检索结果-内蒙古大学图书馆

ViGT: proposal-free video grounding with a learnable token in the transformer

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Multiparameter sensor based on the long-period fiber gratings inscribed in a pre-twisted polarization-maintaining fiber

引用

IEEE Sensors Journal 2025年第11期25卷 19315-19322页

作者： Chen, Siyu Jiang, Chen Ma, Yuehui Fan, Xiaolong Zhao, Yunhe Mou, Chengbo Liu, Yunqi Shanghai University Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering 99 Shangda Road Shanghai200444 China Nanjing210023 China Shanghai Maritime University Institute of Logistics Science and Engineering Shanghai201306 China

We demonstrate the fabrication of pre-twisted long-period fiber gratings (PT-LPFGs) in polarization-maintaining fibers (PMFs) using a CO2 laser. This technique leverages pre-twisted fibers combined with laser exposure, eliminating the need for precise alignment along the PMF axis, a key limitation of conventional single-side CO2 laser methods. The PT-LPFGs with the periods of 420 to 480 μm were successfully fabricated, achieving a maximum polarization-dependent loss (PDL) exceeding 20 dB at the resonance wavelength. The dual-dips resonance of the LP11 core mode was observed in the 1.0 μm wavelength band. Further chemical etching was applied to adjust the cladding mode resonance wavelength near the dispersion turning point (DTP). This adjustment enabled dual-dips resonance with LP14 and LP15 cladding modes along the PMF’s slow and fast axes, respectively, within the 2.0 μm wavelength band. The sensing performance of PT-LPFGs near the DTP was evaluated. Experimental results demonstrate that these gratings exhibit a high sensitivity of up to 14100 nm/RIU for the surrounding refractive index range of 1.448 to 1.457. Furthermore, the temperature and strain sensitivities were measured to be at 713 pm/°C and -49.4 pm/μΕ, respectively. These findings highlight the potential of PT-LPFGs for high-sensitivity fiber sensors, PDL compensators, and other advanced optical applications. © 2001-2012 IEEE.

关键词： Polarization-maintaining fiber

来源：评论

学校读者我要写书评

暂无评论

Graph Augmentation Empowered Contrastive Learning for Recommendation

引用

ACM Transactions on Information Systems 2025年第2期43卷 1-27页

作者： Xu, Lixiang Liu, Yusheng Xu, Tong Chen, Enhong Tang, Yuanyan School of Artificial Intelligence and Big Data Hefei University Hefei China State Key Laboratory of Cognitive Intelligence School of Computer Science and Technology University of Science and Technology of China Hefei China Zhuhai UM Science and Technology Research Institute FST University of Macau China

The application of contrastive learning (CL) to collaborative filtering (CF) in recommender systems has achieved remarkable success. CL-based recommendation models mainly focus on creating multiple augmented views by employing different graph augmentation methods and utilizing these views for self-supervised learning. However, current CL methods for recommender systems usually struggle to fully address the problem of noisy data. To address this problem, we propose the Graph Augmentation Empowered Contrastive Learning (GAECL) for recommendation framework, which uses graph augmentation based on topological and semantic dual adaptation and global co-modeling via structural optimization to co-create contrasting views for better augmentation of the CF paradigm. Specifically, we strictly filter out unimportant topologies by reconstructing the adjacency matrix and mask unimportant attributes in nodes according to the PageRank centrality principle to generate an augmented view that filters out noisy data. Additionally, GAECL achieves global collaborative modeling through structural optimization and generates another augmented view based on the PageRank centrality principle. This helps to filter the noisy data while preserving the original semantics of the data for more effective data augmentation. Extensive experiments are conducted on five datasets to demonstrate the superior performance of our model over various recommendation models. © 2025 Copyright held by the owner/author(s).

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Relative-Error-Dependent TOD Protocol for Cyber-Physical Systems under an Event-Triggered Communication

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 318-328页

作者： Yang, Hongchenyu Peng, Chen Tian, Engang Shanghai University School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Power Station Automation Technology Shanghai200444 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China

To deal with different data magnitudes or measurement units of different system nodes, a novel relative-error-dependent try-once-discard (RED-TOD) communication protocol with event-triggered detectors is proposed to improve the accuracy and reliability of node selection for band-limited cyber-physical systems. With the combined effect of the absolute error and the relative error, a novel node activation condition is proposed to comprehensively reflect and fairly compare node transmission requirements. Under such a stricter scheduling rule, the node selection is more accurate as required and the available communication bandwidth is utilized with higher efficiency. Moreover, periodic sampling module and event-triggered detectors are placed before RED-TOD scheduling scheme to deal with redundancy and inaccurate transmissions of the existing variable sampling scheme. Taking the proposed scheduling scheme and non-small network-induced delay into account, an impulsive closed-loop system model is well established. Sufficient criteria for input-to-state stabilization are derived by employing the Lyapunov-Krasovskii functional approach. A searching algorithm is also presented to co-design optimized scheduler parameters and controller gains. Furthermore, to avoid continuous calculations, the next transmission instant and the dormant period of the event-triggered detector are predicted according to the present information carried by each node. Finally, an illustrative example is employed to demonstrate the effectiveness and superiority of the proposed scheduling method. © 2023 IEEE.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

A reposition algorithm for e-hailing based on quantum annealing and intuitive reasoning

引用

Intelligent and Converged Networks 2024年第4期5卷 317-335页

作者： Chao Wang Yiyun Shi Sumin Wang Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai UniversityShanghai 200444China School of Information Engineering Ganzhou Key Laboratory of Cloud Computing and Big Data ResearchGannan University of Science and TechnologyGanzhou 341000China

Currently,the challenge lies in the traditional intelligent algorithm’s ability to effectively address the e-hailing repositioning *** identifying the underlying characteristics in extensive traffic data within a limited timeframe is difficult,ultimately preventing the achievement of the most optimal *** paper suggests a hybrid computing architecture involving reinforcement learning and quantum annealing based on intuitive *** reasoning aims to enhance performance in scenarios with poor system robustness,complex tasks,and diverse goals.A deep learning model is constructed,trained to extract scene features,and combined with expert knowledge,then transformed into a quantum annealable *** final strategy is obtained using a D-wave quantum computer with quantum tunneling effect,which helps in finding optimal solutions by jumping out of local suboptimal *** on 400000 real data,four algorithms are compared:minimum-cost flow,sequential markov decision process,hot-dot strategy,and driver-prefer *** average total revenue increases by about 10%and vehicle utilization by about 15%in various *** summary,the proposed architecture effectively solves the e-hailing reposition problem,offering new directions for robust artificial intelligence in big data decision problems.

关键词： intuitive reasoning reinforcement learning quantum annealing

来源：评论

学校读者我要写书评

暂无评论

3DGCformer: 3-Dimensional Graph Convolutional transformer for multi-step origin–destination matrix forecasting

引用

Applied Intelligence 2025年第6期55卷 1-18页

作者： Huang, Yiou Deng, Hao Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

Forecasting Human mobility is of great significance in the simulation and control of infectious diseases like COVID-19. To get a clear picture of potential future outbreaks, it is necessary to forecast multi-step Origin–Destination (OD) matrices for a relatively long period in the future. However, multi-step Origin–Destination Matrix Forecasting (ODMF) is a non-trivial problem. First, previous ODMF models only forecast the OD matrix for the next time-step, and they cannot perform well on long-term multi-step forecasts due to error accumulation. Second, many ODMF methods capture spatial and temporal dependencies with separate modules, which is insufficient to model spatio-temporal correlations in the time-varying OD matrix sequence. To address the challenges in multi-step ODMF, we propose 3-Dimensional Graph Convolutional Transformer (3DGCformer). As an enhancement of the original 3DGCN, we propose a novel Origin–Destination Feature Propagation (ODFP) rule between 3DGCN layers and integrate 2 3DGCNs with different spatio-temporal graphs and corresponding feature propagation rules to model the formation of OD flows in a more comprehensive way. For multi-step forecasts, 3DGCformer uses Transformer to capture long-term global temporal dependency, and adapt its decoder using labeled tokens to avoid error accumulation and improve time efficiency. To avoid information loss as the number of regions increases, we propose a patch embedding approach to convert data from 3DGCNs to the Transformer module. We perform extensive experiments on 4 real-world human mobility datasets, and the results show that our proposed model outperforms the state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Attack based on data: a novel perspective to attack sensitive points directly

引用

Cybersecurity 2024年第3期7卷 111-123页

作者： Yuyao Ge Zhongguo Yang Lizhe Chen Yiming Wang Chengyang Li School of Information Science and Technology North China University of TechnologyBeijingChina Bejing Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of TechnologyBeijingChina School of Computer Science Peking UniversityBeijingChina

Adversarial attack for time-series classification model is widely explored and many attack methods are *** there is not a method of attack based on the data *** this paper,we innovatively proposed a black-box sparse attack method based on data *** method directly attack the sensitive points in the time-series data accord-ing to statistical features extract from the *** frst,we have validated the transferability of sensitive points among DNNs with different ***,we use the statistical features extract from the dataset and the sensi-tive rate of each point as the training set to train the predictive ***,predicting the sensitive rate of test set by predictive ***,perturbing according to the sensitive *** attack is limited by constraining the LO norm to achieve one-point *** conduct experiments on several datasets to validate the effectiveness of this method.

关键词： Black-box adversarial attack Time series classification data mining

来源：评论

学校读者我要写书评

暂无评论

OSFS-Vague: Online streaming feature selection algorithm based on vague set

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1451-1466页

作者： Jie Yang Zhijun Wang Guoyin Wang Yanmin Liu Yi He Di Wu School of Physics and Electronic Science Zunyi Normal UniversityZunyiChina Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Computer Science Old Dominion UniversityNorfolkVirginiaUSA College of Computer and Information Science Southwest UniversityChongqingChina

Online streaming feature selection(OSFS),as an online learning manner to handle streaming features,is critical in addressing high-dimensional *** real big data-related applications,the patterns and distributions of streaming features constantly change over time due to dynamic data generation ***,existing OSFS methods rely on presented and fixed hyperparameters,which undoubtedly lead to poor selection performance when encountering dynamic *** make up for the existing shortcomings,the authors propose a novel OSFS algorithm based on vague set,named *** main idea is to combine uncertainty and three-way decision theories to improve feature selection from the traditional dichotomous method to the trichotomous ***-Vague also improves the calculation method of correlation between features and ***,OSFS-Vague uses the distance correlation coefficient to classify streaming features into relevant features,weakly redundant features,and redundant ***,the relevant features and weakly redundant features are filtered for an optimal feature *** evaluate the proposed OSFS-Vague,extensive empirical experiments have been conducted on 11 *** results demonstrate that OSFS-Vague outperforms six state-of-the-art OSFS algorithms in terms of selection accuracy and computational efficiency.

关键词： feature selection online feature selection three-way decision vague set

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Progressive and Multi-Prior-Guided Network for Image Inpainting

A Progressive and Multi-Prior-Guided Network for Image Inpai...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Peng, Bo Qiu, Yining Wu, Dong He, Liren Chi, Mingmin School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Deep learning techniques have recently made considerable progress in image inpainting by introducing prior knowledge, e.g. texture and structure. However, the existing methods still suffer from artefacts such as distorted texture and abrupt colors due to insufficient consideration of correlation between the prior visual features. In this paper, we propose a novel progressive and multi-prior-guided network (PMPN) for image inpainting inspired by the human painting process, which first constructs the sketch of painting art, then generates the corresponding textures finally fills the colors to the appropriate locations. In particular, to model the global multi-scale contexts during the reconstruction process, we design a bi-directional cross-stage perception module that captures spatial information across branches and stages and guides the model to synthesize a natural and consistent texture. Our proposed PMPN network is evaluated on three publicly available datasets, outperforming the current state-of-the-art models. © 2022 IEEE.

关键词： computer vision

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：