检索结果-内蒙古大学图书馆

Deep Common Feature Mining for Efficient Video Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Yaoyan Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai201112 China Zhejiang Industrial Big Data and Robot Intelligent System Key Laboratory Hangzhou Innovation Institute Beihang University Hangzhou310051 China

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation process, underscore the need for further innovation. In response, we present Deep Common Feature Mining (DCFM), a novel approach strategically designed to address these challenges by leveraging the concept of feature sharing. DCFM explicitly decomposes features into two complementary components. The common representation extracted from a key-frame furnishes essential high-level information to neighboring non-key frames, allowing for direct re-utilization without feature propagation. Simultaneously, the independent feature, derived from each video frame, captures rapidly changing information, providing frame-specific clues crucial for segmentation. To achieve such decomposition, we employ a symmetric training strategy tailored for sparsely annotated data, empowering the backbone to learn a robust high-level representation enriched with common information. Additionally, we incorporate a self-supervised loss function to reinforce intra-class feature similarity and enhance temporal consistency. Experimental evaluations on the VSPW and Cityscapes datasets demonstrate the effectiveness of our method, showing a superior balance between accuracy and efficiency. The implementation is available at https://***/BUAAHugeGun/DCFM. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

Optimal Design of Work Quantification System 16th

学校读者我要写书评

暂无评论

Optimal Design of Work Quantification System

16th International Conference on intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2020

作者： Liu, Lei Lin, Wenru Huang, Yingcong Software College Minjiang University Fuzhou350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China School of Computer and Control Engineering Minjiang University Fuzhou350121 China

ISBN: (纸本)9789813367562

In view of the requirements of the correctness of quantitative results, the dynamic variety of quantitative rules and collaborative result recording in data management, the work quantification system is analyzed and optimized. The core module of the work quantification is designed by using the features of dynamic parsing script provided by JavaScript engine, and finally, a set of applicative, efficient, and expandable work quantification system is developed. The application of the system will bring convenience to all users due to its effective data management. In addition, easy access to the fast Internet makes the analysis and use of achievement data more efficient. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Information management

Denoi-SpEx+: A Speaker Extraction Network based Speech Dialogue System 17

学校读者我要写书评

暂无评论

Denoi-SpEx+: A Speaker Extraction Network based Speech Dialo...

17th IEEE International Conference on e-Business engineering, ICEBE 2021

作者： Hao, Yun Huang, Xiangkang Huang, Huichou Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Lab Guangzhou China University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9781665444187

The speech dialogue system has gradually been widely used in daily life. Users can consult and communicate with the system through natural language. However, in practical applications, third-person background sounds and background noise interference in real dialogue scenes will be encountered. The uncertainty and complexity of these background sounds will have a bad impact on the recognition of the system. A good speech enhancement module can help us to separate the target speaker from the original speech. Recently, a solution called SpEx+ was proposed from the time domain, but SpEx+ needs a reference speech to assist in training. This reference speech may have noise in actual applications that will affect performance. Therefore, we propose a Denoi-SpEx+ model. Before the reference speech is input to the network, a speech denoising network is added, so that the quality of speech separation in practical applications can be guaranteed. Experiments show that our model can significantly improve the performance of speech separation model of noisy reference speech. © 2021 IEEE.

关键词： Speech enhancement

Multiple Prior Representation Learning for Self-Supervised Monocular Depth Estimation via Hybrid Transformer

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Guodong Liu, Junjie Liu, Mingxuan Liu, Moyun Zhang, Yang School of Mechanical Engineering Hubei University of Technology Wuhan430068 China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing102628 China Hubei Key Laboratory of Modern Manufacturing Quality Engineering Hubei University of Technology Wuhan430068 China School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to capture the intricate details of the scene accurately. Prior information can potentially mitigate this issue, enhancing the model's understanding of scene structure and texture. Nevertheless, solely relying on a single type of prior information often falls short when dealing with complex scenes, necessitating improvements in generalization performance. To address these challenges, we introduce a novel self-supervised monocular depth estimation model that leverages multiple priors to bolster representation capabilities across spatial, context, and semantic dimensions. Specifically, we employ a hybrid transformer and a lightweight pose network to obtain long-range spatial priors in the spatial dimension. Then, the context prior attention is designed to improve generalization, particularly in complex structures or untextured areas. In addition, semantic priors are introduced by leveraging semantic boundary loss, and semantic prior attention is supplemented, further refining the semantic features extracted by the decoder. Experiments on three diverse datasets demonstrate the effectiveness of the proposed model. It integrates multiple priors to comprehensively enhance the representation ability, improving the accuracy and reliability of depth estimation. Codes are available at: https://***/MVME-HBUT/MPRLNet. © 2024, CC BY-NC-SA.

关键词： Textures

Multi-Agent Deep Reinforcement Learning based Collaborative Computation Offloading in Vehicular Edge Networks

学校读者我要写书评

暂无评论

Multi-Agent Deep Reinforcement Learning based Collaborative ...

International Conference on Distributed Computing Systems Workshop

作者： Hao Wang Huan Zhou Liang Zhao Xuxun Liu Victor C. M. Leung Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology China Three Gorges University Yichang China College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Recently, to cope with the long communication distance and unreliability of cloud-based computing architectures, mobile edge computing has emerged as a solution with great promise. This pattern extends cloud-based services towards the vehicular edge network and enables vehicular tasks to be offloaded to intermediate Roadside Units (RSUs) directly. However, as more and more tasks are offloaded to RSUs, the computation capacity of a single RSU becomes insufficient. Without edge cooperation, overall resource utilization and effectiveness are prone to being underutilized. To address this issue, this paper investigates a collaborative computation offloading scheme where adjacent RSUs can process offloaded tasks collaboratively rather than individually. First, we explore a vehicular edge network where the bilateral synergy between RSUs is leveraged. In particular, we incorporate a price-based incentive mechanism into the resource allocation process to promote overall resource utilization. Second, considering the time-varying system conditions and uncertain resource requirements, the optimization problem is approximated as a Markov Decision Process (MDP) and extended to a multi-agent system. Finally, we propose a Multi-agent Deep deterministic policy gradient-based computation Offloading and resource Allocation scheme (MDOA) to solve the corresponding problem. Simulation results show that the proposed MDOA can not only achieve a higher long-term utility of RSUs but also have better performance than other baselines in different scenarios.

关键词：

Electric Field Distribution Characteristics of Novel Fiber Sensor with Semiconductor Light Source 2

学校读者我要写书评

暂无评论

Electric Field Distribution Characteristics of Novel Fiber S...

2nd IEEE International Conference on Electronic Technology, Communication and Information, ICETCI 2022

作者： Jie, Huang Ni, Pengcheng Shuo, Chen Zhao, Xuyang Global Energy Internet Research Institute Changping Beijing China Elec. Pwr. Intelligent Sensing Technology and Application of State Grid Corporation Joint Laboratory Beijing China Anhui Jiyuan Software Co. Ltd Sgitg Hefei China North China Electric Power University School of Electrical and Electronic Engineering Changping Beijing China

ISBN: (数字)9781728181158

ISBN: (纸本)9781728181158

The light source element is an important part of the optical fiber sensor, and the selection of a suitable and reliable light-emitting element is critical factor for accurately measuring the parameters. The structural optimization of the optical fiber sensor semiconductor light source device is based on obtaining a more accurate field distribution. This paper analyzes the electric field distribution characteristics of a novel optical fiber sensor with semiconductor light source device by finite element method (FEM). The rationality of the electromagnetic shielding design of the model is verified by analyzing electric field distribution of the semiconductor light source device under different electromagnetic radiation conditions. © 2022 IEEE.

关键词： Finite element method

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

Pursuit-evasion differential games of players with different speeds in spaces of different dimensions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Shuai Wang, Chen Xie, Guangming The State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing100871 China The National Engineering Research Center of Software Engineering Peking University Beijing100871 China

We study pursuit-evasion differential games between a faster pursuer moving in 3D space and an evader moving in a plane. We first extend the well-known Apollonius circle to 3D space, by which we construct the isochron for the considered two players. Then both cases with and without a static target are considered and the corresponding optimal strategies are derived using the concept of isochron. In order to guarantee the optimality of the proposed strategies, the value functions are given and are further proved to be the solution of Hamilton-Jacobi-Isaacs equation. Simulations with comparison between the proposed strategies and other classical strategies are carried out and the results show the optimality of the proposed strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Game theory

Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Ziyuan Chen, Yingyu Wang, Zhiwen Shan, Hongming Chen, Yang Zhang, Yi College of Computer Science Sichuan University China Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University China School of Cyber Science and Engineering Sichuan University China School of Computer Science and Software Engineering Southwest Petroleum University China Institute of Science and Technology for Brain-inspired Intelligence Fudan University China School of Computer Science and Engineering Southeast University China

Reducing radiation doses benefits patients, however, the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) shows promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, raising privacy concerns. Federated learning (FL) has been introduced to address these privacy concerns;however, current methods are typically tailored to specific scanning protocols, which limits their generalizability and makes them less effective for unseen protocols. To address these issues, we propose SCAN-PhysFed, a novel SCanning- and ANatomy-level personalized Physics-Driven Federated learning paradigm for LDCT reconstruction. Since the noise distribution in LDCT data is closely tied to scanning protocols and anatomical structures being scanned, we design a dual-level physics-informed way to address these challenges. Specifically, we incorporate physical and anatomical prompts into our physics-informed hypernetworks to capture scanning- and anatomy-specific information, enabling dual-level physics-driven personalization of imaging features. These prompts are derived from the scanning protocol and the radiology report generated by a medical large language model (MLLM), respectively. Subsequently, client-specific decoders project these dual-level personalized imaging features back into the image domain. Besides, to tackle the challenge of unseen data, we introduce a novel protocol vector-quantization strategy Copyright © 2025, The Authors. All rights reserved.

关键词： Computerized tomography