addressing this challenge requires a shift towards a compact representation of features during MIM reconstruction. Frequency domain analysis provides a promising avenue for achieving compact image feature representation. In contrast to the commonly used Fourier transform, wavelet transform not only offers frequency information but also preserves spatial characteristics and multi-level features of the image. Additionally, the multi-level decomposition process of wavelet transformation aligns well with the hierarchical architecture of modern neural networks. In this study, we leverage wavelet transform as a tool for efficient representation learning to expedite the training process of MIM. Specifically, we conduct multi-level decomposition of images using wavelet transform, utilizing wavelet coefficients from different levels to construct distinct reconstruction targets representing various frequencies and scales. These reconstruction targets are then integrated into the MIM process, with adjustable weights assigned to prioritize the most crucial information. Extensive experiments demonstrate that our method achieves comparable or superior performance across various downstream tasks while exhibiting higher training efficiency. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Chinese Event Extraction Method Based on Roformer Model

引用

Wireless Communications and Mobile computing 2023年第1期2023卷

作者： Qiang, Baohua Zhou, Xiangyu Wang, Yufeng Yang, Xianyi Wang, Yuemeng Tian, Jubo Chen, Peng Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC Shijiazhuang050081 China

Event extraction is an important research direction in the field of natural language processing. The current Chinese event extraction field still suffers from errors in the pretraining and fine-tuning stages, inability to directly handle texts with more than 512 tokens, and inaccurate event extraction due to insufficient semantic sample diversity. In this paper, we propose a Chinese event extraction method RoformerFC (Roformer model with FGM and CRF) based on the Roformer model to address the above problems. Firstly, our method utilizes the Roformer model based on rotary position embedding, which both moderates the errors in the pretraining and fine-tuning phases and allows the model to directly handle texts with more than 512 tokens;then, the adversarial networks based on FGM (fast gradient method) are realized to increase the diversity of semantic feature samples;finally, the classical CRF (conditional random fields) model is used to decode and identify the event element entity and its corresponding event role and event type. On the short text DuEE dataset, the microP, microR, and microF of our method improved 1.26%, 4.01%, and 2.68%, respectively, over the classical Chinese event extraction method BERT-CRF. On the long text JsEE dataset, the microP, microR, and microF of our method improved 2.26%, 5.03%, and 3.72%, respectively, over the classical Chinese event extraction method BERT-CRF. © 2023 Baohua Qiang et al.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DragEntity:Trajectory Guided Video Generation using Entity and Positional Relationships

arXiv

引用

arXiv 2024年

作者： Wan, Zhang Tang, Sheng Wei, Jiawei Zhang, Ruize Cao, Juan Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Zhengzhou University Zhengzhou China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, existing control methods still face two limitations: Firstly, control conditions (such as depth maps, 3D Mesh) are difficult for ordinary users to obtain directly. Secondly, it’s challenging to drive multiple objects through complex motions with multiple trajectories simultaneously. In this paper, we introduce DragEntity, a video generation model that utilizes entity representation for controlling the motion of multiple objects. Compared to previous methods, DragEntity offers two main advantages: 1) Our method is more user-friendly for interaction because it allows users to drag entities within the image rather than individual pixels. 2) We use entity representation to represent any object in the image, and multiple objects can maintain relative spatial relationships. Therefore, we allow multiple trajectories to control multiple objects in the image with different levels of complexity simultaneously. Our experiments validate the effectiveness of DragEntity, demonstrating its excellent performance in fine-grained control in video generation. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

arXiv

引用

arXiv 2025年

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart 24

CT2C-QA: Multimodal Question Answering over Chinese Text, Ta...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhao, Bowen Cheng, Tianhao Zhang, Yuejie Cheng, Ying Feng, Rui Zhang, Xiaobo Fudan University Shanghai China Children's Hospital of Fudan University Shanghai China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing. China Fudan Zhangjiang Institute Shanghai China Children's Hospital of Fudan University National Children's Medical Center Shanghai China

ISBN: (纸本)9798400706868

Multimodal Question Answering (MMQA) is crucial as it enables comprehensive understanding and accurate responses by integrating insights from diverse data representations such as tables, charts, and text. Most existing researches in MMQA only focus on two modalities such as image-text QA, table-text QA and chart-text QA, and there remains a notable scarcity in studies that investigate the joint analysis of text, tables, and charts. In this paper, we present CT2C-QA, a pioneering Chinese reasoning-based QA dataset that includes an extensive collection of text, tables, and charts, meticulously compiled from 200 selectively sourced webpages. Our dataset simulates real webpages and serves as a great test for the capability of the model to analyze and reason with multimodal data, because the answer to a question could appear in various modalities, or even potentially not exist at all. Additionally, we present AED (Allocating, Expert and Decision), a multi-agent system implemented through collaborative deployment, information interaction, and collective decision-making among different agents. Specifically, the Assignment Agent is in charge of selecting and activating expert agents, including those proficient in text, tables, and charts. The Decision Agent bears the responsibility of delivering the final verdict, drawing upon the analytical insights provided by these expert agents. We execute a comprehensive analysis, comparing AED with various state-of-the-art models in MMQA, including GPT-4. The experimental outcomes demonstrate that current methodologies, including GPT-4, are yet to meet the benchmarks set by our dataset. © 2024 ACM.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Combination of graphics, uncertainty, and semantics: A survey

Combination of graphics, uncertainty, and semantics: A surve...

引用

作者： Gao, Yuan Rafi, Muhammad Adnan Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Chinese Academy of Sciences Beijing China Department of Computer Science Aston University Birmingham United Kingdom

Graphics, uncertainty, and semantics are three approaches to building models. The combination of the three approaches is a way to develop a stronger modeling method. This article surveys the research efforts toward combining these aspects, which can be divided into two routes: One is to combine graphics and uncertainty as probabilistic graphical models and then incorporate semantics, and the other is to combine graphics and semantics and then incorporate probability to handle uncertainty. The models and methods involved in these efforts are introduced and their expressiveness, pros, and cons are discussed. © 2021 John Wiley & Sons Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Trajectory and Resource Optimization for Uav Communication Systems

SSRN

引用

SSRN 2023年

作者： Xu, Jiaming He, Chunlong Li, Xingquan Li, Zhukun The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China The Shenzhen Institute of Information Technology Shenzhen China

In this paper, we focus on trajectory optimization for multiple unmanned aerial vehicles (UAVs) which are utilized as aerial base stations (BS) to provide radio coverage for Internet of Things (IoT) devices. These IoT devices are randomly distributed in a three-dimensional region with unknown locations and channel parameters. By optimizing the UAV trajectory and power, we aim to achieve the minimum communication time for all IoT devices. However, the unknown flight time of the UAVs and the IoT device locations make it difficult to formulate an optimization problem between the objective and variables by using traditional convex optimization. To deal with this intractable problem, we propose a Deep Reinforcement Learning (DRL)-based solution, specifically Proximal Policy Optimization (PPO), modeling it as a Markov Decision Process (MDP). Our simulation results show that the proposed PPO offers promising performance for both training and testing phases. © 2023, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Interactive Navigation Method with Effect-oriented Affordance

An Interactive Navigation Method with Effect-oriented Afford...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaohan Wang Yuehu Liu Xinhang Song Yuyi Liu Sixian Zhang Shuqiang Jiang Institute of Artificial Intelligence and Robotics Xi’ an Jiaotong University Xi'an 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

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Visual navigation is to let the agent reach the target according to the continuous visual input. In most previous works, visual navigation is usually assumed to be done in a static and ideal environment: the target is always reachable with no need to alter the environment. However, the “messy” environments are more general and practical in our daily lives, where the agent may get blocked by obstacles. Thus Interactive Navigation (InterNav) is introduced to navigate to the objects in more realistic “messy” environments according to the object interaction. Prior work on InterNav learns shortterm interaction through extensive trials with reinforcement learning. However, interaction does not guarantee efficient navigation, that is, plan-ning obstacle interactions that make shorter paths and con-sume less effort is also crucial. In this paper, we introduce an effect-oriented affordance map to enable longterm interactive navigation, extending the existing map-based nav-igation framework to the domain of dynamic environment. We train a set of affordance functions predicting available interactions and the time cost of removing obstacles, which informatively support an interactive modular system to ad-dress interaction and longterm planning. Experiments on the ProcTHOR simulator demonstrate the capability of our affordance-driven system in longterm navigation in complex dynamic environments.

关键词： Visualization Computer vision Uncertainty Costs Navigation Affordances Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Thermal constraint control of reversible solid oxide cell for optimal system efficiency

引用

International Journal of Hydrogen Energy 2025年 134卷 198-211页

作者： Xu, Yuanwu Yin, Jie Wang, Jingjing Wu, Xiao-long Peng, Jingxuan Tang, Ruifeng Zou, Suhang Fu, Xiaowei Li, Xi School of Artificial Intelligence and Automation Wuhan University of Science and Technology Hubei Wuhan430081 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China School of Information Engineering Nanchang University Jiangxi Nanchang330031 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore China-Poland Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China

Reversible solid oxide cell (RSOC) demonstrates considerable promise in multimodal energy conversion architectures, particularly as a technology for hydrogen-based energy storage systems. Nevertheless, under dynamic operating regimes with time-varying current inputs, realizing time-efficient and reliable transitions to steady-state operation remains difficult. This difficulty arises from the intricate coupling of thermal, electrical, and gaseous processes within the RSOC system. This study aims to address these challenges by developing a 5 kW mathematical model of the RSOC system. The proposed model enables systematic investigation of thermal safety issues arising during current switching operations while introducing a thermal constraint control strategy to enhance both system efficiency and thermal safety performance. This efficiency-driven study employs the Grid Search algorithm to identify optimal steady-state operating points for the RSOC system, ensuring strict adherence to safety constraints across varying current inputs. Furthermore, by integrating the pre-identified optimal operating points as feedforward control with Model Predictive Control (MPC)-based feedback correction, this hybrid strategy effectively mitigates stack temperature gradient overshoot while synchronously ensuring optimal system efficiency throughout current transition processes. Under simulated variable current inputs, the proposed RSOC system model and control strategy demonstrate the capability to constrain stack temperature gradient overshoot within 2.3K while enhancing transient efficiency by 5 %–8 %, achieving a peak system efficiency of 85 %. It provides a novel methodology for safe and efficient working with intermittent renewable energy. © 2025 Hydrogen Energy Publications LLC

关键词： Thermal variables control

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：