检索结果-内蒙古大学图书馆

Property Constrained Video Summarization via Regret Minimization

SN computer science 2024年第2期5卷 254页

作者： Xu, Yuyao Zheng, Jiping Tao, Yanxin Zhu, Kaiqin College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing 211106 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing 210023 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210016 China

Video summarization has become one of the most effective solutions for quickly understanding a large amount of video data. Video properties such as importance, diversity, representativeness, and storyness have been widely adopted for summarization based on kinds of features of video frames. To fully exploit these properties, in this paper, we propose a property constrained video summarization framework to output fixed-size summaries based on the concept of regret minimization which is popular in the database community for solving multi-criteria decision-making problems. Our framework first uses representativeness property and effective techniques to generate a candidate frame set. Then, the candidate set is transformed into a multi-dimensional point set where dimensions are composed of entities of the importance property and the diversity property. Moreover, our framework runs the regret minimization query on the point set to output a summary. To further improve the quality of the output summary, the property storyness is exploited to add frames satisfying the size constraint. Experimental results on the benchmark datasets demonstrate the effectiveness and superiority of our framework. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Multiple properties Regret minimization Video summarization

来源：评论

学校读者我要写书评

暂无评论

AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models 38

AP-Adapter: Improving Generalization of Automatic Prompts on...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Fu, Yuchen Jiang, Zhiwei Liu, Yuliang Wang, Cong Deng, Zexuan Chen, Zhaoling Gu, Qing State Key Laboratory for Novel Software Technology Nanjing University China

Recent advancements in Automatic Prompt Optimization (APO) for text-to-image generation have streamlined user input while ensuring high-quality image output. However, most APO methods are trained assuming a fixed text-to-image model, which is impractical given the emergence of new models. To address this, we propose a novel task, model-generalized automatic prompt optimization (MGAPO), which trains APO methods on a set of known models to enable generalization to unseen models during testing. MGAPO presents significant challenges. First, we experimentally confirm the suboptimal performance of existing APO methods on unseen models. We then introduce a two-stage prompt optimization method, AP-Adapter. In the first stage, a large language model is used to rewrite the prompts. In the second stage, we propose a novel method to construct an enhanced representation space by leveraging inter-model differences. This space captures the characteristics of multiple domain models, storing them as domain prototypes. These prototypes serve as anchors to adjust prompt representations, enabling generalization to unseen models. The optimized prompt representations are subsequently used to generate conditional representations for controllable image generation. We curate a multi-modal, multi-model dataset that includes multiple diffusion models and their corresponding text-image data, and conduct experiments under a model generalization setting. The experimental results demonstrate the AP-Adapter's ability to enable the automatic prompts to generalize well to previously unseen diffusion models, generating high-quality images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sample Efficiency Matters: Training Multimodal Conversational Recommendation Systems in a Small Data Setting 24

Sample Efficiency Matters: Training Multimodal Conversationa...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Su, Haoyang Du, Wenzhe Wang, Xiaoliang Nguyen, Cam-Tu State Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9798400706868

With the increasing prevalence of virtual assistants, multimodal conversational recommendation systems (multimodal CRS) becomes essential for boosting customer engagement, improving conversion rates, and enhancing user satisfaction. Yet conversational samples, as training data for such a system, are difficult to obtain in large quantities, particularly in new platforms. To effectively train multimodal CRS in a small data setting, we enhance data quality to make up for the small data quantity by augmenting conversations with dialogue states. We then devise an effective dialogue state encoder to bridge the semantic gap between conversation and product representations for recommendation. To further reduce the cost of dialogue state annotation, a semi-supervised learning method is developed to effectively train the dialogue state encoder with a small set of labeled conversations. In addition, we design a correlation regularisation that leverages knowledge in the multimodal product database to help align textual and visual modalities. Experiments on the dataset MMD demonstrate the effectiveness of our method. Particularly, with only 5% of the MMD training set, our method (namely SeMANTIC) obtains better NDCG scores than those of baseline models trained on the full MMD training set. © 2024 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A path planning method based on deep reinforcement learning for crowd evacuation

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第6期15卷 2925-2939页

作者： Meng, Xiangdong Liu, Hong Li, Wenhao School of Information Science and Engineering Shandong Normal University Jinan250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250014 China

Deep reinforcement learning (DRL) is suitable for solving complex path-planning problems due to its excellent ability to make continuous decisions in a complex environment. However, the increase in the population size in the crowd evacuation path-planning problem causes a substantial computational burden for the algorithm, which leads to an unsatisfactory efficiency of the current DRL algorithm. This paper presents a path planning method based on DRL for crowd evacuation to solve the problem. First, we divide crowds into groups based on their relationship and distance from each other and select leaders from them. Next, we expand the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to propose an Optimized Multi-Agent Deep Deterministic Policy Gradient (OMADDPG) algorithm to obtain the global evacuation path. The OMADDPG algorithm uses the Cross-Entropy Method (CEM) to optimize policy and improve the neural network’s training efficiency by applying the Data Pruning (DP) algorithm. In addition, the social force model is improved, incorporating the relationship between individuals and psychological factors into the model. Finally, this paper combines the improved social force model and the OMADDPG algorithm. The OMADDPG algorithm transmits the path information to the leaders. Pedestrians in the environment are driven by the improved social force model to follow the leaders to complete the evacuation simulation. The method can use a leader to guide pedestrians safely arrive the exit and reduce evacuation time in different environments. The simulation results prove the efficiency of the path planning method. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via multiple graph fusion and feature weight learning

引用

science China(Information sciences) 2023年第5期66卷 56-72页

作者： Chang TANG Xiao ZHENG Wei ZHANG Xinwang LIU Xinzhong ZHU En ZHU School of Computer Science China University of Geosciences State Key Laboratory for Novel Software Technology Nanjing University School of Computer National University of Defense Technology National Supercomputing Center in Jinan Qilu University of Technology (Shandong Academy of Sciences) College of Mathematics Physics and Information Engineering Zhejiang Normal University

Unsupervised feature selection attempts to select a small number of discriminative features from original high-dimensional data and preserve the intrinsic data structure without using data labels. As an unsupervised learning task, most previous methods often use a coefficient matrix for feature reconstruction or feature projection, and a certain similarity graph is widely utilized to regularize the intrinsic structure preservation of original data in a new feature space. However, a similarity graph with poor quality could inevitably afect the final results. In addition, designing a rational and efective feature reconstruction/projection model is not easy. In this paper, we introduce a novel and efective unsupervised feature selection method via multiple graph fusion and feature weight learning（MGF2WL） to address these issues. Instead of learning the feature coefficient matrix, we directly learn the weights of diferent feature dimensions by introducing a feature weight matrix, and the weighted features are projected into the label space. Aiming to exploit sufficient relation of data samples, we develop a graph fusion term to fuse multiple predefined similarity graphs for learning a unified similarity graph, which is then deployed to regularize the local data structure of original data in a projected label space. Finally, we design a block coordinate descent algorithm with a convergence guarantee to solve the resulting optimization problem. Extensive experiments with sufficient analyses on various datasets are conducted to validate the efficacy of our proposed MGF2WL.

关键词： unsupervised feature selection graph fusion feature weight learning local structure preservation

来源：评论

学校读者我要写书评

暂无评论

Robust and Effort-Efficient Image-Based Indoor Localization With Generative Features

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6394-6412页

作者： Zhu, Zhenhan Zhao, Yanchao Tang, Maoxing Bu, Yanling Han, Hao Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing211106 China Nanjing University State KeyLab. for Novel Software Technology Nanjing210093 China

Image-based indoor localization using smartphones has become popular, leveraging visual landmarks and fingerprint extraction for localization. Fingerprint density significantly affects accuracy, but collecting dense, high-resolution fingerprints during on-site surveys is labor-intensive and incurs high computation/storage costs during matching. Additionally, efficient fingerprint extraction often constrains users to specific shooting poses, with deviations markedly reducing localization accuracy. To address these challenges, we introduce ARGILS, an Automated Real-time Generative Image Localization System. The key idea is to use cross sparse sampling instead of dense sampling, generate fingerprint features for missing locations, and quickly match locations through feature orthogonal decomposition. Cross sparse sampling ensures full coverage of scene features and helps to generate missing fingerprints. To maintain high localization resolution with sparse sampling, we designed a distance-constrained generative adversarial network to generate fingerprints for unsampled locations. Additionally, we developed an orthogonal fingerprint extraction method to decompose image features into horizontal and vertical directions in 2D space. To improve robustness against obstacles, we implemented a scanning localization scheme using key frame filtering and clustering. We have implemented ARGILS and performed extensive real-world evaluations. Experiment results show that when reducing 75% site survey effort, the average location error of ARGILS is around 2.5m in a shopping mall, 48% higher than state-of-the-art methods. ARGILS can also efficiently speed up localization process, with the time consumption ranging from 0.1 to 0.3 seconds on smartphones of various configurations. © 2002-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

SyNet:Medical image anomaly detection with noise synthesis network 10

SyNet:Medical image anomaly detection with noise synthesis n...

引用

10th IEEE Conference on Big Data Security on Cloud, BigDataSecurity 2024

作者： Liu, Jingnian Liang, Wei Chen, Yuxiang Jin, Kai Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Xiangtang China

ISBN: (纸本)9798350389524

Medical image anomaly detection refers to machine learning techniques to analyze and identify lesions and abnormalities in them. However, in medical images, anomaly samples are usually sparse, which can lead to supervised learning not being able to obtain sufficient training. While existing unsupervised learning is mainly based on reconstruction and generation as well as feature embedding, these methods do not take into account the problem of data type bias during domain migration and often face the problem of loose judgment boundaries. To this end, this paper proposes a novel unsupervised learning method, SyNet, based on noisy anomaly synthesis. First, the problem at domain migration is well solved by aggregating the range of features within the feature map, fusing the multiscale features at the intermediate level, and adding feature adapters. Then, anomaly samples are synthesized by adding noise in the feature space, which is more efficient and stable than generating samples in the image space. Finally, normal and abnormal data are distinguished by training the discriminator. In this paper, experiments are conducted on ISIC and brain MRI datasets, and SyNet achieves nearly 20% improvement in AUC, ACC and other metrics compared with the current mainstream methods, and also has good inference efficiency. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution 38

IODA: Instance-Guided One-shot Domain Adaptation for Super-R...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tang, Zai-Zuo Yang, Yu-Bin State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

The domain adaptation method effectively mitigates the negative impact of domain gaps on the performance of super-resolution (SR) networks through the guidance of numerous target domain low-resolution (LR) images. However, in real-world scenarios, the availability of target domain LR images is often limited, sometimes even to just one, which inevitably impairs the domain adaptation performance of SR networks. We propose Instance-guided One-shot Domain Adaptation for Super-Resolution (IODA) to enable efficient domain adaptation with only a single unlabeled target domain LR image. To address the limited diversity of the target domain distribution caused by a single target domain LR image, we propose an instance-guided target domain distribution expansion strategy. This strategy effectively expands the diversity of the target domain distribution by generating instance-specific features focused on different instances within the image. For SR tasks emphasizing texture details, we propose an image-guided domain adaptation method. Compared to existing methods that use text representation for domain difference, this method utilizes pixel-level representation with higher granularity, enabling efficient domain adaptation guidance for SR networks. Finally, we validate the effectiveness of IODA on multiple datasets and various network architectures, achieving satisfactory one-shot domain adaptation for SR networks. Our code is available at https://***/ZaizuoTang/IODA. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Framework for Pedestrian Tracking and Counting Based on DeepSORT 20th

An Improved Framework for Pedestrian Tracking and Counting...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Tao, Yanxin Zheng, Jiping College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9789819970247

Due to the rapid growth in the demand for crowd analysis and monitoring methods, there is an urgent need for pedestrian tracking and counting methods that are more efficient, accurate, and reliable. However, the existing trackers and counters rarely have the three characteristics of efficiency, accuracy and reliability simultaneously. Therefore, we propose a framework named FR-DeepSORT for tracking and counting pedestrians based on DeepSORT. FR-DeepSORT first selects the YOLOv5 network as the object detector. Then the Re-ID information is combined with IoU to construct a cost matrix to improve the tracker by introducing FastReID. Finally, FR-DeepSORT introduces vector cross product and combines the tracking results to monitor the pedestrian crossing dynamics. The experimental results on the MOT tracking benchmark datasets show that the accuracy of our tracker is 89.38%, and the IDF1 value is 82.45%, which are competitive and more reliable to existing tracking methods. The counter error rate is also superior in the real-time dynamic statistical accuracy of the crowd. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An effective data placement strategy for IIoT applications

An effective data placement strategy for IIoT applications

引用

作者： Shen, Zhijie Liu, Bowen Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

With the rapid development of the Internet of things (IoT) and mobile communication technology, the amount of data related to industrial Internet of things (IIoT) applications has shown a trend of explosive growth, and hence edge-cloud collaborative environment becomes one of the most popular paradigms to place the IIoT applications data. However, edge servers are often heterogeneous and capacity limited while having lower access delay, so there is a contradiction between capacity and latency while using edge storage. Additionally, when IIoT applications deployed crossing edge regions, the impact of data replication and data privacy should not be ignored. These factors often pose challenges to proposing an effective data placement strategy to take full advantage of edge storage. To address these challenges, an effective data placement strategy for IIoT applications is designed in this article. We first analyze the data access time and data placement cost in an edge-cloud collaborative environment, with the consideration of data replication and data privacy. Then, we design a data placement strategy based on (Formula presented.) -constraint and Lagrangian relaxation, to reduce the data access time and meanwhile limit the data placement cost to an ideal level. As a result, our proposed data placement strategy can effectively reduce data access time and control data placement costs. Simulation and comparative analysis results have demonstrated the validity of our proposed strategy. © 2023 John Wiley & Sons Ltd.

关键词： Internet of things

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：