检索结果-内蒙古大学图书馆

Content-aware Warping for View Synthesis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Mantang Hou, Junhui Jin, Jing Liu, Hui Zeng, Huanqiang Lu, Jiwen The Department of Computer Science City University of Hong Kong Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China The School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The School of Information Science and Engineering Huaqiao University Xiamen China The Department of Automation Tsinghua University Beijing China

Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limited neighborhood and only distance-based interpolation weights. To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network. Based on this learnable warping module, we propose a new end-to-end learning-based framework for novel view synthesis from a set of input source views, in which two additional modules, namely confidence-based blending and feature-assistant spatial refinement, are naturally proposed to handle the occlusion issue and capture the spatial correlation among pixels of the synthesized view, respectively. Besides, we also propose a weight-smoothness loss term to regularize the network. Experimental results on light field datasets with wide baselines and multi-view datasets show that the proposed method significantly outperforms state-of-the-art methods both quantitatively and visually. The source code will be publicly available at https://***/MantangGuo/CW4VS. Copyright © 2022, The Authors. All rights reserved.

关键词： Interpolation

Generative AI for Space-Air-Ground Integrated Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Ruichen Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Zhang, Ping Kim, Dong In The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The University of Sydney SydneyNSW2006 Australia The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Recently, generative AI technologies have emerged as a significant advancement in artificial intelligence field, renowned for their language and image generation capabilities. Meantime, space-air-ground integrated network (SAGIN) is an integral part of future B5G/6G for achieving ubiquitous connectivity. Inspired by this, this article explores an integration of generative AI in SAGIN, focusing on potential applications and case study. We first provide a comprehensive review of SAGIN and generative AI models, highlighting their capabilities and opportunities of their integration. Benefiting from generative AI’s ability to generate useful data and facilitate advanced decision-making processes, it can be applied to various scenarios of SAGIN. Accordingly, we present a brief survey on their integration, including channel modeling and channel state information (CSI) estimation, joint air-space-ground resource allocation, intelligent network deployment, semantic communications, image extraction and processing, security and privacy enhancement. Next, we propose a framework that utilizes a generative diffusion model (GDM) to construct channel information map to enhance quality of service for SAGIN. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we discuss potential research directions for generative AI-enabled SAGIN. © 2023, CC BY.

关键词： Generative adversarial networks

A new sensor bias-driven spatio-temporal fusion model based on convolutional neural networks

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第4期63卷 24-39页

作者： Yunfei LI Jun LI Lin HE Jin CHEN Antonio PLAZA Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation School of Geography and Planning Sun Yat-sen University School of Automation Science and Engineering South China University of Technology State Key Laboratory of Earth Surface Processes and Resource Ecology Institute of Remote Sensing Science and Engineering Faculty of Geographical ScienceBeijing Normal University Hyperspectral Computing Laboratory Department of Technology of Computers and CommunicationsEscuela Politécnica University of Extremadura

Owing to the tradeoff between scanning swath and pixel size, currently no satellite Earth observation sensors are able to collect images with high spatial and temporal resolution simultaneously. This limits the application of satellite images in many fields, including the characterization of crop yields or the detailed investigation of human-nature interactions. Spatio-temporal fusion(STF) is a widely used approach to solve the aforementioned problem. Traditional STF methods reconstruct fine-resolution images under the assumption that changes are able to be transferred directly from one sensor to another. However, this assumption may not hold in real scenarios, owing to the different capacity of available sensors to characterize changes. In this paper, we model such differences as a bias, and introduce a new sensor bias-driven STF model(called Bia STF) to mitigate the differences between the spectral and spatial distortions presented in traditional methods. In addition, we propose a new learning method based on convolutional neural networks(CNNs) to efficiently obtain this bias. An experimental evaluation on two public datasets suggests that our newly developed method achieves excellent performance when compared to other available approaches.

关键词： spatio-temporal fusion(STF) convolutional neural networks(CNNs) sensor bias-driven STF

Channel pruning via automatic structure search 29

学校读者我要写书评

暂无评论

Channel pruning via automatic structure search

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Lin, Mingbao Ji, Rongrong Zhang, Yuxin Zhang, Baochang Wu, Yongjian Tian, Yonghong Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University China School of Automation Science and Electrical Engineering Beihang University China Co. Ltd China School of Electronics Engineering and Computer Science Peking University Beijing China

ISBN: (纸本)9780999241165

Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/optimization or regularization based on rule-of-thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did. To solve the intractably huge combinations of pruned structure for deep networks, we first propose to shrink the combinations where the preserved channels are limited to a specific space, thus the combinations of pruned structure can be significantly reduced. And then, we formulate the search of optimal pruned structure as an optimization problem and integrate the ABC algorithm to solve it in an automatic manner to lessen human interference. ABCPruner has been demonstrated to be more effective, which also enables the fine-tuning to be conducted efficiently in an end-to-end manner. The source codes can be available at https://***/lmbxmu/ABCPruner. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Deep neural networks

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

Multiple-pilot collaboration for advanced remote intervention using reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Ziwei Bai, Weibang Chen, Zhang Xiao, Bo Liang, Bin Yeatman, Eric M. Department of Bioengineering Imperial College London London United Kingdom Department of Computing Imperial College London London United Kingdom Department of Automation Tsinghua University Beijing China Department of Electrical and Electronic Engineering Imperial College London London United Kingdom

—The traditional master-slave teleoperation relies on human expertise without correction mechanisms, resulting in excessive physical and mental workloads. To address these issues, a co-pilot-in-the-loop control framework is investigated for cooperative teleoperation. A deep deterministic policy gradient (DDPG) based agent is realised to effectively restore the master operators’ intents without prior knowledge on time delay. The proposed framework allows for introducing an operator (i.e., copilot) to generate commands at the slave side, whose weights are optimally assigned online through DDPG-based arbitration, thereby enhancing the command robustness in the case of possible human operational errors. With the help of interval type-2 (IT2) Takagi–Sugeno (T-S) fuzzy identification, force feedback can be reconstructed at the master side without a sense of delay, thus ensuring the telepresence performance in the force-sensor-free scenarios. Two experimental applications validate the effectiveness of the proposed framework. © 2021, CC BY-NC-SA.

关键词： Time delay

A Scalable Test Problem Generator for Sequential Transfer Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xue, Xiaoming Yang, Cuie Feng, Liang Zhang, Kai Song, Linqi Tan, Kay Chen The Department of Computer Science City University of Hong Kong Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The College of Computer Science Chongqing University Chongqing400044 China The Civil Engineering School Qingdao University of Technology Qingdao266520 China The Department of Computing Hong Kong Polytechnic University Hong Kong

Sequential transfer optimization (STO), which aims to improve the optimization performance on a task of interest by exploiting the knowledge captured from several previously-solved optimization tasks stored in a database, has been gaining increasing research attention over the years. However, despite the remarkable advances in algorithm design, the development of a systematic benchmark suite for comprehensive comparisons of STO algorithms received far less attention. Existing test problems are either simply generated by assembling other benchmark functions or extended from specific practical problems with limited scalability. The relationships between the optimal solutions of the source and target tasks in these problems are also often manually configured, limiting their ability to model different similarity relationships presented in real-world problems. Consequently, the good performance achieved by an algorithm on these problems might be biased and hard to be generalized to other problems. In light of the above, in this study, we first introduce four concepts for characterizing STO problems and present an important problem feature, namely similarity distribution, which quantitatively delineates the relationship between the optima of the source and target tasks. Then, we present the general design guidelines of STO problems and a particular STO problem generator with good scalability. Specifically, the similarity distribution of a problem can be easily customized, enabling a continuous spectrum of representation of the diverse similarity relationships of real-world problems. Lastly, a benchmark suite with 12 STO problems featured by a variety of customized similarity relationships is developed using the proposed generator, which would serve as an arena for STO algorithms and provide more comprehensive evaluation results. The source code of the problem generator is available at htt s://ithub com/Xmin Hsueh/STOP-G. Copyright © 2023, The Authors. All rights reserved.

关键词： Scalability

The Combination of Two Control Strategies for Series Hybrid Electric Vehicles

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第2期6卷 596-608页

作者： Can Luo Zhen Shen Simos Evangelou Gang Xiong Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Cloud Computing Center Chinese Academy of Sciences IEEE Department of Electrical and Electronic Engineering Imperial College London Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Qingdao Academy of Intelligent Industries

With most countries paying attention to the environment protection, hybrid electric vehicles have become a focus of automobile research and development due to the characteristics of energy saving and low emission. Power follower control strategy(PFCS) and DC-link voltage control strategy are two sorts of control strategies for series hybrid electric vehicles(HEVs). Combining those two control strategies is a new idea for control strategy of series hybrid electric vehicles. By tuning essential parameters which are the defined constants under DClink voltage control and under PFCS, the points of minimum mass of equivalent fuel consumption(EFC) corresponding to a series of variables are marked for worldwide harmonized light vehicles test procedure(WLTP). The fuel economy of series HEVs with the combination control schemes performs better compared with individual control scheme. The results show the effects of the combination control schemes for series HEVs driving in an urban environment.

关键词： DC-Link voltage control power follower control strategy series hybrid electric vehicles tuning

Parallel mining operating systems: From digital twins to mining intelligence 1

学校读者我要写书评

暂无评论

Parallel mining operating systems: From digital twins to min...

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Chen, Long Hu, Xiaoming Wang, Ge Cao, Dongpu Li, Lingxi Wang, Fei-Yue Sun Yat-sen University Guangzhou510006 China Waytous Inc. Qingdao266109 China College of Intelligence and Computing Tianjin University Tianjin300350 China Institute of Systems Engineering Macau University of Science and Technology 999078 China Indiana University-Purdue University ECE Department IndianapolisIN46202 United States Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781665433372

With the rapid development and modernization requirement of global coal industry, there is an emerging need for intelligent and unmanned mining systems. In this paper, the Intelligent Mining Operating System (IMOS) is proposed and developed, based on the parallel management and control of mining operating infrastructure that integrates the intelligent mining theory, the ACP-based (Artificial societies, Computational experiments, Parallel execution) parallel intelligence approaches, and the new generation of artificial intelligence (AI) technologies. To satisfy the intelligent and unmanned demand of open-pit mines, the IMOS architecture is developed by integrating the theory of digital quadruplets. The main subsystems and functions of IMOS are elaborated in detail, including a single-vehicle operating subsystem, multi-vehicle collaboration subsystem, vehicle-road collaboration subsystem, unmanned intelligent subsystem, dispatch management subsystem, parallel management and control subsystem, supervisory subsystem, remote takeover subsystem, and communication subsystem. The IMOS presented in this paper is the first integrated solution for intelligent and unmanned mines in China, and has been implemented over ten main open pits in the past few years. Its deployment and utilization will effectively improve the production efficiency and safety level of open-pit mines, promote the construction of ecological mines, and bring great significance to the realization of sustainable mining development. © 2021 IEEE.

关键词： Computation theory