检索结果-内蒙古大学图书馆

Prompt learning in computer vision: a survey

Frontiers of Information Technology & Electronic Engineering 2024年第1期25卷 42-63页

作者： Yiming LEI Jingqi LI Zilong LI Yuan CAO Hongming SHAN Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200438China Institute of Science and Technology for Brain-Inspired Intelligence Fudan UniversityShanghai 200433China MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China

Prompt learning has attracted broad attention in computer vision since the large pre-trained visionlanguagemodels (VLMs) exploded. Based on the close relationship between vision and language information builtby VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligencegenerated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual promptlearning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, wereview the vision prompt learning methods and prompt-guided generative models, and discuss how to improve theefficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising researchdirections concerning prompt learning.

关键词： Prompt learning Visual prompt tuning(VPT) Image generation Image classification Artificial intelligence generated content(AIGC)

来源：评论

学校读者我要写书评

暂无评论

BERD+: A Generic Sequential Recommendation Framework by Eliminating Unreliable data with Item- and Attribute-level Signals

引用

ACM Transactions on Information Systems 2023年第2期42卷 1-33页

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Bin School of Computer Science and Engineering Northeastern University School of Computing Macquarie University China Australia Institute of High Performance Computing Centre for Frontier AI Research A*STAR Singapore School of Computer Science and Engineering Northeastern University China National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Key Laboratory of Data Analytics and Optimization for Smart Industry [Northeastern University Ministry of Education China

A preliminary work of our study was published at IJCAI’21 [47], which is substantially extended in the following aspects: (1) In Section 1, we analyze the necessity of introducing item attributes for detecting unreliable instances, together with the problems and challenges that attributes may bring in. (2) In Section 2, we add discussions about the limitations of existing attribute-aware recommender systems (Section 2.2) and denoising methods (Section 2.3) in the context of detecting unreliable instances. (3) In Section 4.2, we further conduct an in-depth analysis at the attribute level to demonstrate the capability of attributes for rectifying instance loss and uncertainty, as well as the disturbance caused by attributes. (4) We generalize BERD to a generic framework BERD+ in Section 5.1, equipped with novel modules, i.e., HU-GCN (Section 5.2) and EPE (Section 5.4), which properly incorporate item attributes while reducing their disturbance for rectifying instance uncer tainty (Section 5.5) and loss (Section 5.6). The generic BERD+ can be flexibly plugged into existing SRSs for performance enhanced recommendation via eliminating unreliable data. (5) In Section 6.2, we apply our BERD+ framework to seven state-of-the-art SRSs on five real-world datasets to illustrate its superiority. (6) To avoid unfair comparison caused by item attributes, we build and compare with the baseline that combines the original BERD and an advanced attribute-aware recommender system, KSR [19]. (7) For more comprehensive comparison, in Section 6.2.2, we compare BRED+ with two state-of-the-art denoising approaches;in Section 6.2.3, to examine the efficacy of HU-GCN and EPE, we compare HU-GCN with various attribute embedding techniques, i.e., variants of graph neural networks, and compare EPE with different attribute fusing methods, i.e., adding, concatenation, and weighted sum. (8) In Section 6.2.4, a detailed ablation study is conducted to verify the effectiveness of each module of BERD+. (

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A novel clinical artificial intelligence model for disease detection via retinal imaging

引用

The Innovation 2024年第2期5卷 11-12页

作者： Yidian Fu Liang Ma Sheng Wan Shengfang Ge Zhi Yang Department of Ophthalmology Ninth People’s HospitalShanghai JiaoTong University School of MedicineShanghai 200011China Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology Shanghai 200011China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationNanjing 210000China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing 210000China

Artificial intelligence(AI)is an emerging field in which computerized systems are used to carry out complex tasks in place of *** AI algorithms have been developed for disease diagnosis and prediction and treatment recommendation across various clinical data types,e.g.,chest X-rays,electrocardiograms,and other radiological images.1 In ophthalmology,particularly,great progress has been made in AI systems over the past *** fundus photography(CFP)and optical coherence tomography(OCT),which are readily available in routine clinical practice,are both mainstream and useful retinal imaging modalities in *** September 2023,the 2023 Lasker-Debakey Clinical Medical Research Award was awarded to three scientists for their work on OCT for accurate retinal disease detection.

关键词： clinical routine diagnosis

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification 35

Heterogeneous Directed Hypergraph Neural Network over abstra...

引用

35th International Conference on Software Engineering and Knowledge Engineering, SEKE 2023

作者： Yang, Guang Jin, Tiancheng Dou, Liang School of Computer Science and Technology East China Normal University Shanghai China NPPA Key Laboratory of Publishing Integration Development ECNUP Shanghai China

Code classification is a difficult issue in program understanding and automatic coding. Due to the elusive syntax and complicated semantics in programs, most existing studies use techniques based on abstract syntax tree (AST) and graph neural network (GNN) to create code representations for code classification. These techniques utilize the structure and semantic information of the code, but they only take into account pairwise associations and neglect the high-order correlations that already exist between nodes in the AST, which may result in the loss of code structural information. On the other hand, while a general hypergraph can encode high-order data correlations, it is homogeneous and undirected which will result in a lack of semantic and structural information such as node types, edge types, and directions between child nodes and parent nodes when modeling AST. In this study, we propose to represent AST as a heterogeneous directed hypergraph (HDHG) and process the graph by heterogeneous directed hypergraph neural network (HDHGN) for code classification. Our method improves code understanding and can represent high-order data correlations beyond paired interactions. We assess heterogeneous directed hypergraph neural network (HDHGN) on public datasets of Python and Java programs. Our method outperforms previous AST-based and GNN-based methods, which demonstrates the capability of our model. © 2023 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ShellGPT: Generative Pre-trained Transformer Model for Shell Language Understanding

ShellGPT: Generative Pre-trained Transformer Model for Shell...

引用

International Symposium on Software Reliability Engineering (ISSRE)

作者： Jie Shi Sihang Jiang Bo Xu Jiaqing Liang Yanghua Xiao Wei Wang Shanghai Key Laboratory of Data Science School of Computer Science Fudan University School of Computer Science and Technology Donghua University

This paper presents ShellGPT, a pre-trained language model specifically designed to enhance the understanding of shell language which plays a crucial role in IT operations. Based on the GPT series of models, ShellGPT is trained on a corpus that aligns shell language with natural language, aiming to inject domain-specific knowledge into the model. The technique of pre-tokenization is employed to maximize the reuse of a general-purpose vocabulary, facilitating effective model transfer from general domain. Furthermore, a new pre-training objective, named equivalent command learning, is proposed to refine the command representations through modeling function equivalence of commands. To evaluate the performance of ShellGPT, we conduct fine-tuning on various downstream tasks related to shell language understanding. These tasks include command recommendation, command correction, and translation from natural language to shell command. Our experimental results demonstrate that ShellGPT outperforms other baseline models in terms of performance across almost all evaluated tasks. The findings from our experiments highlight the effectiveness of Shell-GPT in enhancing shell language understanding and demonstrate its potential for practical applications in IT operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments

arXiv

引用

arXiv 2025年

作者： Cai, Yin Gu, Zhouhong Du, Zhaohan Ye, Zheyu Cao, Shaosheng Xu, Yiqian Feng, Hongwei Chen, Ping Institute of Big Data Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Computer Science Fudan University China Xiaohongshu Inc. China

Large Language Models (LLMs) have shown remarkable capabilities in environmental perception, reasoning-based decision-making, and simulating complex human behaviors, particularly in interactive role-playing contexts. This paper introduces the Multiverse Interactive Role-play Ability General Evaluation (MIRAGE), a comprehensive framework designed to assess LLMs' proficiency in portraying advanced human behaviors through murder mystery games. MIRAGE features eight intricately crafted scripts encompassing diverse themes and styles, providing a rich simulation. To evaluate LLMs' performance, MIRAGE employs four distinct methods: the Trust Inclination Index (TII) to measure dynamics of trust and suspicion, the Clue Investigation Capability (CIC) to measure LLMs' capability of conducting information, the Interactivity Capability Index (ICI) to assess role-playing capabilities and the Script Compliance Index (SCI) to assess LLMs' capability of understanding and following instructions. Our experiments indicate that even popular models like GPT-4 face significant challenges in navigating the complexities presented by the MIRAGE. The datasets and simulation codes are available in github. © 2025, CC BY.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Integrated Device for Controllable Droplet Generation and Detection on Open Array Chip 16th

Integrated Device for Controllable Droplet Generation and De...

引用

16th International Conference on Intelligent Robotics and Applications, ICIRA 2023

作者： Zhou, Zijian Wang, Jie Li, Yuxin Zhou, Jia Du, Lin School of Mechanical Engineering University of Shanghai for Science and Technology Shanghai200433 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200433 China State Key Laboratory of ASIC and System School of Microelectronics Fudan University Shanghai200433 China

ISBN: (纸本)9789819965007

The open array chip is an incredibly valuable tool for analyzing single molecule levels. Its efficiency, speed, compatibility, and precision make it an essential part of this process. However, efficient sample addition has become a significant challenge in the development of open array chips due to the coupling of the solid-liquid interface and the need for high-precision control. To address this challenge, we have developed an integrated adding sample device using technology of generates and detects controllable droplets array based on an open array chip with a biomimetic structure. This device combines a microfluidic chip, image detection, and smear speed regulation. We have studied the factors that affect the efficiency of sample loading, such as the number, speed and fluctuation of smears, and microwell size. The experiments have shown that the open array chip with the microwell’s diameter of 350 µm can generate arrays of ~470/cm2 ~8 nL droplets, significantly reducing controlled speed fluctuation errors by7.24% and volume fluctuation errors by 24% compared to traditional manual ways. The device has also displayed excellent performance on chips with microwell diameters of 120, 350, 700, and 1300 µm, respectively, with a notable first-time success rate of up to 91% on chips with microwell diameters of 120 µm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Microfluidic chips

来源：评论

学校读者我要写书评

暂无评论

Translating Motion to Notation: Hand Labanotation for Intuitive and Comprehensive Hand Movement Documentation 24

Translating Motion to Notation: Hand Labanotation for Intuit...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Ling Yang, WenRui Yu, Xinchun Xing, Junliang Zhang, Xiao-Ping Shenzhen Key Laboratory of Ubiquitous Data Enabling Shenzhen International Graduate School Tsinghua University Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798400706868

Symbols play a pivotal role in the documentation and dissemination of art. For instance, we use musical scores and dance notation to document musical compositions and choreographic movements. Existing hand representations do not fit well with hand movement documentation since (1) data-oriented representations, e.g., coordinates of hand keypoints, are not intuitive and vulnerable to noise, and (2) the sign language, another widely adopted representation for hand movements, focuses solely on semantic interaction rather than action encoding. To balance intuitiveness and precision, we propose a novel notation system, named Hand Labanotation (HL), for hand movement documentation. We first introduce a new HL dataset comprising 4M annotated images. Thereon, we propose a novel multi-view transformer architecture for automatically translating hand movements to HL. Extensive experiments demonstrate the promising capacity of our method for representing hand movements. This makes our method a general tool for hand movement documentation, driving various downstream applications like using HL to control robotic hands. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Program Testing Ability of Large Language Models for Code

The Program Testing Ability of Large Language Models for Cod...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Xiong, Weimin Guo, Yiwen Chen, Hao National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Tencent Security Big Data Lab China UC Davis United States

ISBN: (纸本)9798891761667

Recent development of large language models (LLMs) for code like CodeX and CodeT5+ shows promise in achieving code intelligence. Their ability of synthesizing program targeting a pre-defined algorithmic coding task has been intensively tested and verified on datasets including HumanEval and MBPP. Yet, evaluation of these LLMs from more perspectives (than just program synthesis) is also anticipated, considering their broad scope of applications. In this paper, we explore their ability of automatic test cases generation. We show intriguing observations and reveal how the quality of their generated test cases can be improved. Following recent work which uses generated test cases to enhance program synthesis, we further leverage our findings in improving the quality of the synthesized programs and show +11.77% and +4.22% higher code pass rates on HumanEval+ comparing with the GPT-3.5-turbo baseline and the recent state-of-the-art, respectively. Our code is publicly available at https://***/asdasxzxcq/TestCaseGen. © 2024 Association for Computational Linguistics.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Frequency domain deepfake detection based on two-stream neural network 14

Frequency domain deepfake detection based on two-stream neur...

引用

14th International Conference on Graphics and Image Processing, ICGIP 2022

作者： Xu, Yijia Zhang, Dong Dong Sun, Chengyu School of Computer Science Tongji University Shanghai201800 China Shanghai Key Laboratory of Urban Renewal and Spatial Optimization Technology Tongji University Shanghai200092 China

ISBN: (纸本)9781510666313

Benefiting from the progress of deep learning driven generative models, face forgery technologies have rapidly become mature, thus raising public concerns about the illegal usage of these technologies. Despite the fact that fake images and videos are often unrecognizable to human eyes, recent work has found that hidden artifacts can be exposed in frequency domain. Our meth-od introduces the idea of separating human face area using landmarks before mining the forgery patterns in frequency domain. This we believe can help the network learn more discriminative features, also, a two-stream learning framework combining single-frame pathway and multi-frame pathway is developed to mine frequency clues. Compared with previous methods, our approach showed good results while using a few training data and little time. The effectiveness of our method is shown on different versions of the FF++ and Celeb-DF dataset. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Deep learning

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：