检索结果-内蒙古大学图书馆

Time-aware bike flow prediction framework with dynamic edge fusion and memory integration

Knowledge-Based Systems 2025年 322卷

作者： M.Rajeh, Taha Li, Tianrui Luo, Zhpeng Javed, Muhammad Hafeez Alhaek, Fares School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Stirling College Chengdu University Chengdu610106 China Computing Science Faculty of Natural Sciences University of Stirling StirlingFK9 4LA United Kingdom

Bike-Sharing Systems (BSSs) have become a popular solution to urban sustainability concerns, providing affordable and environmentally friendly transportation. However, modeling and predicting shared-bike flow patterns are essential for developing intelligent transportation systems and facilitating city management. Despite the existence of several inflow and outflow prediction models, certain unresolved issues remain, including the inability to differentiate and capture heterogeneous dynamic relationships within daily flows, and the suboptimal utilization of historical flow data for forecasting. To address these limitations, we propose MVRC (Multi-View Relational Framework based on Clustering), a novel deep-learning framework for precise inflow and outflow prediction. The MVRC framework models three types of heterogeneous dynamic flow relationships during different periods of the day. Initially, we introduce a novel clustering method to group nearby stations exhibiting similar patterns, followed by creating a dynamic memory module to store and update edge attributes based on the time of day. Furthermore, the dynamic edge fusion mechanism effectively integrates heterogeneous, time-evolving flow features, capturing their varying impacts. To further enhance the model's capabilities, an offline component that leverages historical data is incorporated, improving performance during testing. Extensive experiments conducted on real datasets from New York City and Washington, D.C., demonstrate the superior prediction efficiency and framework effectiveness of the MVRC framework compared to existing state-of-the-art techniques. These results highlight the practicality and efficacy of MVRC in terms of prediction accuracy and stability. © 2025

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Size-invariance matters: rethinking metrics and losses for imbalanced multi-object salient object detection 24

Size-invariance matters: rethinking metrics and losses for i...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

arXiv

引用

arXiv 2025年

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian Key Laboratory of Network Fuzhou350002 China Computing and Intelligent Information Processing [Fuzhou University Fuzhou350116 China Department of Computer Science Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Informatics University of Oslo Oslo0316 Norway

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Automatically Labeling Aging Scenarios with a Machine Learning Approach 1

引用

24th International Conference on Human-Computer Interaction, HCII 2022

作者： An, Ning Xu, Yang Gao, Qinglin Zhu, Wenjie Wu, Aoran Chen, Honglin School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Shanghai Tianyu Senior Living Service Co. Ltd. Shanghai China School of Basic Courses Bengbu Medical College Bengbu China Management and Business Department Skidmore College Saratoga SpringsNY United States Department of Social Sciences University of Eastern Finland Kuopio70150 Finland

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

Older adults have diversified needs often associated with particular aging scenarios. People started to use aging scenarios to provide better Smart Eldercare services and develop innovative solutions. The problem is how to manage these scenarios effectively. To our best knowledge, this study is the first to develop a model to provide a structured framework of aging scenarios for research and teaching of eldercare services. Labeling aging scenarios can facilitate their collection, classification, and consolidation within this model. This study uses the automatic labeling approach to manage and utilize aging scenarios. Under each class, there are labels with different numbers and smaller granularity to reflect the requirements in each scenario case. Since a scenario case often involves more than one label, properly labeling it becomes a multi-label text classification problem. We extend the multi-label text classification model LSAN for labeling aging scenario cases. For evaluation purposes, we collected 938 scenario cases as the dataset. Experimental results show that our proposed method can achieve an average accuracy of 61.66%, better than other classical methods. © 2022, Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Graph-Order Optimization Algorithm Based on Equal-in-Space Distance Model for High-Resolution Image Matting

Graph-Order Optimization Algorithm Based on Equal-in-Space D...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Fujian Feng Han Huang Yihui Liang School of Software Engineering South China University of Technology Guangzhou China School of Data Science and Information Engineering Guizhou Minzu University Guiyang China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education Guangzhou China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China

ISBN: (纸本)9781665441506

Image matting is an essential image processing technology. optimized-based image matting methods can significantly improve the alpha matte quality of high-resolution images. However, the local information of the foreground may be similar to the background, which causes the inversion problem of the alpha matte in the single-point optimized. In this paper, we propose an image matting mathematical model of the equal-in-space distance. The model transforms the high-resolution image matting problem into several small-scale combinatorial optimization problems according to the similarity among pixel features. Inspired by spanning tree, we propose a graph-order optimization strategy, which generates the optimization sequence of small-scale optimization problems according to the edge weight among graph nodes. In addition, we designed a graph-order optimization algorithm based on optimized information transfer to solve each node in the graph. Experimental results show that the proposed model solves the alpha matte inversion problem of single-point optimization matting. Besides, the proposed algorithm outperforms the state-of-the-art optimization algorithms for the high-resolution image matting problem.

关键词： Cloud computing Image processing Image edge detection Conferences Computational modeling Transforms Information processing

来源：评论

学校读者我要写书评

暂无评论

Q&A driven conversational recommendation integrating multiple interest modeling

引用

Neurocomputing 2025年 647卷

作者： Haiping Zhu Yuqi Sun Shuwei Che Yan Chen School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an 710049 China

The conversational recommendation aims to provide users with recommendations in an interaction form of “System Ask-User Respond”. Existing studies rarely consider combining users’ multi-interest at the attribute level for preference modeling, and conduct inefficient conversational recommendation strategy learning, which affects the recommendation performance and conversation performance. To this end, we proposed a Q-A driven conversational recommendation method integrating multiple interest modeling. Specifically, we integrate the user’s positive and negative feedback to model a session dynamic graph, then use the signed graph convolutional network for graph representation learning, and we model multiple interest sequences based on the attention mechanism, then obtain the user interest state representation by fusing of sequence representations to solve the problem of insufficient user preference representation. Besides, we proposed a personalized decision space optimization method to narrow the range of action candidates and train the model with a multi-agent reinforcement learning method integrating hierarchical decision debiasing to solve the problem of poor conversational recommendation strategy learning effect. Experimental results on three public datasets, LastFM, Yelp, and Book, show that compared with existing conversational recommendation methods, our method demonstrates consistent performance improvement across all datasets. In addition, the results of ablation experiments verify the effectiveness of each component in our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noise-Tolerant Learning for Audio-Visual Action Recognition

arXiv

引用

arXiv 2022年

作者： Han, Haochen Zheng, Qinghua Luo, Minnan Miao, Kaiyao Tian, Feng Chen, Yan The National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an710049 China The School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Ministry of Education Xi’an710049 China The School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an710049 China

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. Despite the benefits brought by contrastive training, it would overfit the noisy correspondence and thus provide false supervision. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Furthermore, due to the lack of suitable datasets, we establish a benchmark of real-world noisy correspondence in audio-visual data by relabeling the Kinetics dataset. Extensive experiments on a wide range of noisy levels demonstrate that our method significant

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Graph convolutional module for temporal action localization in videos

arXiv

引用

arXiv 2021年

作者： Zeng, Runhao Huang, Wenbing Tan, Mingkui Rong, Yu Zhao, Peilin Huang, Junzhou Gan, Chuang The School of Software Engineering South China University of Technology The Pazhou Laboratory Guangzhou China China The School of Software Engineering South China University of Technology The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Tencent AI Laboratory Shenzhen China The MIT-IBM Watson AI Lab CambridgeMA02142 United States

Temporal action localization, which requires a machine to recognize the location as well as the category of action instances in videos, has long been researched in computer vision. The main challenge of temporal action localization lies in that videos are usually long and untrimmed with diverse action contents involved. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e., proposals in two-stage methods and segments in one-stage methods) and then perform action recognition/regression on each of them individually, without explicitly exploiting their relations during learning. In this paper, we claim that the relations between action units play an important role in action localization, and a more powerful action detector should not only capture the local content of each action unit but also allow a wider field of view on the context related to it. To this end, we propose a general graph convolutional module (GCM) that can be easily plugged into existing action localization methods, including two-stage and one-stage paradigms. To be specific, we first construct a graph, where each action unit is represented as a node and their relations between two action units as an edge. Here, we use two types of relations, one for capturing the temporal connections between different action units, and the other one for characterizing their semantic relationship. Particularly for the temporal connections in two-stage methods, we further explore two different kinds of edges, one connecting the overlapping action units and the other one connecting surrounding but disjointed units. Upon the graph we built, we then apply graph convolutional networks (GCNs) to model the relations among different action units, which is able to learn more informative representations to enhance action localization. Experimental results show that our GCM consistently improves the performance of existing action localization methods, including two-stage methods

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Single-path Bit Sharing for Automatic Loss-aware Model Compression

arXiv

引用

arXiv 2021年

作者： Liu, Jing Zhuang, Bohan Chen, Peng Shen, Chunhua Cai, Jianfei Tan, Mingkui The School of Software Engineering South China University of Technology China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China The School of Computer Science the University of Adelaide Australia The Faculty of Information Technology Monash University Australia The College of Computer Science and Technology Zhejiang University Hangzhou China

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct quantization based on the pruned model. However, this strategy may ignore that the pruning and quantization would affect each other and thus performing them separately may lead to sub-optimal performance. To address this, performing pruning and quantization jointly is essential. Nevertheless, how to make a trade-off between pruning and quantization is non-trivial. Moreover, existing compression methods often rely on some pre-defined compression configurations (i.e., pruning rates or bitwidths). Some attempts have been made to search for optimal configurations, which however may take unbearable optimization cost. To address these issues, we devise a simple yet effective method named Single-path Bit Sharing (SBS) for automatic loss-aware model compression. To this end, we consider the network pruning as a special case of quantization and provide a unified view for model pruning and quantization. We then introduce a single-path model to encode all candidate compression configurations, where a high bitwidth value will be decomposed into the sum of a lowest bitwidth value and a series of re-assignment offsets. Relying on the single-path model, we introduce learnable binary gates to encode the choice of configurations and learn the binary gates and model parameters jointly. More importantly, the configuration search problem can be transformed into a subset selection problem, which helps to significantly reduce the optimization difficulty and computation cost. In this way, the compression configurations of each layer and the trade-off between pruning and quantization can be automatically determined. Extensive experiments on CIFAR-100 and ImageNet show that SBS significantly reduces computation cost while achieving promising performance. For example, our SBS compressed MobileNetV2 achieves

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

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：