检索结果-内蒙古大学图书馆

35th Conference on Neural Information Processing Systems, NeurIPS 2021

作者： Zeng, Yanhong Yang, Huan Wang, Jianbo Fu, Jianlong School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Microsoft Research Asia China University of Tokyo Japan

ISBN: (纸本)9781713845393

We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new formulation enables a flexible local manipulation for different image regions, which makes it possible to learn content-aware and fine-grained style control for image synthesis. Specifically, it takes as input a sequence of latent tokens to predict the visual tokens for synthesizing an image. Under this perspective, we propose a token-based generator (i.e.,TokenGAN). Particularly, the TokenGAN inputs two semantically different visual tokens, i.e., the learned constant content tokens and the style tokens from the latent space. Given a sequence of style tokens, the TokenGAN is able to control the image synthesis by assigning the styles to the content tokens by attention mechanism with a Transformer. We conduct extensive experiments and show that the proposed TokenGAN has achieved state-of-the-art results on several widelyused image synthesis benchmarks, including FFHQ and LSUN CHURCH with different resolutions. In particular, the generator is able to synthesize high-fidelity images with 1024 × 1024 size, dispensing with convolutions entirely. © 2021 Neural information processing systems foundation. 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

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

arXiv

引用

arXiv 2024年

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2024, CC BY-NC-SA.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Data Augmentation for Garbage Classification with Target Detection Algorithm

Research on Data Augmentation for Garbage Classification wit...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Chen, Jiansong Zuo, Shikai Lin, Yun Tang, Kai Zou, Jianhang Feng, Naixing Cai, Yijun Xiamen University of Technology Smart Sensing Integrated Circuit Engineering Research Center of Universities in Fujian Province Xiamen361024 China Xiamen Wish Information Technology Co. Ltd Xiamen361006 China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei China

ISBN: (纸本)9781665452366

Garbage classification is an essential work in daily life. With the development of artificial intelligence (AI), we have begun to use object detection to achieve garbage classification. However, the stacking and occlusion of garbage often make the detection performance unsatisfactory. In this paper, YOLOv5 algorithm is used for garbage detection and classification. YOLOv5 has three detection heads, which can detect objects at multiple scales. At the same time, Mosaic and Coarse Dropout image augmentation techniques are used to process our private data set of garbage, which improves the diversity of images. In this way, the target classification accuracy of the detection model can reach 75.7%, which is significantly improved compared with 69.9% without data augmentation. This paper provides a new technical support for the scene classification of stacked garbage based on deep learning. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Static Virus Spread Algorithm for DNA Sequence Design

arXiv

引用

arXiv 2023年

作者： Yao, Yao Zhang, Xun Liu, Xin Liu, Yuan Zhang, Xiaokang Zhang, Qiang The School of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China The Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian116622 China

DNA is not only the genetic material of life, but also a favorable material for a new computing model. Various research works based on DNA computing have been carried out in recent years. DNA sequence design is the foundation of such research. The sequence quality directly affects the universality, robustness, and stability of DNA computing. How to design DNA sequences depends on the biological properties and target requirements, which is a typical combinatorial optimization problem. In this paper, in order to design DNA sequences with high-quality, we propose a novel meta-heuristic evolutionary algorithm, termed the static virus spread algorithm (SVS). Through this algorithm, we focus on the constraints of universal DNA sequence design and produce a large number of DNA sequences with non-complementarity and small difference in melting temperature as the objectives, and fully considering the balanced proportion of the four bases. The computer simulation and polyacrylamide gel electrophoresis experiments show that the high-quality DNA sequences designed by this algorithm are effective, which is expected to provide a convenient tool for sequence preparation before DNA biochemical operations. Copyright © 2023, The Authors. All rights reserved.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Nodule Classification of CT Images with Attribute Self-guided Graph Convolutional V-Shape Networks 18th

Pulmonary Nodule Classification of CT Images with Attribute ...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Zhang, Xiangbo Wang, Kun Zhang, Xiaohong Huang, Sheng Key Laboratory of Dependabel Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing400044 China The School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (纸本)9783030891879

Accurate identification and early diagnosis of malignant pulmonary nodules are critical to improving the survival rate of lung cancer patients. Recently, deep learning methods have been proved to be successful in computer-aided diagnosis tasks. However, most advanced research work does not fully utilized valuable attribute prior knowledge for semantic reasoning to guide the network. Therefore, it lacks interpretability and hence is difficult for clinical radiologists to understand and apply. To comprehensively tackle these challenges, we propose a novel Attribute Self-guided Graph Convolutional V-shape Networks (AS-GCVN) for pulmonary nodules classification with steps as follows. We first develop a sub-network for representation learning, which can effectively extract image-level features. Second, we construct a graph convolution V-shape network to model the semantic information of attributes to guide the classification of benign and malignant pulmonary nodules accurately. Moreover, an Attribute Self-guided Feature Enhancement (ASFE) module is proposed to improve the ability of graph semantic reasoning, which can map the image features extracted by the convolutional neural network to attribute features through adaptive learning. Finally, the two sub-networks effectively integrate attribute inference knowledge and representation learning to enable end-to-end training. This way can further improve the interpretability and robustness of pulmonary nodule classification. Extensive experimental results on the LIDC-IDRI dataset demonstrate that our approach obviously outperforms other existing state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

DSP Assembler Auto-Generation Technique and ToolChain Integration 21

DSP Assembler Auto-Generation Technique and ToolChain Integr...

引用

21st IEEE International Conference on Communication Technology, ICCT 2021

作者： Wang, Wanli Wu, Jun Ren, Haoqi Zhang, Zhifeng Tongji University Electronics and Information Engineering College Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Fudan University School of Computer Science Shanghai200438 China

ISBN: (纸本)9781665432061

To promote the application of DSP, a fast and accurate toolchain generation method must be realized. Unlike the traditional manual method, in this paper, we propose a toolchain generation algorithm based on the architecture description language, and migrate the toolchain to adapt to the specified processor architecture. The algorithm uses the DSP architecture description as input to generate intermediate expressions, then uses lexical analysis and syntax analysis tools to migrate the assembly toolchain. In addition, an integrated development environment is developed based on Eclipse, which creates a friendly human-computer interface. Experiments show that this toolchain generation algorithm runs fast and accurately, which solves problems of the development and application of the DSP toolchain, and creates favorable conditions for the promotion of DSP. © 2021 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

JGC-IAGCL: Fusing joint graph convolution and intent-aware graph contrastive learning for explainable recommendation

引用

Information Fusion 2025年 123卷

作者： Yang, Zhi Lin, Chuan Qin, Yongbin Huang, Ruizhang Chen, Yanping Qin, Jiwei State Key Laboratory of Public Big Data Guizhou University Guiyang Guizhou550025 China Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and Technology Guizhou University Guiyang Guizhou550025 China College of Information Science and Engineering Xinjiang University Xinjiang Uygur Autonomous Region Urumqi830046 China

Graph contrastive learning (GCL) enhances recommendation accuracy by leveraging self-supervised features to refine node representations from large-scale unlabeled data. Traditional GCL-based recommendation models typically construct contrastive views via graph augmentation (e.g., stochastic node/edge dropout) or embedding-space perturbation, aiming to maximize representation consistency. However, these methods struggle to effectively model and interpret user preferences and consumption intents, limiting explainability and recommendation performance. To address these challenges, we propose JGC-IAGCL (Joint Graph Convolution and Intent-Aware Graph Contrastive Learning), an explainable recommendation framework. JGC-IAGCL integrates joint graph convolution to capture implicit user preferences and employs intent-aware graph contrastive learning to extract explicit user intents from user–item interactions. By fusing these features, our method generates evenly distributed, intent-propensity-aware user/item representations. Theoretical analysis shows that JGC-IAGCL mitigates popularity bias while enhancing the exposure of long-tail items. Extensive experiments on four highly sparse public datasets validate its effectiveness, demonstrating superior recommendation accuracy and improved interpretability. © 2025

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Integrating transcriptomics and biochemical analysis to understand the interactive mechanisms of the coexisting exposure of nanoplastics and erythromycin on Chlorella pyrenoidosa

引用

Chemosphere 2024年 349卷 140869页

作者： Yang, Wenfeng Gao, Pan Liu, Dongyang Wang, Wei Wang, Hanzhi Zhu, Liandong School of Resources & Environmental Science Hubei International Scientific and Technological Cooperation Base of Sustainable Resource and Energy Hubei Key Laboratory of Biomass-Resources Chemistry and Environmental Biotechnology Wuhan University Wuhan430079 China Key Laboratory of Molecular Biophysics of Ministry of Education College of Life Science and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China State Key Laboratory of Water Resources Engineering and Management Wuhan University Hubei Wuhan430072 China

Nanoplastics and antibiotics frequently co-exist in water polluted by algal blooms, but little information is available about interaction between substances. Erythromycin, as a representative of antibiotics, has been frequently detected in aquatic environments. This investigation attempted to reveal the interaction mechanism of nanoplastics and erythromycin on Chlorella pyrenoidosa. Results demonstrated that the joint toxicity of erythromycin and nanoplastics was dynamic and depended on nanoplastics concentration. Antagonistic effects of 1/2 or 1 EC50 erythromycin and nanoplastic concentration (10 mg/L) on the growth of C. pyrenoidosa was observed. The joint toxicity of 1/2 or 1 EC50 erythromycin and nanoplastic concentration (50 mg/L) was initially synergistic during 24–48 h and then turned to antagonistic during 72–96 h. Consequently, antagonistic effect was the endpoint for joint toxicity. Integration of transcriptomics and physiological biochemical analysis indicated that the co-existence of nanoplastics and erythromycin affected the signal transduction and molecular transport of algal cell membrane, induced intracellular oxidative stress, and hindered photosynthetic efficiency. Overall, this study provided a theoretical basis for evaluating the interactive mechanisms of nanoplastics and antibiotics. © 2023 Elsevier Ltd

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification

PM2: A New Prompting Multi-modal Model Paradigm for Few-shot...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhenwei Wang Qiule Sun Bingbing Zhang Weijian Su Pengfei Wang Jianxin Zhang Qiang Zhang Key Laboratory of Social Computing and Cognitive Intelligence (Ministry of Education) Dalian University of Technology China School of Computer Science and Technology Dalian University of Technology China School of Computer Science and Engineering Dalian Minzu University China School of Information and Communication Engineering Dalian University of Technology China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Few-shot learning has become a key technical solution for addressing the challenges of limited data and difficult annotation acquisition in medical image classification. However, relying solely on a single image modality proves inadequate for capture conceptual categories. This paper proposes a novel medical image classification paradigm based on a multi-modal foundation model, called PM 2 . In addition to the image modality, PM 2 introduces supplementary text input (prompt) to further describe images or conceptual categories and facilitate cross-modal few-shot learning. We empirically studied five different prompting schemes under this new paradigm. Furthermore, linear probing in multi-modal models only takes class token as input, ignoring the rich statistical data contained in high-level visual tokens. Therefore, we alternately perform linear classification on the feature distributions of visual tokens and class token. To effectively extract statistical information, we use global covariance pool with efficient matrix power normalization to aggregate the visual tokens. We then combine two classification heads: one for handling image class token and prompt representations encoded by the text encoder, and the other for classifying the feature distributions of visual tokens. Experiments on two medical datasets demonstrate that regardless of the prompting scheme, our method PM 2 outperforms its counterparts, achieving state-of-the-art performance.

关键词： Visualization Head Foundation models Feature extraction Data models Data mining Few shot learning Covariance matrices Medical diagnostic imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

MRLATO: An Adaptive Task Offloading Mechanism Based on Meta Reinforcement Learning in Edge computing Environment

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Peiying Liu, Jiamin Guizani, Maher Wang, Jian Kumar, Neeraj Tan, Lizhuang Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao266580 China Ministry of Education Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China University of Texas Arlington Computer Science and Engineering Department TX United States College of Science Qingdao266580 China Thapar University Department of Computer Science and Engineering Patiala147004 India Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Traditional cloud computing models struggle to meet the requirements of latency-sensitive applications when processing large amounts of data. As a solution, Multi-access Edge computing (MEC) extends computing resources to the edge of the network to reduce processing delays and improve user experience. However, in dynamically changing edge computing environments, effective decision making on whether to offload tasks to edge servers remains a core challenge. For this purpose, we propose MRLATO, an adaptive task offloading mechanism based on Meta Reinforcement Learning (MRL), which exploits a large amount of a priori knowledge of different tasks to achieve fast adaptation. The task offloading process is modelled as multiple Markov Decision Processes (MDPs) and solved using a Sequence to Sequence (Seq2Seq) neural network integrating multi-head attention and recursive task sequencing. It is shown by the experimental results that the proposed method has the lowest latency in all experimental settings and the convergence efficiency is improved by 14.06% compared to the traditional Deep Reinforcement Learning (DRL) algorithm. This research fully demonstrates the significant benefits of the deep integration of MRL with the edge computing domain, providing new optimisation ideas for task offloading decisions. © 1967-2012 IEEE.

关键词： Computation offloading

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：