检索结果-南通市图书馆

Expression Complementary Disentanglement Network for Facial Expression Recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第3期33卷 742-752页

作者： Shanmin WANG Hui SHUAI Lei ZHU Qingshan LIU college of Computer science and technology Nanjing University of Aeronautics and Astronautics college of Computer and Software Nanjing University of Information Science and Technology School of information and Control Nanjing University of Information Science and Technology

Disentangling facial expressions from other disturbing facial attributes in face images is an essential topic for facial expression *** methods only care about facial expression disentanglement(FED)itself,ignoring the negative effects of other facial *** to the annotations on limited facial attributes,it is difficult for existing FED solutions to disentangle all disturbance from the input *** solve this issue,we propose an expression complementary disentanglement network(ECDNet).ECDNet proposes to finish the FED task during a face reconstruction process,so as to address all facial attributes during *** from traditional reconstruction models,ECDNet reconstructs face images by progressively generating and combining facial appearance and matching *** designs the expression incentive(EIE) and expression inhibition(EIN) mechanisms,inducing the model to characterize the disentangled expression and complementary parts *** geometry and appearance,generated in the reconstructed process,are dealt with to represent facial expressions and complementary parts,*** combination of distinctive reconstruction model,EIE,and EIN mechanisms ensures the completeness and exactness of the FED *** results on RAF-DB,AffectNet,and CAER-S datasets have proven the effectiveness and superiority of ECDNet.

关键词： Geometry Image recognition Annotations Face recognition Task analysis Image reconstruction Facial features

Families of Schmidt-number witnesses for high dimensional quantum states

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2024年第8期76卷 44-51页

作者： Xian Shi college of information science and technology Beijing University of Chemical TechnologyBeijing 100029China

Higher dimensional entangled states demonstrate significant advantages in quantum information processing tasks. The Schmidt number is a quantity of the entanglement dimension of a bipartite state. Here we build families of k-positive maps from the symmetric information complete positive operator-valued measurements and mutually unbiased bases, and we also present the Schmidt number witnesses, correspondingly. At last, based on the witnesses obtained from mutually unbiased bases, we show the distance between a bipartite state and the set of states with a Schmidt number less than k.

关键词： Schmidt number entanglement witness mutually unbiased bases

维普期刊数据库

A New Random Sampling Method and Its Application in Improving Progressive BKZ Algorithm

在线全文

学校读者我要写书评

暂无评论

Journal of Systems science & Complexity 2024年第5期37卷 2262-2292页

作者： SUN Minghao WANG Shixiong CHEN Hao QU Longjiang college of sciences National University of Defense Technology Academy of Military sciences college of information science and technology/Cyber Security Jinan University

Random sampling algorithm was proposed firstly by Schnorr in 2003 to find short lattice vectors, as an alternative to enumeration. The follow-up developments in random sampling were mainly proposed by Fukase and Kashiwabara in 2015 and Aono and Nguyen in 2017. Although they extended the sampling space compared to Schnorr's work through the natural number representation, they did not show how to sample specifically in practice and what vectors should be sampled, in order to find short enough lattice vectors. In this paper, the authors firstly introduce a practical random sampling algorithm under some reasonable assumptions which can find short enough lattice vectors ***, as an application of this new random sampling algorithm, the authors show that it can improve the performance of progressive BKZ algorithm in practice. Finally, the authors solve the Darmstadt's Lattice Challenge and get a series of new records in the dimension from 500 to 825, using the improved progressive BKZ algorithm.

关键词： Darmstadt’s lattice challenge lattice lattice reduction algorithm post-quantum cryptography random sampling

A Distributed Adaptive Second-Order Latent Factor Analysis Model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2343-2345页

作者： Jialiang Wang Weiling Li Xin Luo the School of Computer science and technology Dongguan University of Technology the college of Computer and information science Southwest University

Dear Editor,This letter presents a distributed adaptive second-order latent factor(DAS) model for addressing the issue of high-dimensional and incomplete data representation. Compared with first-order optimizers, a second-order optimizer has stronger ability in approaching a better solution when dealing with the non-convex optimization problems, thus obtaining better performance in extracting the latent factors(LFs) well representing the known information from high-dimensional and incomplete data.

关键词： Particle swarm optimization (PSO)

IQABC-Based Hybrid Deployment Algorithm for Mobile Robotic Agents Providing Network Coverage

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua science and technology 2024年第2期29卷 589-604页

作者： Shuang Xu Xiaojie Liu Dengao Li Jumin Zhao college of Computer science and technology(college of Data science) Taiyuan University of TechnologyTaiyuan 030024China Pengcheng Laboratory Shenzhen 518055China college of information and Computer Taiyuan University of TechnologyTaiyuan 030024China

Working as aerial base stations,mobile robotic agents can be formed as a wireless robotic network to provide network services for on-ground mobile devices in a target ***,a challenging issue is how to deploy these mobile robotic agents to provide network services with good quality for more users,while considering the mobility of on-ground *** this paper,to solve this issue,we decouple the coverage problem into the vertical dimension and the horizontal dimension without any loss of optimization and introduce the network coverage model with maximum coverage ***,we propose a hybrid deployment algorithm based on the improved quick artificial bee *** algorithm is composed of a centralized deployment algorithm and a distributed *** proposed deployment algorithm deploy a given number of mobile robotic agents to provide network services for the on-ground devices that are independent and identically *** results have demonstrated that the proposed algorithm deploys agents appropriately to cover more ground area and provide better coverage uniformity.

关键词： wireless robotic networks network coverage deployment algorithm improved quick artificial bee colony

Tunable hexagonal boron nitride topological optical delay line in the visible region

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第5期22卷 124-130页

作者：费宏明武敏林瀚杨毅彪肖连团 college of Physics Taiyuan University of TechnologyTaiyuan 030024China college of information Engineering Shanxi Vocational University of Engineering Science and TechnologyJinzhong 030619China college of science RMIT UniversityMelbourneVictoria 3000Australia college of Electronic information and Optical Engineering Taiyuan University of TechnologyTaiyuan 030024China

Tunability,ultracompact design,high group index,low loss,and broad bandwidth are desired properties for integrated optical delay lines(ODLs).However,those properties are challenging to achieve simultaneously in the visible *** paper proposes a tunable hexagonal boron nitride topological optical delay line(ODL)in the visible region based on valley photonic *** topological edge state from the beard-type boundary allows the achievement of an ultralow group velocity close to zero,which results in a large group index of 629 at 645 ***,we demonstrate tuning of the slow-light wavelength and optical delay times with electrically tunable liquid crystals by applying external *** device has an ultracompact size of 5μm×2.7μm with an optical delay distance of 25a(a is the lattice constant)and a delay time of 12 *** design can provide a new possibility for designing ODLs working in the visible region for optical communication and quantum computing systems.

关键词： valley photonic crystal topological edge states optical delay lines

维普期刊数据库

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 965-981页

作者： Yong-Chao Li Rui-Sheng Jia Ying-Xiang Hu Hong-Mei Sun the college of Computer science and Engineering Shandong University of Science and TechnologyQingdao 266590 the Faculty of information science and Engineering Ocean University of ChinaQingdao 266000China the college of Computer science and Engineering Shandong University of Science and TechnologyQingdao 266590China the college of Computer science and Engineering Nanjing University of Science and TechnologyNanjing 210000China

In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation *** this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised *** this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the ***,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd *** addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density *** experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.

关键词： Crowd density estimation linear feature calibration vision transformer weakly-supervision learning

维普期刊数据库

Robust video question answering via contrastive cross-modality representation learning

在线全文

学校读者我要写书评

暂无评论

science China(information sciences) 2024年第10期67卷 211-226页

作者： Xun YANG Jianming ZENG Dan GUO Shanshan WANG Jianfeng DONG Meng WANG School of information science and technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center School of Computer science and information Engineering Hefei University of Technology Institutes of Physical science and information technology Anhui University School of Computer science and technology Zhejiang Gongshang University

Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.

关键词： video question answering cross-modality fusion contrastive learning cross-media reasoning

Bioinspired sensing-memory-computing integrated vision systems: biomimetic mechanisms, design principles, and applications

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(information sciences) 2024年第5期67卷 5-27页

作者： Yujie HUANG Yinlong TAN Yan KANG Yabo CHEN Yuhua TANG Tian JIANG Institute for Quantum information and State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology college of Advanced Interdisciplinary Studies National University of Defense Technology Institute for Quantum science and technology College of ScienceNational University of Defense Technology

With the explosion of sensory data in the Internet of Things(Io T) era, conventional machine vision systems are becoming increasingly difficult to meet the requirements of high efficiency, low energy consumption, and low latency due to their inherent shortcomings of separate sensing, memory, and computing units. Inspired by the retina and neuromorphic computing, the sensing-memory-computing integrated vision system(SMCVS) that features low power consumption, low latency, and high parallelism has been considered a promising technology to surpass the von Neumann architecture and realize strong artificial ***, novel materials like two-dimensional semiconductors and quantum dots with novel optoelectronic performance provide hardware carriers for implementing integrated sensing-memory-computing architectures,attracting considerable attention. This paper reviews the recent research progress in bioinspired vision systems in terms of biomimetic mechanisms, design principles, computational architectures, and ***, the biomimetic mechanisms are illustrated to guide the design of high-performance artificial visual perception systems. Then the research progress of optoelectronic-synapse-based bioinspired vision systems in the device principles and applications including image filtering, color recognition, visual adaptation, and motion detection are summarized. Finally, the challenges and future developing directions of the SMCVS are provided regarding bionic application, architecture design, and device fabrication.

关键词： sensing-memory-computing architecture neuromorphic computing retinomorphic device image recognition visual system