检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Lin, Yang Guo, Hang Wang, Jinbao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment

arXiv

引用

arXiv 2023年

作者： Xu, Xiaoxu Yuan, Yitian Zhang, Qiudan Wu, Wenhui Jie, Zequn Ma, Lin Wang, Xu College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Meituan Inc. China College of Electronics and Information Engineering Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China

Learning to ground natural language queries to target objects or regions in 3D point clouds is quite essential for 3D scene understanding. Nevertheless, existing 3D visual grounding approaches require a substantial number of bounding box annotations for text queries, which is time-consuming and labor-intensive to obtain. In this paper, we propose 3D-VLA, a weakly supervised approach for 3D visual grounding based on Visual Language Alignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models (VLMs) on aligning the semantics between texts and 2D images, as well as the naturally existing correspondences between 2D images and 3D point clouds, and thus implicitly constructs correspondences between texts and 3D point clouds with no need for fine-grained box annotations in the training procedure. During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images. To the best of our knowledge, this is the first work to investigate 3D visual grounding in a weakly supervised manner by involving large scale vision-language models, and extensive experiments on ReferIt3D and ScanRefer datasets demonstrate that our 3D-VLA achieves comparable and even superior results over the fully supervised *** code will be available at https://***/xuxiaoxxxx/3D-VLA. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Secure and Scalable Blockchain for IIoT with Dual Compression Scheme

Secure and Scalable Blockchain for IIoT with Dual Compressio...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Tianxi Wang Jiqiang Liu Tianhao Liu Di Zhai Jian Wang Tao Zhang Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China School of Software Engineering Beijing Jiaotong University Beijing China

The Industrial Internet of Things(IIoT) plays a vital role as a fundamental technology supporting intelligent manufacturing. Existing IIoT platform adopts cloud-edge design, the centralized cloud stores a large amount of sensitive data, which is vulnerable to attack and faces the risk of single point of failure. As a distributed system, blockchain enables secure and robust IIoT systems. Therefore, this paper builds a blockchain-based IIoT platform to store the data in IIoT into the blockchain and ensure security through a decentralized and distributed consensus mechanism. However, the existing blockchain platforms have low throughput and cannot meet the demand of high concurrent data processing. To solve this problem, this paper designs a dual data compression optimization scheme, which can effectively reduce the size of the transaction and improve the transaction processing speed. This scheme provides an effective solution for promoting the deep application of blockchain and IIoT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Visual SLAM System for Autonomous Vehicles in Dynamic Environments

A Novel Visual SLAM System for Autonomous Vehicles in Dynami...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Xinyu Zeng Ying He F. Richard Yu Guang Zhou Shenzhen Key Lab of Digital & Intelligent Technologies & Systems College of Computer Science and Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Deeproute Inc

With the development of autonomous vehicles and intelligent robots, visual simultaneous localization and mapping (SLAM) has attracted great attentions. Most existing visual SLAM systems assume that the objects are stationary in static environments. However, in the real world, there are many objects that are non-stationary in dynamic environments, which will cause performance degradation of visual SLAM systems. In this paper, to address this issue, we propose a novel visual SLAM system based on multi-task deep neural networks. Specifically, we apply multi-task deep neural networks to extract oriented keypoints and perceive dynamic semantic regions, which are used to perform outlier rejection in the SLAM system. We evaluate our method on public datasets, and the results show that our method outperforms existing visual SLAM systems. The presentation video url is: https://***/qGE1OvaJvV0.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions

arXiv

引用

arXiv 2023年

作者： Peng, Qiuyu Jiang, Zifei Huang, Yan Peng, Jingliang School of Software Shandong University Shandong Jinan250101 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and Engineering University of Jinan Shandong Jinan250022 China

The existing face image super-resolution (FSR) algorithms usually train a specific model for a specific low input resolution for optimal results. By contrast, we explore in this work a unified framework that is trained once and then used to super-resolve input face images of varied low resolutions. For that purpose, we propose a novel neural network architecture that is composed of three anchor auto-encoders, one feature weight regressor and a final image decoder. The three anchor auto-encoders are meant for optimal FSR for three pre-defined low input resolutions, or named anchor resolutions, respectively. An input face image of an arbitrary low resolution is firstly up-scaled to the target resolution by bi-cubic interpolation and then fed to the three auto-encoders in parallel. The three encoded anchor features are then fused with weights determined by the feature weight regressor. At last, the fused feature is sent to the final image decoder to derive the super-resolution result. As shown by experiments, the proposed algorithm achieves robust and state-of-the-art performance over a wide range of low input resolutions by a single framework. Code and models will be made available after the publication of this work. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Question generation based on chat-response conversion

Question generation based on chat-response conversion

引用

作者： Zhong, Sheng-Hua Peng, Jianfeng Liu, Peiqi College of Computer Science and Software Engineering Shenzhen University Shenzhen China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Today, thanks to the major breakthrough of sequences to sequences model in the field of natural language, most of the dialogue generation tasks are focused on generating more effective responses. However, the responses proposed by the chat-bot are only a passive answer or assentation, which does not arouse the desire of people to continue communicating. How to transform the chat robot from a passive reply to an active questioner has become an urgent problem. In this paper, a question generalization method with four types of question proposing schemes are designed, implemented, and tested to automate question generation process. The proposed system is controlled by a probability-triggered multiple conversion mechanism to actively propose different types of questions. We embed our methods in the mainstream dialogue generation model and demonstrate its effectiveness in dialogue response generalization on a standard dataset. In addition, it achieves good performance in subjective conversational assessment. © 2019 John Wiley & Sons, Ltd.

关键词： dialogue response generalization system probability-triggered question generation

来源：评论

学校读者我要写书评

暂无评论

Integration of Artificial Intelligence and Wearable Internet of Things for Mental Health Detection

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 307-315页

作者： Wang, Wei Chen, Jian Hu, Yuzhu Liu, Han Chen, Junxin Gadekallu, Thippa Reddy Garg, Lalit Guizani, Mohsen Hu, Xiping Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong Shenzhen518172 China School of Medical Technology Beijing Institute of Technology Beijing100081 China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen518000 China School of Software Dalian University of Technology Dalian116621 China Division of Research and Development Lovely Professional University Phagwara India Center of Research Impact and Outcome Chitkara University Punjab India Faculty of Information and Communication Technology University of Malta Msida Malta United Arab Emirates

The integration of Artificial Intelligence (AI) and Wearable Internet of Things (WIoT) for mental health detection is a promising area of research with the potential to revolutionize mental health monitoring and diagnosis. Since early detection of mental diseases, i.e., depression, is of great importance for diagnosis and treatment, a fast and convenient way is urgently needed. Traditional diagnostic methods are time-consuming, laborious, over-subjective, and easily lead to misdiagnosis. The advance in information techniques and wearable devices brings innovation to mental disease detection. Therefore, this article first compares intelligent depression detection methods and traditional methods to illustrate the significance and then analyzes the opportunities of the wearable device. Then we provide specific psychophysiological data measured by wearable devices and introduce relevant datasets for depression detection. An illustrative example of depression detection with sleep data is presented and discussed and our proposed ensemble method has improved nearly 10% to baselines. Analytical results demonstrate the great potential of using wearable device-measured psychophysiological data to detect depression intelligently. © 2024 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Unstructured Data Representation Enhanced Model for Postoperative Risk Prediction 21

An Unstructured Data Representation Enhanced Model for Posto...

引用

21st Chinese National Conference on Computational Linguistic, CCL 2022

作者： Wang, Yaqiang Yang, Xiao Hao, Xuechao Shu, Hongping Chen, Guo Zhu, Tao College of Software Engineering Chengdu University of Information Technology China Institute for Data Science and Engineering Chengdu University of Information Technology China Sichuan Key Laboratory of Software Automatic Generation and Intelligent Service China Department of Anesthesiology Sichuan University China

Postoperative risk prediction has a positive effect on clinical resource planning, emergency plan preparation and reducing postoperative risk and mortality. Postoperative risk prediction is mainly based on patient's basic information, laboratory tests, vital signs and other structured data, while the value of unstructured preoperative diagnosis with rich semantic information remains to be verified. Aiming at attempting this problem, an unstructured data representation enhanced postoperative risk prediction model is proposed in this paper. The model utilizes self-attention to fuse structured data with preoperative diagnosis. Through comparing with the commonly used statistical machine learning models and the state-of-the-art deep neural networks, the proposed model has not only better prediction performance, but also better interpretability. © 2022 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dual Channel Convolution Hypergraph Representation Learning for Technological Intellectual Property

Adaptive Dual Channel Convolution Hypergraph Representation ...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yuxin Liu Yawen Li Yingxia Shao Zeli Guan Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing School of Economics and Management Beijing University of Posts and Telecommunications Beijing

ISBN: (纸本)9781665456579

In the age of big data, the demand for hidden information mining in technological intellectual property (tech-IP) is increasing in discrete countries. Definitely, a considerable number of graph learning algorithms for technological intellectual property have been proposed. The goal is to model the technological intellectual property entities and their relationships through the graph structure and use the neural network algorithm to extract the hidden structure information in the graph. However, most of the existing graph learning algorithms merely focus on the information mining of binary relations in technological intellectual property, ignoring the higher-order information hidden in non-binary relations. Therefore, a hypergraph neural network model based on dual channel convolution is proposed. For the hypergraph constructed from technological intellectual property data, the hypergraph channel and the line expanded graph channel of the hypergraph are used to learn the hypergraph, and the attention mechanism is introduced to adaptively fuse the output representations of the two channels. The proposed model outperforms the existing approaches on a variety of datasets.

关键词： Representation learning Adaptation models Convolution Fuses Computational modeling Neural networks Intellectual property

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Semantic Representation Learning of Scientific Literature Based on Graph Attention Mechanism and Maximum Mutual Information

Unsupervised Semantic Representation Learning of Scientific ...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Hongrui Gao Yawen Li Meiyu Liang Zeli Guan Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing School of Economics and Management Beijing University of Posts and Telecommunications Beijing

ISBN: (纸本)9781665456579

Since most scientific literature data are unlabeled, this makes unsupervised graph-based semantic representation learning crucial. Therefore, an unsupervised semantic representation learning method of scientific literature based on graph attention mechanism and maximum mutual information (GAMMI) is proposed. By introducing a graph attention mechanism, the weighted summation of nearby node features makes the weights of adjacent node features entirely depend on the node features. Depending on the features of the nearby nodes, different weights can be applied to each node in the graph. In addition, an unsupervised graph contrastive learning strategy is proposed to solve the problem of being unlabeled and scalable on large-scale graphs. By comparing the mutual information between the positive and negative local node representations on the latent space and the global graph representation, the graph neural network can capture both local and global information. Experimental results demonstrate competitive performance on various node classification benchmarks, achieving good results and sometimes even surpassing the performance of supervised learning.

关键词： Representation learning Cloud computing Semantics Supervised learning Computer architecture Benchmark testing Graph neural networks

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：