检索结果-内蒙古大学图书馆

Conference on Computer vision and Pattern Recognition (CVPR)

作者： Jinxia Xie Bineng Zhong Zhiyi Mo Shengping Zhang Liangtao Shi Shuxiang Song Rongrong Ji Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University School of Computer Science and Technology Harbin Institute of Technology Media Analytics and Computing Lab School of Informatics Xiamen University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal information aggregation. Consequently, the spatio-temporal information is far away from being fully explored. To alleviate this issue, we propose an adaptive tracker with spatio-temporal transformers (named AQA-Track), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components. Firstly, we introduce a set of learnable and autoregressive queries to capture the instantaneous target appearance changes in a sliding window fashion. Then, we design a novel attention mechanism for the interaction of existing queries to generate a new query in current frame. Finally, based on the initial target template and learnt autoregressive queries, a spatio-temporal information fusion module (STM) is designed for spatiotemporal formation aggregation to locate a target object. Benefiting from the STM, we can effectively combine the static appearance and instantaneous changes to guide robust tracking. Extensive experiments show that our method significantly improves the tracker's performance on six popular tracking benchmarks: LaSOT, LaSOT ext , TrackingNet, GOT-10k, TNL2K, and UAV123. Code and models will be https://***/orgs/GXNU-ZhongLab.

关键词： Adaptation models Visualization Computer vision Target tracking Computational modeling Transformers Market research

来源：评论

学校读者我要写书评

暂无评论

Robust Bayesian optimization with reinforcement learned acquisition functions

arXiv

引用

arXiv 2022年

作者： Liu, Zijing Qu, Xiyao Liu, Xuejun Lyu, Hongqiang Ministry of Industry and Information Technology Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China College of Aerospace Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210023 China Key Laboratory of Aerodynamic Noise Control State Key Laboratory of Aerodynamics Mianyang621000 China

In Bayesian optimization (BO) for expensive black-box optimization tasks, acquisition function (AF) guides sequential sampling and plays a pivotal role for efficient convergence to better optima. Prevailing AFs usually rely on artificial experiences in terms of preferences for exploration or exploitation, which runs a risk of a computational waste or traps in local optima and resultant re-optimization. To address the crux, the idea of data-driven AF selection is proposed, and the sequential AF selection task is further formalized as a Markov decision process (MDP) and resort to powerful reinforcement learning (RL) technologies. Appropriate selection policy for AFs is learned from superior BO trajectories to balance between exploration and exploitation in real time, which is called reinforcement-learning-assisted Bayesian optimization (RLABO). Competitive and robust BO evaluations on five benchmark problems demonstrate RL's recognition of the implicit AF selection pattern and imply the proposal's potential practicality for intelligent AF selection as well as efficient optimization in expensive black-box problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset

arXiv

引用

arXiv 2024年

作者： Lian, Shijie Zhang, Ziyi Li, Hua Li, Wenjie Yang, Laurence Tianruo Kwong, Sam Cong, Runmin Hainan University China The Hong Kong University of Science and Technology Guangzhou China Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications Southeast University Ministry of Education China Huazhong University of Science and Technology China St. Francis Xavier University Canada LIngnan University School of Data Science Hong Kong Shandong University School of Control Science and Engineering China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China

With the breakthrough of large models, Segment Anything Model (SAM) and its extensions have been attempted to apply in diverse tasks of computer vision. Underwater salient instance segmentation is a foundational and vital step for various underwater vision tasks, which often suffer from low segmentation accuracy due to the complex underwater circumstances and the adaptive ability of models. Moreover, the lack of large-scale datasets with pixel-level salient instance annotations has impeded the development of machine learning techniques in this field. To address these issues, we construct the first large-scale underwater salient instance segmentation dataset (USIS10K), which contains 10,632 underwater images with pixel-level annotations in 7 categories from various underwater scenes. Then, we propose an Underwater Salient Instance Segmentation architecture based on Segment Anything Model (USIS-SAM) specifically for the underwater domain. We devise an Underwater Adaptive Visual Transformer (UA-ViT) encoder to incorporate underwater domain visual prompts into the segmentation network. We further design an out-of-the-box underwater Salient Feature Prompter Generator (SFPG) to automatically generate salient prompters instead of explicitly providing foreground points or boxes as prompts in SAM. Comprehensive experimental results show that our USIS-SAM method can achieve superior performance on USIS10K datasets compared to the state-of-the-art methods. Datasets and codes are released on Github. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Three-Variable and Five-Variable Weng-Zhang Algorithms of Different Traversal Types Applied to UKHP Prediction

Three-Variable and Five-Variable Weng-Zhang Algorithms of Di...

引用

Chinese Automation Congress (CAC)

作者： Yunong Zhang Yining Zhang Lilian Li School of Compute Science and Engineering Sun Yat-sen University Guangzhou China Research Institute of Sun Yat-sen University in Shenzhen Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Key Laboratory of Modern Control Technology Guangzhou China School of Artificial Intelligence Sun Yat-sen University Zhuhai China

ISBN: (纸本)9781665426480

UK hung parliament (UKHP) prediction is a concern. It may not only cause political issues, but also lead to troubles in other fields such as economics. It is important to make predictions on UKHP. In this paper, we use three-variable and five-variable Weng-Zhang algorithms (also termed addition- subtraction and frequency [ASF] algorithms) of different traversal types to predict the risky time-intervals and years of UKHP to give an early alert for avoidance. Experiment results show that 2021-2023, 2047-2068, and 2098-2104 are more potentially risky, and 2023, 2053, 2055, 2061, 2068, and 2098 have a greater risk for the occurrence of UKHP.

关键词： Economics Time-frequency analysis Automation Human factors Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Digital yard remote control solution for cement manufacturing based on Industrial IOT

Digital yard remote control solution for cement manufacturin...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Xiongjie Tao Hui Guo Caixu Xu Hubei Normal University Huangshi China Guangzhou ForceControl-Yuanhai IT Co. Ltd Guangdong China Faculty of Arts and Humanities Macao University of Science and Technology Macao China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China

With the development of artificial intelligence and the deep integration of digitalization and intelligent manufacturing. Aiming at the “raw material storage yard for raw material preparation in cement manufacturing” which still adopts the traditional manual control method for production, the realization of the digital storage yard not only improves the production efficiency, reduces the production cost of the enterprise, but also improves the working environment of the employees. Therefore, this paper uses IIoT technology and PLC control technology to digitally transform the site, and uses three-dimensional visualization technology to realize the simulation of intelligent equipment in the yard, and at the same time improves the security protection of production data. The realization shows that the remote control scheme of the digital yard based on the IIoT proposed in this paper is of great significance for the enterprise to realize the goal of intelligent, digital and safe production.

关键词： Solid modeling Computational modeling Process control Production Raw materials Data models Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-Query Oriented Continuous Subgraph Matching

Efficient Multi-Query Oriented Continuous Subgraph Matching

引用

International Conference on Data Engineering

作者： Ziyi Ma Jianye Yang Xu Zhou Guoqing Xiao Jianhua Wang Liang Yang Kenli Li Xuemin Lin School of Artificial Intelligence Hebei University of Technology China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University China Cyberspace Institute of Advanced Technology Guangzhou University China Department of New Networks PengCheng Laboratory China College of Computer Science and Electronic Engineering Hunan University China Shenzhen Research Institute Hunan University China Antai College of Economics and Management Shanghai Jiao Tong University China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Continuous subgraph matching (CSM) is a critical task for analyzing dynamic graphs and has a wide range of applications, such as merchant fraud detection, cyber-attack hunting, and rumor detection. Although many efficient CSM algorithms have been recently proposed, they are mainly designed to process a single query. However, in some application scenarios, multi-query oriented continuous subgraph matching (MQCSM) may be of more interest. To our knowledge, the two existing solutions to MQCSM are outdated due to unsatisfactory performance. In this paper, we propose MQ-Match, an efficient approach to MQCSM. First, we design a compact yet effective index structure CCG, which maintains the local matching result of vertices in the data graph using a directed graph. The directed edges in CCG can be utilized as an effective pruning rule for the subsequent incremental matching algorithm when expanding a partial match. Then, we develop a computation sharing incremental matching algorithm. In specific, a set of matching trees is constructed based on the depth-first search trees of the query graphs. By utilizing CCG, we conduct subgraph matching for the matching tree to collect the incremental matches for the query graphs, where the common structures of query graphs are matched only once. Extensive experiments show that MQ-Match can achieve 3.1x-7071.4x speedup over the competitors, and consumes much less memory under the majority of the experiment settings.

关键词： Heuristic algorithms Memory management Directed graphs Data engineering Fraud Computational efficiency Indexes

来源：评论

学校读者我要写书评

暂无评论

A Novel Coiled Cable-Conduit-Driven Hyper-Redundant Manipulator for Remote Operating in Narrow Spaces

A Novel Coiled Cable-Conduit-Driven Hyper-Redundant Manipula...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Mingrui Luo Yunong Tian En Li Minghao Chen Cunfeng Kang Guodong Yang Min Tan School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Engineering Laboratory of Industrial Vision and Intelligent Equipment Technology Chinese Academy of Sciences Beijing China Beijing-University of Technology Beijing China

Operating in narrow spaces is an important challenge in the development of robots. Redundant manipulators are one way to solve this problem, but their mechanism design and control method still have much room for improvement. In this paper, we propose a coiled cable-conduit-driven hyper-redundant manipulator (C-CDHRM) with great slenderness and flexibility. In terms of mechanism design, it considers both compactness and operability. By imitating the structure and behavior of a constricting snake, it can be uncoiled sequentially from a coiled storage state, led by the head. In terms of control methods, we propose a multi-layer control system that can make remote operations more accurate and reliable. On the one hand, guiding, segmenting, and following the path overcome the planning ambiguity caused by redundancy. On the other hand, conduit transmission modeling and cable length correction overcome the nonlinear mapping of cable-driven joints and were verified in experiments. Through tests, the mobile integrated system composed of C-CDHRM has an excellent performance in operation precision and accuracy, ensuring safety and accessibility in narrow spaces. Finally, in field experiments, the inspection and cleaning of various types of electrical equipment have been successfully completed, showing excellent application prospects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Coding Mode Prediction for Intra Prediction in VVC SCC

Fast Coding Mode Prediction for Intra Prediction in VVC SCC

引用

IEEE International Conference on Image Processing

作者： Dayong Wang Junyi Yu Xin Lu Frederic Dufaux Hongwei Guo Hui Guo Ce Zhu Chongqing Key Laboratory on Big Data for Bio Intelligence Chongqing University of Posts and Telecommunications Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Faculty of Computing Engineering and Media (CEM) De Montfort University Université Paris-Saclay CNRS CentraleSupélec Laboratoire des signaux et systèmes School of Engineering Honghe University Mengzi Yunnan China University of Electronic Science and Technology of China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Currently, screen content video applications are increasingly widespread in our daily lives. The latest Screen Content Coding (SCC) standard, known as Versatile Video Coding (VVC) SCC, employs screen content Coding Modes (CMs) selection. While VVC SCC achieves high coding efficiency, its coding complexity poses a significant obstacle to the further widespread adoption of screen content video. Hence, it is crucial to enhance the coding speed of VVC SCC. In this paper, we propose a fast mode and splitting decision for Intra prediction in VVC SCC. Specifically, we initially exploit deep learning techniques to predict content types for all CUs. Subsequently, we examine CM distributions of different content types to predict candidate CMs for CUs. We then introduce early skip and early terminate CM decisions for different content types of CUs to further eliminate unlikely CMs. Finally, we develop Block-based Differential Pulse-Code Modulation (BDPCM) early termination to improve coding speed. Experimental results demonstrate that the proposed algorithm can improve coding speed by $34.95 \%$ on average while maintaining almost the same coding efficiency.

关键词： Video coding Deep learning Image coding Modulation Prediction algorithms Complexity theory Copper

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Visual Speech Analysis: A Survey

arXiv

引用

arXiv 2022年

作者： Sheng, Changchong Kuang, Gangyao Bai, Liang Hou, Chenping Guo, Yulan Xu, Xin Pietikäinen, Matti Liu, Li China The National Key Laboratory of Electromagnetic Energy Naval University of Engineering China The College of Systems Engineering NUDT China The College of Liberal Arts and Sciences NUDT China The College of Intelligence Science and Technology NUDT China The Center for Machine Vision and Signal Analysis Oulu University Finland

Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment. As a powerful AI strategy, deep learning techniques have extensively promoted the development of visual speech learning. Over the past five years, numerous deep learning based methods have been proposed to address various problems in this area, especially automatic visual speech recognition and generation. To push forward future research on visual speech, this paper will present a comprehensive review of recent progress in deep learning methods on visual speech analysis. We cover different aspects of visual speech, including fundamental problems, challenges, benchmark datasets, a taxonomy of existing methods, and state-of-the-art performance. Besides, we also identify gaps in current research and discuss inspiring future research directions. © 2022, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Resource-Efficient Cooperative Online Scalar Field Mapping via Distributed Sparse Gaussian Process Regression

arXiv

引用

arXiv 2023年

作者： Ding, Tianyi Zheng, Ronghao Zhang, Senlin Liu, Meiqin The College of Electrical Engineering Zhejiang University Hangzhou310027 China The Jinhua Institute of Zhejiang University Jinhua321036 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi'an Jiaotong University Xi’an710049 China The National Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China

Cooperative online scalar field mapping is an important task for multi-robot systems. Gaussian process regression is widely used to construct a map that represents spatial information with confidence intervals. However, it is difficult to handle cooperative online mapping tasks because of its high computation and communication costs. This letter proposes a resource-efficient cooperative online field mapping method via distributed sparse Gaussian process regression. A novel distributed online Gaussian process evaluation method is developed such that robots can cooperatively evaluate and find observations of sufficient global utility to reduce computation. The error bounds of distributed aggregation results are guaranteed theoretically, and the performances of the proposed algorithms are validated by real online light field mapping experiments. Copyright © 2023, The Authors. All rights reserved.

关键词： Multipurpose robots

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：