检索结果-内蒙古大学图书馆

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Chen, Jiadong Ye, Hengyu Gao, Xiaofeng Wu, Fan Kong, Linghe Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783031466601

Event sequences play as a general fine-grained representation for temporal asynchronous event streams. However, in practice, event sequences are often fragmentary and incomplete with censored intervals or missing data, making it hard for downstream prediction and decision-making tasks. In this work, we propose a fresh extension on the definition of the temporal point process, which conventionally characterizes chronological prediction based on historical events, and introduce inverse point process that characterizes counter-chronological attribution based on future events. These two point process models allow us to impute missing events for one partially observed sequence with conditional intensities in two symmetric directions. We further design a peer imitation learning algorithm that lets two models cooperatively learn from each other, leveraging imputed sequences given by the counterpart as the supervised signal. The training process consists of iterative learning of two models and facilitates them to achieve a consensus. We conduct extensive experiments on both synthetic and real-world datasets, which demonstrate that our model can recover incomplete event sequences very close to the ground-truth, with averagely 49.40% improvement compared with related competitors measured by normalized optimal transport distance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

ELA: A Time-Series Forecasting Model for Liner Shipping Based on EMD-LSTM and Attention 11th

ELA: A Time-Series Forecasting Model for Liner Shipping Bas...

引用

11th International Conference on Computational Data and Social Networks, CSoNet 2022

作者： Chen, Jiadong Gao, Xiaofeng Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783031263026

The development of modern information technology has led to the digital and intelligent transformation of many traditional industries. In order to face the challenge of difficult transition, liner shipping industry is in urgent need of prediction methods for strategy adjustment, and much research remains to be done in this area. In our paper, we put forward a time-series forecasting model named ELA based on modified EMD-LSTM (Empirical Mode Decomposition and Long Short-Term Memory), AR (Autoregressive) and the attention mechanism. Tailored for handling the market characteristics of the liner shipping industry, our method effectively reduces the negative impact of noise on model training and learns the short-term dependencies and long-term trend in time series. Experiments on real-world liner shipping datasets show the powerful prediction performance of ELA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

BuckTracker: System for Multi Banknotes Tracking 1

BuckTracker: System for Multi Banknotes Tracking

引用

1st International Conference of Intelligent Methods, Systems and Applications, IMSA 2023

作者： Elbarrany, Abdullah Magdy Mosallam, Khaled Atia, Ayman Faculty of Computer Science Giza Egypt Helwan University HCI-LAB Faculty of Computers and Artificial Intelligence Giza Egypt

ISBN: (纸本)9798350335569

BuckTracker is a software that allows users to track their money transactions on a daily basis. Users scan cash banknotes using BuckTracker, which localizes each serial number, detects the currency denomination, and records the location of the scan. BuckTracker presents a novel solution for tracking money transactions, effectively enhancing transparency, accountability, and security in a wide range of financial operations. Users can track their transactions and retrieve the money in case of theft crimes. While the user is counting the money, the BuckTracker system scans each banknote, extracts its serial number, and detects the currency denomination. In this paper, two different object character recognition (OCR) techniques were experimented with in order to maximize the accuracy. The methodology used in this research improved previous work by enhancing the accuracy. The proposed system achieved an average accuracy of 92.3% on different data-sets, compared to a similar work that achieved 91.7% accuracy. © 2023 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

On Weighted Maximum Model Counting: Complexity and Fragments 36

On Weighted Maximum Model Counting: Complexity and Fragments

引用

36th IEEE International Conference on Tools with artificial intelligence, ICTAI 2024

作者： Bannach, Max Hecher, Markus Advanced Concepts Team European Space Agency Noordwijk Netherlands Computer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge United States

ISBN: (纸本)9798331527235

Maximum model counting (MAX#∃SAT) is a recently introduced extension of projected model counting (#∃SAT) that maximizes over a set of variables X the number of assignments over a set Y that can be extended to a satisfying assignment over Z. It is known that MAX#∃SAT also generalizes weighted #∃SAT and MAXSAT if weights are introduced to the problem. However, for the latter a non-trivial gadget is needed. We propose a more generic weighting scheme that evaluates a fitness term and a probability term simultaneously. In this setting, MAX#∃SAT extends weighted MAXSAT and #∃SAT without the need of gadgets. As MAXSAT is the canonical problem of cost-optimal reasoning and #∃SAT can be seen as canonical problem of probabilistic reasoning, MAX#3SAT with the proposed weighting scheme naturally fills the role as canonical problem for cost-optimal probabilistic reasoning. We study the problem from a complexity-theoretic point of view for unary weights and prove that the decision version is D2P- complete. We then focus on structural parameters and provide an ETH lower bound with respect to the inputs treewidth, as well as a treewidth-aware reduction from MAX#∃SAT to MAX#∃SAT. © 2024 IEEE.

关键词： max-sat sharp-sat treewidth

来源：评论

学校读者我要写书评

暂无评论

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding

Fast and High-Quality Auto-Regressive Speech Synthesis via S...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Bohan Wang, Hankun Zhang, Situo Guo, Yiwei Yu, Kai MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

The auto-regressive (AR) architecture, exemplified by models such as GPT, is extensively utilized in modern Text-to-Speech (TTS) systems. However, it often leads to considerable inference delays, primarily due to the challenges associated with next-token prediction in long speech sequences. In this work, we introduce VADUSA, one of the first approaches to accelerate AR-based TTS through speculative decoding. Our findings demonstrate that VADUSA not only delivers a significant reduction in inference time but also enhances TTS quality by employing draft heads to predict future speech tokens in an auto-regressive manner. Additionally, the incorporation of a tolerance mechanism during the sampling process further boosts performance, yielding approximately a 3× speedup in AR TTS. Moreover, our approach exhibits strong generalization across diverse datasets and various speech token types. © 2025 IEEE.

关键词： inference speedup speculative decoding text-to-speech

来源：评论

学校读者我要写书评

暂无评论

ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation 41

ACM-MILP: Adaptive Constraint Modification via Grouping and ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Guo, Ziao Li, Yang Liu, Chang Ouyang, Wenli Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China AI Lab Lenovo Research Beijing China

Data plays a pivotal role in the development of both classic and learning-based methods for Mixed-Integer Linear Programming (MILP). However, the scarcity of data in real-world applications underscores the necessity for MILP instance generation methods. Currently, these methods primarily rely on iterating random single-constraint modifications, disregarding the underlying problem structure with constraint interrelations, thereby leading to compromised quality and solvability. In this paper, we propose ACM-MILP, a framework for MILP instance generation, to achieve adaptive constraint modification and constraint interrelation modeling. It employs an adaptive constraint selection mechanism based on probability estimation within the latent space to preserve instance characteristics. Meanwhile, it detects and groups strongly related constraints through community detection, enabling collective modifications that account for constraint dependencies. Experimental results show significant improvements in problem-solving hardness similarity under our framework. Additionally, in the downstream task, we showcase the efficacy of our generated instances for hyperparameter tuning. Source code is available: https://***/Thinklab-SJTU/ACM-MILP. Copyright 2024 by the author(s)

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport 41

OT-CLIP: Understanding and Generalizing CLIP via Optimal Tra...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Shi, Liangliang Fan, Jack Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China Department of Computer Science University of North Carolina Chapel Hill United States

We propose to understand Contrastive Language-Image Pretraining model (CLIP) from the Optimal Transport (OT) perspective. Specifically, we show that training of CLIP is an embodiment of inverse OT and the adopted two InfoNCE losses in CLIP correspond to a special case of bilevel optimization of a modified entropic OT. We then generalize the original CLIP loss to an OT-based loss family using variants of Regularized OT (e.g. Fused Gromov OT, unbalanced OT, etc.), and show their superior performance on public datasets for downstream tasks in both image and text domain. We also rethink the inference stage of CLIP by using the tool of OT, and propose to adopt the fused Gromov OT for (zero-shot) classification, in which the prediction is based on the graph representation whereby images and texts are nodes for graph matching. By our new technique, we show how to generalize zero-shot classification to other more flexible zero-shot tasks with competitive performance: long-tailed classification and selective classification. The former assumes the known prior distribution of labels, while in the latter case, only a subset of samples are asked to predict, yet with the need of high prediction confidence. The code is available at https://***/fan23j/ICML2024-OT-CLIP. Copyright 2024 by the author(s)

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A Practical Predefined-Time Stability Criterion and Its Application to Uncertain Nonlinear Systems

引用

Journal of Systems science & Complexity 2024年第6期37卷 2556-2578页

作者： XU Hao YU Dengxiu SUI Shuai XU Bowen CHEN C.L.Philip Unmanned System Research Institute Northwestern Polytechnical UniversityXi'an 710072China College of Science Liaoning University of TechnologyJinzhou 121001China School of Artificial Intelligence Optics and ElectronicsNorthwestern Polytechnical UniversityXi'an 710072China School of Computer Science and Engineering South China University of Technology and Pazhou LabGuangzhou 510641China

In this paper,the singularity-free predefined-time fuzzy adaptive tracking control problem is studied for non-strict feedback(NSF)nonlinear systems considering mismatched external *** innovative practical predefined-time stability(PPTS)criterion is proposed to provide the theoretical basis for subsequent control *** to the existing predefined-time stability(PTS)criterion,this criterion has a broader application range and can solve the control design issues of nonlinear systems with system *** logic systems(FLSs)are employed to identify unknown nonlinear *** on the backstepping control technology,a singularity-free predefined-time control(PTC)design method is proposed,in which the hyperbolic tangent function is utilized to avoid the singular problem,and the nature of fuzzy basis function is adopted to resolve the algebraic loop *** PPTS of the closed-loop NSF nonlinear system is proven with the Lyapunov theory and the proposed PPTS ***,the efficiency of the presented PTC design method is verified by several sets of simulations on a single link manipulator system.

关键词： Fuzzy adaptive control nonlinear systems practical predefined-time stability predefinedtime control singularity-free control

来源：评论

学校读者我要写书评

暂无评论

MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness 41

MILP-FBGen: LP/MILP Instance Generation with Feasibility/Bou...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yahong Fan, Chenchen Chen, Donghui Li, Congrui Ouyang, Wenli Zhu, Mingda Yan, Junchi AI Lab Lenovo Research Beijing China School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China

Machine learning (ML) has been actively adopted in Linear Programming (LP) and Mixed-Integer Linear Programming (MILP), whose potential is hindered by instance *** synthetic instance generation methods often fall short in closely mirroring the distribution of original datasets or ensuring the feasibility and boundedness of the generated data - a critical requirement for obtaining reliable supervised labels in model *** this paper, we present a diffusion-based LP/MILP instance generative framework called *** strikes a balance between structural similarity and novelty while maintaining feasibility/boundedness via a meticulously designed structure-preserving generation module and a feasibility/boundedness-constrained sampling *** method shows superiority on two fronts: 1) preservation of key properties (hardness, feasibility, and boundedness) of LP/MILP instances, and 2) enhanced performance on downstream *** studies show two-fold superiority that our method ensures higher distributional similarity and 100% feasibility in both easy and hard datasets, surpassing current state-of-the-art techniques. Copyright 2024 by the author(s)

关键词： Mixed-integer linear programming

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：