检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Han, Fangzhou Yu, Tianyi Zhang, Lamei Si, Lingyu Zhang, Yiqi Dept. of Information Engineering Harbin Institute of Technology Harbin China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350368741

Despite significant advancements in remote sensing multimodal learning, particularly in image-image feature fusion, the exploration of audio-image feature fusion remains insufficient. Given the complexity and redundancy of ground objects in remote sensing images, accurately aligning audio features with image features during the fusion process is a critical challenge. In this paper, we introduce an object-centric feature fusion method named SlotFusion. By employing a slot attention-based feature decoupling module and a slot-based audiovisual feature fusion module, we transform modality features with complex semantic information into a set of slot features corresponding to object units and use gated activation units to adaptively implement object-centric feature fusion. Experiments on the Audio Visual Aerial Scene Recognition dataset (ADVANCE) demonstrate that the proposed SlotFusion significantly improves remote sensing scene recognition performance, with a 7.04% increase in overall accuracy compared to previous methods, achieving state-of-the-art results. © 2025 IEEE.

关键词： Audiovisual feature fusion Gated feature fusion Object-centric learning Slot attention

来源：评论

学校读者我要写书评

暂无评论

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

A Static and Dynamic Attention Framework for Multi Turn Dial...

引用

作者： Zhang, Weinan Cui, Yiming Zhang, Kaiyan Wang, Yifa Zhu, Qingfu Li, Lingzhi Liu, Ting Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Harbin China State Key Laboratory of Cognitive Intelligence IFLYTEK Research Beijing China

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using an RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this article, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on the Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation. © 2023 Association for Computing Machinery.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection

arXiv

引用

arXiv 2023年

作者： Yang, Jianhua Dai, Kun The State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Wuhu Robot Industry Technology Research Institute Harbin Institute of Technology Wuhu241000 China

Designing a real-time framework for the spatiotemporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we adopt the existing efficient 3D CNN to save development time. By combining 3D backbones and 2D backbones of different sizes, we design a YOWOv2 family including YOWOv2-Tiny, YOWOv2-Medium, and YOWOv2-Large. We also introduce the popular dynamic label assignment strategy and anchor-free mechanism to make the YOWOv2 consistent with the advanced model architecture design. With our improvement, YOWOv2 is significantly superior to YOWO, and can still keep real-time detection. Without any bells and whistles, YOWOv2 achieves 87.0% frame mAP and 52.8% video mAP with over 20 FPS on the UCF101-24. On the AVA, YOWOv2 achieves 21.7% frame mAP with over 20 FPS. Our code is available on https://***/yjh0410/YOWOv2. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Transfer force perception skills to robot‐assisted laminectomy via imitation learning from human demonstrations

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 903-916页

作者： Meng Li Xiaozhi Qi Xiaoguang Han Ying Hu Bing Li Yu Zhao Jianwei Zhang Harbin Institute of Technology ShenzhenChina Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhenChina Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenChina Beijing Jishuitan Hospital Capital Medical UniversityBeijingChina Department of Orthopedics Peking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina University of Hamburg Hamburg22527Germany

A comparative study of two force perception skill learning approaches for robot‐assisted spinal surgery,the impedance model method and the imitation learning(IL)method,is *** impedance model method develops separate models for the surgeon and patient,incorporating spring‐damper and bone‐grinding *** surgeons'feature parameters are collected and mapped using support vector regression and image navi-gation *** imitation learning approach utilises long short‐term memory networks(LSTM)and addresses accurate data labelling challenges with custom *** results demonstrate skill recognition rates of 63.61%-74.62%for the impedance model approach,relying on manual feature ***,the imitation learning approach achieves a force perception recognition rate of 91.06%,outperforming the impedance model on curved bone *** findings demonstrate the potential of imitation learning to enhance skill acquisition in robot‐assisted spinal surgery by eliminating the laborious process of manual feature extraction.

关键词： learning(artificial intelligence) medical applications medical signal processing robotics

来源：评论

学校读者我要写书评

暂无评论

Multipath matching pursuit using a cross-validation technique for sparse direction-of-arrival estimation with an acoustic vector array

引用

Chinese Journal of Acoustics 2023年第2期42卷 153-170页

作者： TAN Peng HU Bo ZHANG Youwen WU Yuquan YANG Desen Acoustic Science and Technology Laboratory Harbin Engineering UniversityHarbin 150001 Key Laboratory of Marine Information Acquisition and Security(Harbin Engineering University) Ministry of Industry and Information TechnologyHarbin 150001 College of Underwater Acoustic Engineering Harbin Engineering UniversityHarbin 150001 School of Electronics and Information Jiangsu University of Science and TechnologyZhenjiang 212100 Science and Technology on Integrated Information System Laboratory Institute of SoftwareChinese Academy of SciencesBeijing 100190

High-resolution direction-of-arrival(DOA)estimations and the starboard ambiguity of moving underwater targets have always been key issues in underwater acoustic array signal *** with sound pressure arrays,vector arrays have natural advantages with respect to solving the starboard ambiguity problem and obtaining higher processing *** high-resolution DOA estimation methods such as Capon have disadvantages such as being unable to resolve coherent sources,requiring multiple snapshot processing,and being sensitive to array manifold ***-resolution DOA estimation and the starboard ambiguity of moving underwater targets have always been challenging research *** one hand,maneuvering underwater targets reduce the coherence time of the received signals,which ultimately leads to poor performance when using high-resolution DOA estimation technologies based on the covariance matrix of the received *** the other hand,traditional DOA estimation technologies based on sound pressure arrays have the problem of port and starboard ambiguity,which can be solved by maneuvering the sonar ***,maneuvering the sonar platform can impair the coherence of the received signal,on which some algorithms *** approach greatly limits the combat effectiveness and performance of the *** the aforementioned problems and taking advantage of the target sparsity,a cross-validation multipath matching pursuit technique based on the sparse DOA estimation of an acoustic vector array is proposed in this article for sonar *** proposed algorithm uses cross-validation technology to achieve a sparse DOA estimation with an unknown number of targets in a sonar observation *** with the conventional acoustic vector array-based Capon algorithm,the proposed algorithm can achieve a sparse DOA estimation and high-resolution capability with small numbers of snapshots or even single *** effectiveness of the proposed

关键词： multipath estimation underwater

来源：评论

学校读者我要写书评

暂无评论

LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction 30

LM-Combiner: A Contextual Rewriting Model for Chinese Gramma...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Wang, Yixuan Wang, Baoxin Liu, Yijun Wu, Dayong Che, Wanxiang Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China State Key Laboratory of Cognitive Intelligence iFLYTEK Research China

ISBN: (纸本)9782493814104

Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods based on voting can effectively mitigate over-correction and improve the precision of the GEC system. However, these methods still require the output of several GEC systems and inevitably lead to reduced error recall. In this light, we propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble. Specifically, we train the model on an over-correction dataset constructed through the proposed K-fold cross inference method, which allows it to directly generate filtered sentences by combining the original and the over-corrected text. In the inference stage, we directly take the original sentences and the output results of other systems as input and then obtain the filtered sentences through LM-Combiner. Experiments on the FCGEC dataset show that our proposed method effectively alleviates the over-correction of the original system (+18.2 Precision) while ensuring the error recall remains unchanged. Besides, we find that LM-Combiner still has a good rewriting performance even with small parameters and few training data, and thus can cost-effectively mitigate the over-correction of black-box GEC systems (e.g., ChatGPT). © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Flapping-Wing Robot Achieves Multi-Domain Locomotion Using Transformable Wheel Mechanism

Flapping-Wing Robot Achieves Multi-Domain Locomotion Using T...

引用

IEEE International Conference on robotics and Biomimetics

作者： Xiangxiao Chai Shihua Wang Erzhen Pan Wenfu Xu School of Mechanical Engineering and Automation Harbin Institute of Technology (Shenzhen) Shenzhen China Key University Laboratory of Mechanism & Machine Theory and Intelligent Unmanned Systems of Guangdong Shenzhen China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

The difficulty of moving from aquatic to aerial environment is one of the major challenges limiting the development of trans-medium multi-domain locomotion vehicles. In this paper, the concept of the transformable wheel, a feature commonly found in autonomous land vehicles (AL V s), is introduced into the design. Additionally, a flapping-wing robot equipped with multi-domain locomotion capability, which can not only realize aerial flight and surface navigation on water, but also ascend from water to land for subsequent takeoff is presented. The paper first introduces the system design of the robot and proposes the corresponding multi-domain locomotion strategy. Subsequently, the design of the transformable wheel mechanism is described in detail and the force analysis for the water-exit is conducted. The feasibility of the proposed strategy is experimentally validated, confirming the prototype's multi-domain locomotion performance finally. This research explores the feasibility of introducing the transformable wheel mechanism into trans-medium multi-domain vehicle platforms and provides a design example.

关键词： Legged locomotion Torque Limiting Navigation Propellers Roads Wheels Prototypes Motors system analysis and design

来源：评论

学校读者我要写书评

暂无评论

Simulation study of a spider-like robot based on leg reorganization

Simulation study of a spider-like robot based on leg reorgan...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Wang, Shu Qi Fan, Ji Zhuang Zhang, Kuan Zhang, Wei Liu, Gang Feng Zhao, Jie Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China Harbin University of Science and Technology College of Mechanical and Power Engineering Harbin China

ISBN: (纸本)9781665436786

This paper presents a four-legged bionic robot based on leg reorganization with the hunter spider as the bionic research object. By studying the biological structure of the hunter spider, its movement mode, and the characteristics of limb movement during the conversion process is analyzed and the principle of wheel and foot conversion of the robot is obtained. The three-dimensional model of the bionic robot is designed, and the overall assembly of the bionic structure model is completed. The rationality of the design of the bionic structure is initially verified by the leg reorganization. The virtual prototype is built by adding constraints to realize the bionic motion simulation, including in-situ rotary motion, foot-wheel conversion motion, wheel motion, wheel-foot conversion motion, foot motion, which provides a theoretical basis for the development of the physical prototype and the selection of hardware. © 2021 IEEE.

关键词： Wheels

来源：评论

学校读者我要写书评

暂无评论

AEROENGINE remaining life prediction based on grey similarity multiscale matching 20

AEROENGINE remaining life prediction based on grey similarit...

引用

20th International Conference on Condition Monitoring and Asset Management, CM 2024

作者： Sun, Shilong Huang, Haodong Ding, Jian Lu, Wenjie Wang, Dong School of Mechanical Engineering and Automation Harbin Institute of Technology Guangdong Shenzhen518055 China Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9780903132848

In this paper, we address the challenge of predicting the remaining useful life (RUL) of aero-engines, which are critical components of aircraft that operate under increasingly extreme conditions as engine performance enhances. Ensuring the safety and reliability of these engines is paramount. To this end, we introduce a novel RUL prediction methodology that leverages grey similarity multiscale matching. This approach employs the robust capabilities of Long Short-Term Memory (LSTM) networks for processing time-series data. Specifically, an LSTM Stacked AutoEncoder (L-SAE) is designed to extract pivotal operational features of the engine, thereby delineating its degradation trajectory. Furthermore, the grey correlation analysis is utilized to assess the similarity between these degradation trajectories, which is complemented by a multi-time scale sliding window technique for enhanced similarity matching. Subsequently, kernel density estimation is applied to gauge the uncertainty associated with the prediction outcomes. The efficacy and superiority of our proposed method are demonstrated through the validation of the experiment study. Comparative analysis reveals that our method outperforms existing techniques in key evaluation metrics, underscoring its potential applicability to large-scale datasets. This validation not only confirms the method’s effectiveness but also its advantage in predicting the RUL of aero-engines with greater accuracy and reliability. © 2024 20th International Conference on Condition Monitoring and Asset Management, CM 2024. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

S2H-GNN: Learning Soft to Hard Feature Matching with Sparsified Graph Neural Network

S2H-GNN: Learning Soft to Hard Feature Matching with Sparsif...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Tao Xie Ruifeng Li Zhiqiang Jiang Kun Dai Ke Wang Lijun Zhao Shuozhan Li State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China Fujian (Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China

In this work, we introduce a soft-to-hard network (S2H-GNN) for precise local feature matching between image pairs. The core of S2H-GNN is a weighted context aggregation algorithm that enables nodes to receive information from their neighbors in order to form a more global understanding. S2HGNN leverages a sparsified graph neural network to enhance the features, consisting of the following modules alternately: (1) Inducing Point Initial Module that uses cosine correlation to identify highly scored keypoints as Inducing points. (2) Message Passing Module that integrates the features of original keypoints into those of Inducing points, which are further leveraged to exchange messages through self attention and cross attention. (3) Attention Upsample Module that propagates the feature of Inducing points to that of original keypoints, obtaining discriminative feature representation. Additionally, we propose an assignment layer to obtain a soft assignment matrix, which views feature matching as a graphy matching problem. Finally, we introduce a novel gap loss to guide S2H-GNN in learning a discriminative cognition of matching and non-matching keypoints, ultimately obtaining the hard assignment matrix. Experimental results demonstrate that S2H-GNN achieves comparable or higher performance in image matching and homography estimation tasks.

关键词：

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：