检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Sun, Wei Min, Xiongkuo Tu, Danyang Zhai, Guangtao Ma, Siwei The Institute of Image Communication and Information Processing Shanghai Jiao Tong University China The MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China The Institute of Digital Media School of Electronic Engineering and Computer Science Peking University Beijing100871 China

image quality assessment (IQA) is very important for both end-users and service providers since a high-quality image can significantly improve the user’s quality of experience (QoE) and also benefit lots of computer vision algorithms. Most existing blind image quality assessment (BIQA) models were developed for synthetically distorted images, however, they perform poorly on in-the-wild images, which are widely existed in various practical applications. In this paper, we propose a novel BIQA model for in-the-wild images by addressing two critical problems in this field: how to learn better quality-aware feature representation, and how to solve the problem of insufficient training samples in terms of their content and distortion diversity. Considering that perceptual visual quality is affected by both low-level visual features (e.g. distortions) and high-level semantic information (e.g. content), we first propose a staircase structure to hierarchically integrate the features from intermediate layers into the final feature representation, which enables the model to make full use of visual information from low-level to high-level. Then an iterative mixed database training (IMDT) strategy is proposed to train the BIQA model on multiple databases simultaneously, so the model can benefit from the increase in both training samples and image content and distortion diversity and can learn a more general feature representation. Experimental results show that the proposed model outperforms other state-of-the-art BIQA models on six in-the-wild IQA databases by a large margin. Moreover, the proposed model shows an excellent performance in the cross-database evaluation experiments, which further demonstrates that the learned feature representation is robust to images with diverse distortions and content. The code is available at https://***/sunwei925/StairIQA. Copyright © 2021, 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

Online Attentive Kernel-Based Temporal Difference Learning

arXiv

引用

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Robust Containment Control of Multi-agent Systems With Input Saturation

Observer-Based Robust Containment Control of Multi-agent Sys...

引用

Chinese Control Conference (CCC)

作者： Juan Qian Xiaoling Wang Guo-Ping Jiang Housheng Su College of Automation and College of Artificial Intelligence Nanjing University of Posts and Telecommunications and Jiangsu Engineering Lab for IOT Intelligent Robots(IOTRobot) Nanjing PR China School of Artificial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry ofChina Huazhong University of Science and Technology Wuhan PR China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

In this paper, the robust containment control problem of the leader-following multi-agent systems with input saturation and input additive disturbance is addressed, where the followers can be informed by multiple leaders. With the help of the lowand-high gain feedback technique and the high-gain observer approach, a distributed control algorithm for each agent is firstly designed by using the observed output information, then sufficient conditions are provided to guarantee the semi-global robust containment of the system. Finally, some numerical simulations are given to verify the correctness of the theoretical results.

关键词： Multi-agent systems Robustness Observers Electronic mail State feedback Additives

来源：评论

学校读者我要写书评

暂无评论

image Fusion Algorithm Based on Features Motivated Multi-Channel Pulse Coupled Neural Networks

Image Fusion Algorithm Based on Features Motivated Multi-Cha...

引用

International Conference on Bioinformatics and Biomedical Engineering (ICBBE)

作者： Xiaobo Qu Jingwen Yan 1Dept. of Communication Engineering Xiamen University.Fujian P.R.China 361005 1Dept. of Communication Engineering Xiamen University.Fujian P.R.China 3610052Key Lab of Digital Signal and Image Processing ofGuangdong Province Shantou University.Guangdong P.R.China 515063.

Pulse coupled neural networks (PCNN) is a mammal visual cortex-inspired artificial neural networks. Owing to the coupling links in neurons, PCNN is successful to utilize the local information, thus it has been successfully employed in image fusion. However, in traditional PCNN for image fusion, value of per pixel is used to motivate per neuron. In this paper, image feature of per pixel, e.g. gradient and local energy, is used to motivate per neuron and generate firing maps. Each firing map is corresponding to one type feature. Furthermore, a new multi-channel PCNN is presented to combine these firing maps via a weighting function which measures the contribution of these features to the fused image quality. Finally, pixels with maximum firing times, when firing times of source images are compared, are selected as the pixels of the fused image. Experimental results demonstrate that the proposed algorithm outperforms Wavelet- based and Wavelet-PCNN-based fusion algorithms.

关键词： image fusion Neural networks Neurons Pixel Discrete wavelet transforms image processing Artificial neural networks Fusion power generation Humans Pulse modulation

来源：评论

学校读者我要写书评

暂无评论

ReAL: Improving image-Text Retrieval with Authentic Negative Repository Learning

引用

ACM Transactions on Multimedia Computing, communications, and Applications 1000年

作者： Renjie Pan Hua Yang Xiangyu Zhao Institute of Image Communication and Network Engineering Shanghai Key Lab of Digital Media Processing and Transmission Shanghai Jiao Tong University China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China

Current methods for image-text retrieval commonly propose various fusion modules to achieve robust visual-textual alignment, primarily relying on in-batch learning to guide the matching process. Some follow-up methods seek to enlarge the number of negative samples to boost image-text contrastive learning. However, these methods often face challenges posed by semantic-consistent negatives, i.e., negatives samples that share correspondence with the ground truth, leading to confusion in learning cross-modal semantics. To address this issue, we propose a novel Retrieve with Authentic negative repository Learning (ReAL) method, which constructs a specific Authentic Negative Repository filled with valuable negative sample pairs. By introducing a Unique Negative Filter with a Discriminative Triplet Ranking Loss, ReAL effectively filters out the semantic-consistent negatives through similarity distribution analysis and threshold learning. Moreover, existing fusion paradigms suffer from intricate use of fine-grained representations from word- and region-level instances to progressively refine the fused embedding. In this paper, we propose a lightweight Cluster Refinement Module to exploit cross-modal semantics in a 1-way-1-out paradigm. Each visual-textual alignment can spontaneously uncover correlations with adjacent alignments through aggregation and re-allocation, without the need for a redundant and cost-inefficient refinement stage. Furthermore, ReAL employs dual momentum encoders with two memory banks, expanding the selection range of the Authentic Negative Repository to include a broader set of negatives. Extensive experiments conducted on Flickr30K, MS-COCO, and the augmented Flickr30K (with more hard negatives) demonstrate the superiority and robustness of ReAL, while also showcasing its significantly reduced inference time compared to other competitive baselines.

关键词： image-text Retrieval Authentic Negative Repository Cross-modal Fusion

来源：评论

学校读者我要写书评

暂无评论

Fast multiple reference frame selection algorithm based on H.264/AVC

引用

Sichuan Daxue Xuebao (Gongcheng Kexue Ban)/Journal of Sichuan University (Engineering Science Edition) 2005年第4期37卷 100-103页

作者： Teng, Guo-Wei Zhang, Zhao-Yang Zhang, Yi-Jun Zhang, Wen-Jun Key Lab. of Advanced Display and System Appl. Shanghai Univ. Shanghai 200072 China Inst. of Image Communication and Info. Processing Shanghai Jiaotong Univ. Shanghai 200030 China

A reference frame selection algorithm was proposed to fast determine the reference frames required by the current macroblock, which can avoid redundant reference frames. This algorithm can utilize the texture characteristic of sequence to estimate the possible number of reference frames, and further determine the best reference frame of 16 × 16, 8 × 8 and 4 × 4 modes according to the motion information and the monotony of RDO among different reference frames. So the likely reference frames of other modes may be adaptively chosen according to the correlation of reference frame selection with the above modes. The results showed that it can save about 30% of encoding time while maintaining nearly unchanged PSNR and bit-rate.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Neighborhood Interval Observer Based Coordination Control for Multi-agent Systems with Disturbances ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 10994-10999页

作者： Xiaoling Wang Guo-Ping Jiang Wen Yang Housheng Su Xiaofan Wang College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China and also with Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot) Nanjing 210023 China Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai 200237 China School of Artifcial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Luoyu Road 1037 Wuhan 430074 China Department of Automation Shanghai University Shanghai 200072 China

This paper focuses on multi-agent systems with uncertain disturbances, in which only the bounding functions on the disturbances and the bounds on the initial state of each agent are known. By designing a neighborhood interval observer for this kind of multi-agent system, the estimation of the sum of the relative state of each agent associated with itself and its neighbors is frstly realized. Then, on the basis of these estimated information, local control algorithm is designed to drive the system to achieve bounded consensus.

关键词： Multi-agent system disturbance neighborhood interval observer bounded consensus

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FULL-LENGTH-BODY CBCT IMAGING IN UPRIGHT POSITION WITH ROBOTIC-ARM SYSTEM: A SIMULATION STUDY

arXiv

引用

arXiv 2023年

作者： Lin, Tong Lyu, Tianling Wu, Zhan Xi, Yan Zhu, Wentao Chen, Yang Laboratory of Image Science and Technology Southeast University Nanjing China Research Center of Augmented Intelligence Zhejiang Lab Hangzhou China Shanghai First-Imaging Tech Shanghai China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

Upright position CT scans make it possible for full-length-body imaging at conditions more relevant to daily situations, but the substantial weight of the upright CT scanners increases the risks to floor’s stability and patients’ safety. Robotic-arm CBCT systems are supposed to be a better solution for this task, but such systems still face challenges including long scanning time and low reconstruction quality. To address the above challenges, this paper proposes a novel method to calculate optimal scanning pitch based on data completeness analysis, which can complete the whole-body scan in the shortest time without a significant decline in image quality. Besides, an FDK-style reconstruction method based on normalized projections is proposed to obtain fast image reconstruction. Extensive experiments prove the effectiveness of the proposed optimal scanning trajectory. Qualitative and quantitative comparisons with FDK and iterative algorithms show that the proposed reconstruction method can obtain high imaging quality with reasonable computation costs. The method proposed in this paper is expected to promote the application of robotic-arm CBCT systems in orthopedic functional analysis. © 2023, CC BY-NC-SA.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Full-Length-Body CBCT Imaging in Upright Position with Robotic-arm System: A Simulation Study

Full-Length-Body CBCT Imaging in Upright Position with Robot...

引用

IEEE International Symposium on Biomedical Imaging

作者： Tong Lin Tianling Lyu Zhan Wu Yan Xi Wentao Zhu Yang Chen Laboratory of Image Science and Technology Southeast University Nanjing China Research Center of Augmented Intelligence Zhejiang Lab Hangzhou China Shanghai First-Imaging Tech Shanghai China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

关键词： image quality Computed tomography Reconstruction algorithms Stability analysis Trajectory Safety Iterative methods

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：