检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Junfan, Chen Zhang, Richong Zheng, Yaowei Chen, Qianben Hu, Chunming Mao, Yongyi SKLSDE School of Software Beihang University Beijing China SKLSDE School of Computer Science Beihang University Beijing China School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

ISBN: (纸本)9798400701719

Text classification is a fundamental task in web content mining. Although the existing supervised contrastive learning (SCL) approach combined with pre-trained language models (PLMs) has achieved leading performance in text classification, it lacks fundamental principles. Theoretically motivated by a derived lower bound of mutual information maximization, we propose a dual contrastive learning framework DualCL that satisfies three properties, i.e., parameter-free, augmentation-easy and label-aware. DualCL generates classifier parameters from the PLM and simultaneously uses them for classification and as augmented views of the input text for supervised contrastive learning. Extensive experiments conclusively demonstrate that DualCL excels in learning superior text representations and consistently outperforms baseline models. © 2024 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

PointDKT: Dual-Key Transformer for Point Cloud 7

PointDKT: Dual-Key Transformer for Point Cloud

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Yang, Jifeng Zhou, Guang-Guan Chen, Yang Southeast University School of Software Nanjing China Southeast University School of Biological Science and Medical Engineering Nanjing China Southeast University School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350363173

Benefiting from the development of transformer-based networks in natural language processing and computer vision, researches on 3D point cloud understanding have made great progress in recent years. However, existing works often focus solely on aggregating local features or construct global dependencies through methods that significantly increase memory and computation complexity. Addressing these challenges, we present Point Dual-Key Transformer(PDKT), a novel and straightforward end-to-end network architecture. To expand the receptive fields and preserve the local geometric structural information, we introduce an efficient dual-key cross attention mechanism, which builds upon standard cross attention to facilitate global feature capture across the network without neglecting local detail. Furthermore, we adopt a learnable operator to automatically integrate local and global branches. Extensive experiment results demonstrate the effectiveness and superiority of our method on point cloud understanding tasks. © 2024 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Recipe Optimization of College Students Based on Simulated Annealing 3

Machine Learning Model for Recipe Optimization of College St...

引用

3rd International Conference on Data Analytics, Computing and Artificial Intelligence, ICDACAI 2024

作者： Sheng, Peizhi Chen, Xuhao School of Computer and Information Science Software Southwest University Chongqing China School of Engineering and Technology Southwest University Chongqing China

ISBN: (纸本)9798331519032

This paper first made a comprehensive dietary nutrition evaluation of the two recipes provided, and conducted a visual analysis of the differences of various nutrient components by querying the "Table of Chinese Food Ingredients". The nutrients involved included major daily productivity nutrients such as protein and fat, and non-productivity nutrients such as calcium, iron and zinc, which were used as collaborative evaluation indicators. Secondly, in order to specifically evaluate the daily diet of two male and female students, we pointed out the problems in the diet according to the Basic requirements for Analysis, Evaluation and Optimal Design of Dietary Recipes, and then adjusted and improved them, and made a comprehensive dietary nutrition evaluation again. Finally, the diet after adjustment has been improved to basically meet the nutritional requirements. Then, two models are established. Firstly, a model based on linear programming algorithm is established to solve the problem, and a model based on simulated annealing algorithm is established as a backup scheme and innovative ideas. Then, we used Model 1 to optimize male and female college birthday meal recipes with different goals (most economical, highest AAS, and dual goals). Finally, we also compare these three kinds of daily diet recipes with different objective optimization, and get the conclusion that the daily diet recipes with dual objective optimization have the highest cost performance. Finally, in order to realize the optimal design of weekly balanced diet, the paper extends the optimization model of daily diet based on problem 2. In order to solve the problem that the extended optimization model is difficult to solve due to too many decision variables, we propose a random elimination strategy to solve the weekly recipe scheme step by step according to the time granularity. After the design of daily recipes for each day is completed, the food of the day is eliminated from the daily recipes of the n

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

CLIP-Guided Bidirectional Prompt and Semantic Supervision for Dynamic Facial Expression Recognition 18

CLIP-Guided Bidirectional Prompt and Semantic Supervision fo...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Zhang, Junliang Liu, Xu Liang, Yu Xian, Xiaole Xie, Weicheng Shen, Linlin Song, Siyang Shenzhen University School of Computer Science & Software Engineering China University of Leicester School of Computing and Mathematical Sciences United Kingdom

ISBN: (纸本)9798350364132

Due to the insufficient semantic information supervision in existing works for dynamic facial expression recognition (DFER), videos with similar facial changes but different expressions may be easily confused. Thanks to the potential textual information for semantic supervision, contrastive language-image pretraining (CLIP) model provides a new direction for DFER. However, pre-trained CLIP based on image-text pairs has difficulty in capturing temporal features in the video domain. Therefore, we propose a novel visual language model that captures and aggregates dynamic features of expressions in semantic supervision via Inter-Frame Interaction Transformer (Inter-FIT) and Multi-Scale Temporal Aggregation (MSTA). Furthermore, though prompt learning is often used in CLIP to enhance semantic supervision, previous studies have only focused on the role of textual prompts, ignoring the importance of visual prompts in facilitating the relationality between the two. Therefore, we designed a Bidirectional Enhanced Prompt (BiEhPro) to facilitate the learning of this relationality between text and visual cues in enhancing semantic supervision. Extensive experiments and ablation studies on three benchmark datasets, i.e., DFEW, FERV39K, and MAFW, validate the effectiveness of our modules and algorithm. Code is publicly available at https://***/JunLiangZ/CLIP-Guided-DFER. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

EDAW: Enhanced Knowledge Distillation and Adaptive Pseudo Label Weights for Continual Named Entity Recognition

EDAW: Enhanced Knowledge Distillation and Adaptive Pseudo La...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Sheng, Yubin Zhang, Zuping Tang, Panrui Huang, Bo Xiao, Yao School of Computer Science and Engineering Central South University Chang-sha China School of Software Xinjiang University Urumqi China

ISBN: (纸本)9781665410205

Continual Learning for Named Entity Recognition (CL-NER) is designed to train models capable of adapting to evolving data by continuously introducing new entity types. This approach is crucial in dynamic environments where data evolves, such as social media, healthcare, and legal documents, necessitating the model to retain the memory of previously learned entity types while learning to identify new ones. However, due to the neural network's tendency to acquire new knowledge and forget old knowledge in continual learning and the unique non-entity type annotations in NER tasks, CL-NER faces severe catastrophic forgetting and semantic drift issues. In this paper, we propose Enhanced Knowledge Distillation and Entropy-based Adaptive Pseudo Label Weights (EDAW) to address the catastrophic forgetting and semantic drift issues in CL-NER. Specifically, we develop an enhanced knowledge distillation method that combines Kullback-Leibler divergence and feature cosine discrepancy. This method effectively minimizes the variance in output probability distributions and aligns the internal feature spaces between new and old models, thus reducing catastrophic forgetting. Additionally, we propose an entropy-based adaptive pseudo label weight method that allows the model to assign different weights to pseudo labels with varying certainties during training, effectively alleviating semantic drift and error accumulation caused by erroneous relabeling of pseudo labels. Notably, this study pioneers the in-clusion of a Chinese dataset in CL-NER, enhancing the model's robustness and demonstrating its efficacy in a multilingual context. Experiments on fourteen CL-NER settings across four public NER datasets show that EDAW improves average Micro-F1 and Macro-F1 scores by 3.44% and 3.72%, respectively, over existing state-of-the-art(SOTA) methods. We make our code available at: https://***/livosr/EDAW/tree/master © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Part-based Person Re-Identification with Swin Transformer 6

Part-based Person Re-Identification with Swin Transformer

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Qin, Yusong Huang, Pu Zhou, Yao Huang, Zengxi Xihua University School of Computer Science and Software Engineering Chengdu China Xihua University School of Computer and Software Engineering and the Sichuan Xihua Jiaotong Forensics Center Chengdu China

ISBN: (纸本)9798350325485

Person re-identification(Re-ID) is a crucial task in computer vision, which aims to match pedestrian images captured in non-overlapping camera views. It has significant implications for public safety applications. However, current methods primarily rely on global features and thus are vulnerable to background clutters and occlusion. To address these issues, this paper proposes a part-based Re-ID method using the Swin Transformer. In this method, we first utilize human pose estimation method to detect the body keypoints of a pedestrian. We then extract local windows and patches centered at these keypoints, so as to minimize the involvement of background and occlusion information in the down-stream re-identification. These body parts in pose guided windows are fed to the Swin Transformer network. The hierarchical structure of Swin Transformer also enables the proposed method more robust to multi-scale problems. Our experimental results on both holistic and occluded datasets, i.e., Market-1501, DukeMTMC-reID, and Occluded-Duke, demonstrate that the proposed method is on par with the state-of-The-Art methods. © 2023 IEEE.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

Application of Static Virus Spread Algorithm in Base-Balanced DNA Fragment Optimization

Application of Static Virus Spread Algorithm in Base-Balance...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yao, Yao Zheng, Yanfen Zhang, Xun Liu, Xin Zhang, Xiaokang Wang, Bin Zhang, Qiang Dalian University of Technology School of Computer Science and Technology Dalian China Dalian University School of Software Engineering Dalian China

ISBN: (纸本)9798350386226

DNA has found applications in a diverse array of fields such as computing, medical diagnosis, and circuits. Designing DNA fragments that meet specific requirements is crucial for ensuring the smooth execution of tasks in these domains. However, the conventional approach of combining constraints with evolutionary algorithms often encounters challenges like orthogonality and thermodynamic instability. This poses risks to the control of reaction processes. To tackle these challenges, we have undertaken two tasks in this study: expanding constraint sets and innovating evolutionary algorithms. Firstly, we propose a base balance strategy aimed at enhancing the thermodynamic properties within DNA fragment groups by diversifying neighboring base combinations. The addition of this strategy achieves a minimum variance of 0.03 for the melting temperature while ensuring orthogonality. It represents a significant improvement compared to previous results and reduces the complexity of controlling reactions. Secondly, our static virus spread algorithm optimizes target DNA fragments by base mutations and virus amplification. Simultaneously,it demonstrates good performance across 23 benchmark functions, highlighting its optimization potential. This work is expected to further refine theoretical shortcomings and offer a convenient tool for DNA fragment optimization. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Unpaired 3D Shape-to-Shape Translation via Gradient-Guided Triplane Diffusion

引用

IEEE Transactions on Visualization and computer Graphics 2025年第5期31卷 3376-3386页

作者： Zhang, Wenxiao Rahmani, Hossein Liu, Jun Hohai University College of Computer Science and Software Engineering Nanjing211100 China Lancaster University School of Computing and Communications LancasterLA1 4YW United Kingdom

Unpaired shape-to-shape translation refers to the task of transforming the geometry and semantics of an input shape into a new shape domain without paired training data. Previous methods utilize GAN-based architectures to perform shape translation, employing adversarial training to transform the source shape encoding into the target domain in the low-dimensional latent feature space. However, these methods encounter difficulties in generating diverse and high-quality results, as they often suffer from issues such as "mode collapse". This leads to limited generation diversity and makes it challenging to find an accurate latent code that adequately represents the input shape. In this paper, we achieve unpaired shape-to-shape translation via a triplane diffusion model, in which we factorize 3D objects into triplane representations and conduct a diffusion process on these representations to accomplish shape domain transformation. We observe that by adding an appropriate amount of noise to an input object during the forward diffusion process, domain-specific shape structures are smoothed out while the overall structure is still preserved. Subsequently, we progressively remove the noise via an unconditional diffusion model trained on the target shape domain in the reverse diffusion process. This allows us to obtain a denoised output that retains the structural similarities of the source input while aligning with the distribution of the target shape domain. During this process, we propose two gradient-based guidance mechanisms to guide the translation process to guarantee more faithful results during the denoising process. We conduct extensive experiments on different shape domains, and the experimental results demonstrate that our method achieves superior shape fidelity with high quality compared to current state-of-the-art baselines. © 1995-2012 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

A Novel Data Mining Framework for Discovering Association Rules in Multivariate Time Series 7

A Novel Data Mining Framework for Discovering Association Ru...

引用

7th International Conference on Advanced Algorithms and Control engineering, ICAACE 2024

作者： Wang, Shengwei Lyu, Jianhua Zhang, Baili School Of Software Southeast University Nanjing China College Of Computer Science And Engineering Southeast University Nanjing China

ISBN: (纸本)9798350361445

As a significant field within data mining, association rule mining plays a pivotal role in unveiling relationships between items within a dataset. Existing approaches in multivariate time series (MTS) association rule mining primarily emphasize the generation of association rules by combining features from different variables, but neglect to adequately consider the temporal relationship between these features and ignore the trend information of variables, resulting in an incomplete capture of the essential characteristics inherent in MTS data. In this paper, we introduce a novel framework for association rule mining in multivariate time series. First, we discretize the multivariate time series into the symbolic sequence using trend-based symbolic aggregate approximation(TSAX). Then, a rule mining method is introduced to discover association rules that consider the temporal relationship among symbols of different variables. The results of experiments demonstrate the discovery of significant rules within the 'Weather&Traffic' dataset which gives the traffic conditions in France depending on the weather. Further, we also provide the outcomes of the sensitivity analysis conducted on our method, illustrating that significant rules can be mined by adjusting the parameters of TSAX to different settings. The experimental results highlight the utility of our proposed framework in discovering temporal association rules within multivariate time series datasets. © 2024 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Motivating Users to Atend to Privacy: A Theory-Driven Design Study

Motivating Users to Atend to Privacy: A Theory-Driven Design...

引用

2024 ACM Designing Interactive Systems Conference, DIS 2024

作者： Shiri, Varun Xiong, Maggie Cheng, Jinghui Guo, Jin L.C. Department of Computer and Software Engineering Polytechnique Montreal MontrealQC Canada School of Computer Science McGill University MontrealQC Canada

ISBN: (纸本)9798400705830

In modern technology environments, raising users’ privacy awareness is crucial. Existing eforts largely focused on privacy policy presentation and failed to systematically address a radical challenge of user motivation for initiating privacy awareness. Leveraging the Protection Motivation Theory (PMT), we proposed design ideas and categories dedicated to motivating users to engage with privacy-related information. Using these design ideas, we created a conceptual prototype, enhancing the current App Store product page. Results from an online experiment and follow-up interviews showed that our design efectively motivated participants to attend to privacy issues, raising both the threat appraisal and coping appraisal, two main factors in PMT. Our work indicated that efective design should consider combining PMT components, calibrating information content, and integrating other design elements, such as visual cues and user familiarity. Overall, our study contributes valuable design considerations driven by the PMT to amplify the motivational aspect of privacy communication. © 2024 Copyright held by the owner/author(s).

关键词： Motivation

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：