检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liang, Keyu Liu, Zhongxin Liu, Chao Wan, Zhiyuan Lo, David Yang, Xiaohu The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computing and Information Systems Singapore Management University Singapore Singapore

Code search is a crucial task in software engineering, aiming to retrieve code snippets that are semantically relevant to a natural language query. Recently, Pre-trained Language Models (PLMs) have shown remarkable success and are widely adopted for code search tasks. However, PLM-based methods often struggle in cross-domain scenarios. When applied to a new domain, they typically require extensive fine-tuning with substantial data. Even worse, the data scarcity problem in new domains often forces these methods to operate in a zero-shot setting, resulting in a significant decline in performance. RAPID, which generates synthetic data for model fine-tuning, is currently the only effective method for zero-shot cross-domain code search. Despite its effectiveness, RAPID demands substantial computational resources for fine-tuning and needs to maintain specialized models for each domain, underscoring the need for a zero-shot, fine-tuning-free approach for cross-domain code search. The key to tackling zero-shot cross-domain code search lies in bridging the gaps among domains. In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching. We first conduct an empirical study to investigate the effectiveness of these two matching schemas in zero-shot cross-domain code search. Our findings highlight the strong complementarity among the three matching schemas, i.e., query-code, query-comment, and code-code matching. Based on the findings, we propose CodeBridge, a zero-shot, fine-tuning-free approach for cross-domain code search. Specifically, CodeBridge first employs zero-shot prompting to guide Large Language Models (LLMs) to generate a comment for each code snippet in the codebase and produce a code for each query. Subsequently, it encodes queries, code snippets, comments, and the generated code using PLMs and assesses similarities through three matching schemas: query-code, query-comment,

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

DAANet: Dual Attention Aggregating Network for Salient Object Detection

DAANet: Dual Attention Aggregating Network for Salient Objec...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Li, Yijie Wang, Hewei Li, Zhenqi Wang, Shaofan Dev, Soumyabrata Zuo, Guoyu Beijing University of Technology Beijing-Dublin International College Beijing100124 China Beijing University of Technology Faculty of Information Technology Beijing100124 China University College Dublin School of Computer Science Dublin Ireland Beijing University of Technology Faculty of Information Technology China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China

ISBN: (纸本)9798350325706

When the Convolutional neural network (CNN) has been introduced for computer vision, many researches use CNN-based model to perform salient object detection (SOD). In recent years, The feature pyramid network (FPN) based structure is more popular for salient object detection tasks. In this paper, to improve the overall performance of salient object detection tasks, we propose a dual attention aggregating network (DAANet), which is an FPN-based deep convolutional neural network with a dual attention aggregation module (DAAM) and dilated refinement block (DRB). The DRB module uses convolutions with different dilation rates to expand the receptive field. The DAAM considers the salient map prediction from the low-level output as pseudo-attention which can efficiently aggregate multi-scale information. The convolution block attention module (CBAM) in DAAM can refine the aggregation of pseudo-attention which enables better performance. We evaluate DAANet on six benchmark datasets that prove the effectiveness of DAANet and its components. Our implementation can be found at: https://***/Att100/DAANet. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Heads Segmentation and Counting in Crowded Retail Environment with Convolutional Neural Networks Using Top View Depth Images

引用

SN Computer Science 2023年第1期4卷 61页

作者： Abed, Almustafa Akrout, Belhassen Amous, Ikram Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia Multimedia Information Systems and Advanced Computing Laboratory (MIRACL) Sfax University Sfax 3021 Tunisia ENET’COM University of Sfax National School of Electronics and Telecommunications of Sfax Road Tunis City El Ons Sfax 3018 Tunisia

In recent years, researchers have developed several techniques to accurately count the number of people in a crowded retail environment for human behavior analysis, ranging from vision and feature based approaches to machine-learning and deep learning approaches. Due to the availability and affordability of recent advanced technologies such as depth sensors and high computing powers as well as the availability of big data, the need for building accurate models to detect and count people in crowded environments arises. Deep learning approaches has proven to be highly accurate especially when there is enough data to train the model and high computation powers. People detection and counting is a challenging problem. due to several issues such as occlusion, light variations, complex backgrounds to name a few. To cope with these issues, we utilize a top-view configuration depth data to train our model. We propose a convolutional encoder decoder architecture consisting of a resnet50 encoder trained on the ImageNet dataset as a transfer learning technique and we built the decoder part of the model as a novel contribution, for segmenting and counting customers heads in a crowded retail stores where there are more than 6 individuals per square meter without compromising people privacy because the camera does not record people’s faces. The objective of our method is to segment and count people using the publicly available TV-Head Dataset and People Counting DataSet (PCDS). The results demonstrate that our model is robust and can be used for real time people counting with accurate results. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Computer vision Convolutional neural networks Intelligent retail environment People counting Top-view configuration

来源：评论

学校读者我要写书评

暂无评论

Sustainability Forecasting for Deep Learning Packages

Sustainability Forecasting for Deep Learning Packages

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Junxiao Han Yunkun Wang Zhongxin Liu Lingfeng Bao Jiakun Liu David Lo Shuiguang Deng School of Computer & Computing Science Hangzhou City University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Deep Learning (DL) technologies have been widely adopted to tackle various tasks. In this process, through software dependencies, a multi-layer DL supply chain (SC) is formed, with DL frameworks acting as the root, DL packages acting as the bridge nodes, and downstream DL projects acting as the periphery. However, most Open Source Software (OSS) projects may fail. Considering the crucial position of DL packages in the DL SC, to foster the sustainable development of DL SCs and DL packages, we aim to forecast the long-term sustainability of DL packages. Here, sustained activity is adopted as the main proxy of sustainability, and the sustainability status is classified as “sus-tainable” or “dormant”. Relatedly, a DL package is considered as “sustainable” if it has sustained activity in its last 12 months. Otherwise, it is deemed as “dormant”. To this end, we propose an approach that begins with obtaining longitudinal features for each DL package in each month. Then, we develop a model to forecast the sustainability of DL packages by incorporating the longitudinal features, which can aptly predict sustainability with an accuracy of up to 0.81. Subsequently, an interpretable module is developed to interpret the determinants (i.e., important features) that impact the sustainability of DL packages. Finally, we generate sustainability trajectories for each DL package to better understand the monthly changes of their sustainability status. Our findings uncover that for most DL packages, fewer but more centralized developers and a balanced collaboration are more likely to help sustain the DL packages. Furthermore, although some DL packages are sustainable, their sustainability trajectories present statistically decreasing trends over time. Based on the findings, we shed light on the dynamic sustainability of DL packages, highlight future research directions, and provide practical suggestions to DL package maintainers, developers, users, and software engineering researchers.

关键词： Deep learning Supply chains Predictive models Market research Trajectory Sustainable development Task analysis

来源：评论

学校读者我要写书评

暂无评论

RIGID: Recurrent GAN Inversion and Editing of Real Face Videos

arXiv

引用

arXiv 2023年

作者： Xu, Yangyang He, Shengfeng Wong, Kwan-Yee K. Luo, Ping Deapartment of Computer Science The University of Hong Kong Hong Kong School of Computing and Information Systems Singapore Management University Singapore Shanghai AI Laboratory China

GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired inconsistent results over time. In this paper, we propose a unified recurrent framework, named Recurrent vIdeo GAN Inversion and eDiting (RIGID), to explicitly and simultaneously enforce temporally coherent GAN inversion and facial editing of real videos. Our approach models the temporal relations between current and previous frames from three aspects. To enable a faithful real video reconstruction, we first maximize the inversion fidelity and consistency by learning a temporal compensated latent code. Second, we observe incoherent noises lie in the high-frequency domain that can be disentangled from the latent space. Third, to remove the inconsistency after attribute manipulation, we propose an in-between frame composition constraint such that the arbitrary frame must be a direct composite of its neighboring frames. Our unified framework learns the inherent coherence between input frames in an end-to-end manner, and therefore it is agnostic to a specific attribute and can be applied to arbitrary editing of the same video without re-training. Extensive experiments demonstrate that RIGID outperforms state-of-the-art methods qualitatively and quantitatively in both inversion and editing tasks. The deliverables can be found in https://***/RIGID. © 2023, CC BY-NC-ND.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting

arXiv

引用

arXiv 2025年

作者： Zhu, Huilin Yuan, Jingling Yang, Zhengwei Guo, Yu Zhong, Xian He, Shengfeng Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China School of Computing and Information Systems Singapore Management University Singapore School of Computer Science Wuhan University China School of Navigation Wuhan University of Technology China

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods often predict this count without considering class-specific outputs, leading to inaccuracies when such outputs are required. These inaccuracies stem from two key challenges: 1) the prevalence of single-category images in datasets, which leads models to generalize specific categories as representative of all objects, and 2) the use of mean squared error loss during training, which applies uniform penalization. This uniform penalty disregards errors in less frequent categories, particularly when these errors contribute minimally to the overall loss. To address these issues, we propose FocalCount, a novel approach that leverages diverse feature attributes to estimate the number of object categories in an image. This estimate serves as a weighted factor to correct class-count imbalances. Additionally, we introduce Focal-MSE, a new loss function that integrates binary cross-entropy to generate stronger error gradients, enhancing the model’s sensitivity to errors in underrepresented categories. Our approach significantly improves the model’s ability to distinguish between specific classes and general counts, demonstrating superior performance and scalability in both few-shot and zero-shot scenarios across three object counting datasets. The code will be released soon. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DiffusionMat: Alpha Matting as Sequential Refinement Learning

arXiv

引用

arXiv 2023年

作者： Xu, Yangyang He, Shengfeng Shao, Wenqi Wong, Kwan-Yee K. Qiao, Yu Luo, Ping Deapartment of Computer Science The University of Hong Kong Hong Kong School of Computing and Information Systems Singapore Management University Singapore Shanghai AI Laboratory China

In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose guidance for alpha matte prediction, our approach treats image matting as a sequential refinement learning process. This process begins with the addition of noise to trimaps and iteratively denoises them using a pre-trained diffusion model, which incrementally guides the prediction towards a clean alpha matte. The key innovation of our framework is a correction module that adjusts the output at each denoising step, ensuring that the final result is consistent with the input image’s structures. We also introduce the Alpha Reliability Propagation, a novel technique designed to maximize the utility of available guidance by selectively enhancing the trimap regions with confident alpha information, thus simplifying the correction task. To train the correction module, we devise specialized loss functions that target the accuracy of the alpha matte’s edges and the consistency of its opaque and transparent regions. We evaluate our model across several image matting benchmarks, and the results indicate that DiffusionMat consistently outperforms existing methods. Project page at https://***/DiffusionMat. © 2023, CC BY-NC-ND.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

High-Performance Mining of COVID-19 Open Research Datasets for Text Classification and Insights in cloud computing Environments

High-Performance Mining of COVID-19 Open Research Datasets f...

引用

IEEE International Conference on Utility and cloud computing (UCC)

作者： Jie Zhao Maria A. Rodriguez Rajkumar Buyya Cloud Computing and Distributed Systems Laboratory School of Computing and Information Systems The University of Melbourne Australia

ISBN: (数字)9780738123943

ISBN: (纸本)9781665415637

The COVID-19 global pandemic is an unprecedented health crisis. Many researchers around the world have produced an extensive collection of literature since the outbreak. Analysing this information to extract knowledge and provide meaningful insights in a timely manner requires a considerable amount of computational power. cloud platforms are designed to provide this computational power in an on-demand and elastic manner. Specifically, hybrid clouds, composed of private and public data centers, are particularly well suited to deploy computationally intensive workloads in a cost-efficient, yet scalable manner. In this paper, we developed a system utilising the Aneka Platform as a Service middleware with parallel processing and multi-cloud capability to accelerate the data process pipeline and article categorising process using machine learning on a hybrid cloud. The results are then persisted for further referencing, searching and visualising. The performance evaluation shows that the system can help with reducing processing time and achieving linear scalability. Beyond COVID-19, the application might be used directly in broader scholarly article indexing and analysing.

关键词： cloud computing Unified modeling language Task analysis COVID-19 Data visualization Computer architecture Scalability

来源：评论

学校读者我要写书评

暂无评论

Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition

arXiv

引用

arXiv 2023年

作者： Li, Bobo Fei, Hao Liao, Lizi Zhao, Yu Teng, Chong Chua, Tat-Seng Ji, Donghong Li, Fei Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China NExT Research Center School of Computing National University of Singapore Singapore School of Computing and Information Systems Singapore Management University Singapore Tianjin University China Wuhan University China National University of Singapore Singapore

It has been a hot research topic to enable machines to understand human emotions in multimodal contexts under dialogue scenarios, which is tasked with multimodal emotion analysis in conversation (MM-ERC). MM-ERC has received consistent attention in recent years, where a diverse range of methods has been proposed for securing better task performance. Most existing works treat MM-ERC as a standard multimodal classification problem and perform multimodal feature disentanglement and fusion for maximizing feature utility. Yet after revisiting the characteristic of MM-ERC, we argue that both the feature multimodality and conversational contextualization should be properly modeled simultaneously during the feature disentanglement and fusion steps. In this work, we target further pushing the task performance by taking full consideration of the above insights. On the one hand, during feature disentanglement, based on the contrastive learning technique, we devise a Dual-level Disentanglement Mechanism (DDM) to decouple the features into both the modality space and utterance space. On the other hand, during the feature fusion stage, we propose a Contribution-aware Fusion Mechanism (CFM) and a Context Refusion Mechanism (CRM) for multimodal and context integration, respectively. They together schedule the proper integrations of multimodal and context features. Specifically, CFM explicitly manages the multimodal feature contributions dynamically, while CRM flexibly coordinates the introduction of dialogue contexts. On two public MM-ERC datasets, our system achieves new state-of-the-art performance consistently. Further analyses demonstrate that all our proposed mechanisms greatly facilitate the MM-ERC task by making full use of the multimodal and context features adaptively. Note that our proposed methods have the great potential to facilitate a broader range of other conversational multimodal tasks. © 2023, CC BY-NC-ND.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A sustainable and secure load management model for green cloud data centres

引用

Scientific Reports 2023年第1期13卷 1-22页

作者： Saxena, Deepika Singh, Ashutosh Kumar Lee, Chung-Nan Buyya, Rajkumar Department of Computer Applications National Institute of Technology Haryana Kurukshetra 136119 India Department of Computer Science Goethe University Frankfurt Germany Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung 804201 Taiwan Cloud Computing and Distributed Systems (CLOUDS) Lab School of Computing and Information Systems University of Melbourne Melbourne 804201 Australia

The massive upsurge in cloud resource demand and inefficient load management stave off the sustainability of cloud Data Centres (CDCs) resulting in high energy consumption, resource contention, excessive carbon emission, and security threats. In this context, a novel Sustainable and Secure Load Management (SaS-LM) Model is proposed to enhance the security for users with sustainability for CDCs. The model estimates and reserves the required resources viz., compute, network, and storage and dynamically adjust the load subject to maximum security and sustainability. An evolutionary optimization algorithm named Dual-Phase Black Hole Optimization (DPBHO) is proposed for optimizing a multi-layered feed-forward neural network and allowing the model to estimate resource usage and detect probable congestion. Further, DPBHO is extended to a Multi-objective DPBHO algorithm for a secure and sustainable VM allocation and management to minimize the number of active server machines, carbon emission, and resource wastage for greener CDCs. SaS-LM is implemented and evaluated using benchmark real-world Google Cluster VM traces. The proposed model is compared with state-of-the-arts which reveals its efficacy in terms of reduced carbon emission and energy consumption up to 46.9% and 43.9%, respectively with improved resource utilization up to 16.5%. © 2023, The Author(s).

关键词：

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：