检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Huang, Wenxin Li, Dongyang Hu, Ruimin Liang, Chao Zhong, Xian School of Computer and Information Engineering Hubei University China National Engineering Research Center for Multimedia Software Wuhan University China Research Institute of Wuhan University Shenzhen China School of Computer Science and Technology Wuhan University of Technology China

ISBN: (纸本)9781665438643

Person re-identification (re-ID) gains plenty of achievements as a retrieval problem in constrained camera networks. However, most of the researches are concentrated on visual appearance, they still suffer from the complicated environments in unconstrained urban/campus surveillance scenario due to unreliable visual representations with extremely challenging problems as lack of training samples, amounts of irrelevant crowds, etc. Besides, most of the existing person re-ID datasets neglect the physical truth of realistic investigation application: 1) investigators search only few suspects among amounts of crowds. Moreover, he may not go through by every camera in the surveillance area and may appear in the same camera several times;and 2) the corresponding characteristic in multi-space of the same ID can be verified with each other. Therefore, we propose a person retrieval in physical world (PRPW) dataset with large-scale unconstrained surveillance scenario. It contains over 1.4 million bounding boxes, including 20 labeled IDs and numerous irrelevant crowds captured by 86 cameras. Furthermore, over 30,000 records of 20 mobile trajectories are collected in this dataset, and the 20 mobile trajectories are partially overlapped while passing by 86 cameras. Finally, based on two common senses and a verification experiment, we provide a proposal to tackle with PRPW task on the basis of trajectory association which utilizes global optimization to compensate for the errors caused by visual expression on local observation points. The comparison experiments with two typical unsupervised person re-ID methods are implemented on the constructed dataset. © 2021 IEEE

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Relaxed Rotational Equivariance via G-Biases in Vision

arXiv

引用

arXiv 2024年

作者： Wu, Zhiqiang Liu, Yingjie Sun, Licheng Yang, Jian Dong, Hanlin Lin, Shing-Ho J. Tang, Xuan Mi, Jinpeng Jin, Bo Wei, Xian Software Engineering Institute East China Normal University China School of Geospatial Information Information Engineering University China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Communication and Electronic Engineering East China Normal University China Institute of Machine Intelligence University of Shanghai for Science and Technology China School of Computer Science and Technology Tongji University China

Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called G-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group Cn. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Good is Bad: Causality Inspired Cloth-debiasing for Cloth-changing Person Re-identification

Good is Bad: Causality Inspired Cloth-debiasing for Cloth-ch...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhengwei Yang Meng Lin Xian Zhong Yu Wu Zheng Wang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science and Artificial Intelligence Wuhan University of Technology

Entangled representation of clothing and identity (ID)-intrinsic clues are potentially concomitant in conventional person Re- IDentification (ReID). Nevertheless, eliminating the negative impact of clothing on ID remains challenging due to the lack of theory and the difficulty of isolating the exact implications. In this paper, a causality-based Auto-Intervention Model, referred to as AIM 1 1 Codes will publicly available at https://***/BoomShakaY/AIM-CCReID., is first proposed to mitigate clothing bias for robust cloth-changing person ReID (CC-ReID). Specifically, we analyze the effect of clothing on the model inference and adopt a dual-branch model to simulate causal intervention. Progressively, clothing bias is eliminated automatically with model training. AIM is encouraged to learn more discriminative ID clues that are free from clothing bias. Extensive experiments on two standard CC-ReID datasets demonstrate the superiority of the proposed AIM over other state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A cross Transformer for image denoising

引用

Information Fusion 2024年 102卷

作者： Tian, Chunwei Zheng, Menghua Zuo, Wangmeng Zhang, Shichao Zhang, Yanning Lin, Chia-Wen School of Software Northwestern Polytechnical University Xi'anShaanxi710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'anShaanxi710129 China School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Peng Cheng Laboratory Guangdong Shenzhen518055 China School of Computer Science and Engineering Central South University Hunan Changsha410083 China School of Computer Science Northwestern Polytechnical University Shaanxi Xi'an710129 China Department of Electrical Engineering and the Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan

Deep convolutional neural networks (CNNs) depend on feedforward and feedback ways to obtain good performance in image denoising. However, how to obtain effective structural information via CNNs to efficiently represent given noisy images is key for complex scenes. In this paper, we propose a cross Transformer denoising CNN (CTNet) with a serial block (SB), a parallel block (PB), and a residual block (RB) to obtain clean images for complex scenes. A SB uses an enhanced residual architecture to deeply search structural information for image denoising. To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes. Also, to improve denoising performance, Transformer mechanisms are embedded into the SB and PB to extract complementary salient features for effectively removing noise in terms of pixel relations. Finally, a RB is applied to acquire clean images. Experiments illustrate that our CTNet is superior to some popular denoising methods in terms of real and synthetic image denoising. It is suitable to mobile digital devices, i.e., phones. Codes can be obtained at https://***/hellloxiaotian/CTNet. © 2023 Elsevier B.V.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Graph Attention Network Hashing for Cross-Modal Retrieval 38

An End-to-End Graph Attention Network Hashing for Cross-Moda...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jin, Huilong Zhang, Yingxue Shi, Lei Zhang, Shuang Kou, Feifei Yang, Jiapeng Zhu, Chuangying Luo, Jia College of Engineering Hebei Normal University China College of Computer and Cyber Security Hebei Normal University China State Key Laboratory of Media Convergence and Communication Communication University of China China Key Laboratory of Education Informatization for Nationalities Yunnan Normal University Ministry of Education China School of Computer Science Beijing University of Posts and Telecommunications China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology China Chongqing Research Institute Beijing University of Technology China

Due to its low storage cost and fast search speed, cross-modal retrieval based on hashing has attracted widespread attention and is widely used in real-world applications of social media search. However, most existing hashing methods are often limited by uncomprehensive feature representations and semantic associations, which greatly restricts their performance and applicability in practical applications. To deal with this challenge, in this paper, we propose an end-to-end graph attention network hashing (EGATH) for cross-modal retrieval, which can not only capture direct semantic associations between images and texts but also match semantic content between different modalities. We adopt the contrastive language image pretraining (CLIP) combined with the Transformer to improve understanding and generalization ability in semantic consistency across different data modalities. The classifier based on graph attention network is applied to obtain predicted labels to enhance cross-modal feature representation. We construct hash codes using an optimization strategy and loss function to preserve the semantic information and compactness of the hash code. Comprehensive experiments on the NUS-WIDE, MIRFlickr25K, and MS-COCO benchmark datasets show that our EGATH significantly outperforms against several state-of-the-art methods. © 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

Single Image 3D Reconstruction Based on Attention Mechanism and Graph Convolution Network 22

Single Image 3D Reconstruction Based on Attention Mechanism ...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Gao, Wei Yu, Liyang Du, Yuanyuan Lu, Songfeng Software Development Center of Industrial and Commercial Bank of China Limited Zhuhai519000 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430072 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057 China

ISBN: (纸本)9781450396110

This paper innovatively proposes a channel attention mechanism and graph convolutional network model adapted to 3D reconstruction, and combines the target detection model to construct a neural network that generates a target 3D model from a single RGB image. The model first generates the target 3D Voxels, and further generates a more refined 3D Meshes model through the graph convolutional network. Compared with the control group algorithm, the Pix3D datasetAPmesh index has been improved by 2.8%, which fully proves the effectiveness of the model in single-image 3D reconstruction. The experimental results show that the algorithm has good usability in the 3D reconstruction of actual mesh points. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Evaluation of ChatGPT Reliability Through Multilingual Inquiries

arXiv

引用

arXiv 2023年

作者： Puttaparthi, Poorna Chander Reddy Deo, Soham Sanjay Gul, Hakan Tang, Yiming Shang, Weiyi Yu, Zhe Department of Software Engineering Rochester Institute of Technology RochesterNY United States School of Information Rochester Institute of Technology RochesterNY United States Department of Computer Science Rochester Institute of Technology RochesterNY United States Department of Electrical and Computer Engineering University of Waterloo WaterlooON Canada

ChatGPT is currently the most popular large language model (LLM), with over 100 million users, making a significant impact on people's lives. However, due to the presence of jailbreak vulnerabilities, ChatGPT might have negative effects on people's lives, potentially even facilitating criminal activities. Testing whether ChatGPT can cause jailbreak is crucial because it can enhance ChatGPT's security, reliability, and social responsibility. Inspired by previous research revealing the varied performance of LLMs in different language translations, we suspected that wrapping prompts in multiple languages might lead to ChatGPT jailbreak. To investigate this, we designed a study with a fuzzing testing approach to analyzing ChatGPT's cross-linguistic proficiency. Our study includes three strategies by automatically posing different formats of malicious questions to ChatGPT: (1) each malicious question involving only one language, (2) multilingual malicious questions, (3) specifying that ChatGPT responds in a language different from the questions. In addition, we also combine our strategies by utilizing prompt injection templates to wrap the three aforementioned types of questions. We examined a total of 7,892 Q&A data points, discovering that multilingual wrapping can indeed lead to ChatGPT's jailbreak, with different wrapping strategies having varying effects on jailbreak probability. Prompt injection can amplify the probability of jailbreak caused by multilingual wrapping. This study provides insights for OpenAI developers to enhance ChatGPT's support for language diversity and inclusion. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bi-Causal: Group Activity Recognition via Bidirectional Causality

Bi-Causal: Group Activity Recognition via Bidirectional Caus...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Youliang Zhang Wenxuan Liu Danni Xu Zhuo Zhou Zheng Wang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University of Technology National University of Singapore

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Current approaches in Group Activity Recognition (GAR) predominantly emphasize Human Relations (HRs) while often neglecting the impact of Human-Object Inter-actions (HOIs). This study prioritizes the consideration of both HRs and HOIs, emphasizing their interdependence. Notably, employing Granger Causality Tests reveals the presence of bidirectional causality between HRs and HOIs. Leveraging this insight, we propose a Bidirectional-Causal GAR network. This network establishes a causality commu-nication channel while modeling relations and interactions, enabling reciprocal enhancement between human-object interactions and human relations, ensuring their mutual consistency. Additionally, an Interaction Module is devised to effectively capture the dynamic nature of human-object interactions. Comprehensive experiments conducted on two publicly available datasets showcase the superiority of our proposed method over state-of-the-art approaches. Our project page: https://***/***/

关键词： computer vision Computational modeling Cause effect analysis Communication channels Activity recognition

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning and predictive analytics approach for enhancing credit assessment in manufacturing

Decision Analytics Journal

引用

Decision Analytics Journal 2025年 15卷

作者： Razaque, Abdul Beishenaly, Aliya Kalpeyeva, Zhuldyz Uskenbayeva, Raisa Nikolaevna, Moldagulova Aiman Department of Software Engineering & AI School of Computing Gachon University Seongnam-si South Korea Department of Software Engineering Institute of Automation and Information Technologies Satbayev University Kazakhstan Department of Computer Engineering International Information Technology University (IITU) Almaty Kazakhstan

The fundamental issue with a credit system for manufacturers and importers of commodities is inefficient credit assessment. Traditional techniques frequently produce inaccurate risk assessments and credit scores, resulting in financial losses for lenders, missing business growth possibilities, and less favorable client conditions. To overcome this issue, a comprehensive credit assessment scoring system should be implemented to increase importers’ confidence. The article proposes a predictive-based reinforcement learning (PRL) model to help manufacturers and importers acquire more accurate and dependable credit scores while avoiding default risk. Furthermore, the proposed PRL model enhances decision-making, system efficiency, and risk-tolerant financial conditions. To attain these cutting-edge objectives, the proposed PRL model combines three algorithms. Algorithm 1 collects and aggregates data to indicate areas for improvement if credit scoring is poor. Algorithm 2 uses reinforcement learning to validate and enhance bank scores. Algorithm 3 focuses on predictive modeling for bank scoring, ensuring that the credit decision-making system is operational and constantly improving. Furthermore, reinforcement learning leverages the features from local interpretable model-agnostic explanations (LIME) and shapely additive explanations (SHAP) to generate locally reliable explanations and attribute the contribution of each feature for determining the output of the model. The Python platform tests the proposed PRL to achieve the objectives. Based on the results, The PRL model markedly enhances credit assessment precision, achieving an accuracy of over 99.5%, which outstrips current methodologies such OCLA (96.12%), PSML (84.12%), and EMPCC (91.67%). Furthermore, the PRL model augments leverage ratios, rising from 2.75% in 2015 to 3.36% in 2024.5, and increases accounts receivable turnover from 4.38% in 2015 to 7.4% in 2024.5, surpassing alternative credit evaluation methodologi

关键词： Financial analytics Intelligent credit systems Machine learning Manufacturing Predictive analytics Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model

arXiv

引用

arXiv 2025年

作者： Yang, Ziyuan Chen, Yingyu Wang, Zhiwen Shan, Hongming Chen, Yang Zhang, Yi College of Computer Science Sichuan University China Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University China School of Cyber Science and Engineering Sichuan University China School of Computer Science and Software Engineering Southwest Petroleum University China Institute of Science and Technology for Brain-inspired Intelligence Fudan University China School of Computer Science and Engineering Southeast University China

Reducing radiation doses benefits patients, however, the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) shows promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, raising privacy concerns. Federated learning (FL) has been introduced to address these privacy concerns;however, current methods are typically tailored to specific scanning protocols, which limits their generalizability and makes them less effective for unseen protocols. To address these issues, we propose SCAN-PhysFed, a novel SCanning- and ANatomy-level personalized Physics-Driven Federated learning paradigm for LDCT reconstruction. Since the noise distribution in LDCT data is closely tied to scanning protocols and anatomical structures being scanned, we design a dual-level physics-informed way to address these challenges. Specifically, we incorporate physical and anatomical prompts into our physics-informed hypernetworks to capture scanning- and anatomy-specific information, enabling dual-level physics-driven personalization of imaging features. These prompts are derived from the scanning protocol and the radiology report generated by a medical large language model (MLLM), respectively. Subsequently, client-specific decoders project these dual-level personalized imaging features back into the image domain. Besides, to tackle the challenge of unseen data, we introduce a novel protocol vector-quantization strategy Copyright © 2025, The Authors. All rights reserved.

关键词： computerized tomography

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：