检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mandari: Multi-Modal Temporal knowledge Graph-aware Sub-graph Embedding for Next-POI Recommendation

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-grap...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoqian Liu Xiuyun Li Yuan Cao Fan Zhang Xiongnan Jin Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China The Technology Innovation Center of Cultural Tourism Big Data of Hebei Province Chengde China Hebei Normal University for Nationalities Chengde China Knowledge Discovery and Data Mining Research Center Zhejiang Lab Hangzhou China

Next-POI recommendation aims to explore from user check-in sequence to predict the next possible location to be visited. Existing methods are often difficult to model the implicit association of multi-modal data with user choices. Moreover, traditional methods struggle to fully explore the variation of user preferences at variable time intervals. To tackle these limitations, we propose a Multi-Modal Temporal knowledge Graph-aware Sub-graph Embedding approach (Mandari). We first construct a novel Multi-Modal Temporal knowledge Graph. Based on the proposed knowledge graph, we integrate multi-modal information and leverage the graph attention network to calculate sub-graph prediction probability. Next, we implement a temporal knowledge mining method to model the segmentation and periodicity of user check-in and obtain temporal prediction probability. Finally, we fuse temporal prediction probability with the previous sub-graph prediction probability to obtain the final result. Extensive experiments demonstrate that our approach outperforms existing 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

An MRC Framework for Semantic Role labeling

arXiv

引用

arXiv 2021年

作者： Wang, Nan Li, Jiwei Meng, Yuxian Sun, Xiaofei Qiu, Han Wang, Ziyao Wang, Guoyin He, Jun Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China China Shannon.AI China Zhejiang University China Tsinghua University China University of Leeds United Kingdom Amazon Alexa AI United States

Semantic Role labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. In this paper, we propose to use the machine reading comprehension (MRC) framework to bridge this gap. We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense. The chosen predicate sense is then used to determine the semantic roles for that predicate, and these semantic roles are used to construct the query for another MRC model for argument labeling. In this way, we are able to leverage both the predicate semantics and the semantic role semantics for argument labeling. We also propose to select a subset of all the possible semantic roles for computational efficiency. Experiments show that the proposed framework achieves state-of-the-art or comparable results to previous work. Code is available at https://***/ShannonAI/MRC-SRL. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A deep learning system for predicting time to progression of diabetic retinopathy

引用

NATURE MEDICINE 2024年第2期30卷 358-359页

作者： [Anonymous] Shanghai Belt and Road International Joint Laboratory for Intelligent Prevention and Treatment of Metabolic Disorders Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Huadong Sanatorium Wuxi China Department of Ophthalmology Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong China Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Department of Ophthalmology Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing China Medical Records and Statistics Office Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Geriatrics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Tech

We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.

关键词： Diabetes complications Machine learning Predictive markers

来源：评论

学校读者我要写书评

暂无评论

Developing Global Digital Economy after COVID-19: Preface for ITQM 2020 & 2021

引用

Procedia Computer Science 2021年 199卷 1-9页

作者： Liu, Yubin Shi, Yong Wang, Yong Ergu, Daji Berg, Daniel Tien, James Li, Jianping Tian, Yingjie Southwest Minzu University Sichuan Chengdu610041 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China College of Engineering University of Miami Coral GablesFL33124 United States School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China

Welcome to the Eighth International Conference on Information Technology and Quantitative Management (ITQM 2020 & 2021), July 9-11, Chengdu, China. The theme of ITQM 2020 & 2021 is “Developing Global Digital Economy after COVID-19”. ITQM 2020 & 2021 is organized by International Academy of Information Technology and Quantitative Management (IAITQM), Southwest Minzu University, Chinese Academy of Sciences and University of Nebraska at Omaha. IAITQM was formally inaugurated on June 3, 2012 with more than 50 founding members from China, United States, Australia, Japan, Lithuania, Poland, Romania, Spain, Singapore, South Korea, The Netherlands, Turkey and other countries. The International Conference on Information Technology and Quantitative Management (ITQM), established by IAITQM, is a global forum for exchanging research findings and case studies that bridge the latest information technology and quantitative management techniques. It explores how the use of information technology techniques to improve quantitative management and how the development of management tools can reshape the development of information technology. The First International Conference on Information Technology and Quantitative Management (ITQM 2013) took place in Suzhou, China. The Second International Conference on Information Technology and Quantitative Management (ITQM 2014) was held in Moscow, Russia. The Third International Conference on Information Technology and Quantitative Management (ITQM 2015) was held at Rio de Janeiro, Brazil. The Forth International Conference on Information Technology and Quantitative Management (ITQM 2016) was held at Asan, Korea. The Fifth International Conference on Information Technology and Quantitative Management (ITQM 2017) was held at New Delhi, India. The Sixth International Conference on Information Technology and Quantitative Management (ITQM 2018) was hosted at Omaha, USA. The Seventh International Conference on Information Technology and Quantitative

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intersection-free Robot Manipulation with Soft-Rigid Coupled Incremental Potential Contact

arXiv

引用

arXiv 2023年

作者： Du, Wenxin Yao, Siqiong Wang, Xinlei Xu, Yuhang Xu, Wenqiang Lu, Cewu The School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China SJTU-Yale Joint Center of Biostatistics and Data Science National Center for Translational Medicine Shanghai Jiao Tong University China Qing Yuan Research Institute MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China ZenusTech Inc Philippines

This paper presents a novel simulation platform, ZeMa, designed for robotic manipulation tasks concerning soft objects. Such simulation ideally requires three properties: two-way soft-rigid coupling, intersection-free guarantees, and frictional contact modeling, with acceptable runtime suitable for deep and reinforcement learning tasks. Current simulators often satisfy only a subset of these needs, primarily focusing on distinct rigid-rigid or soft-soft interactions. The proposed ZeMa prioritizes physical accuracy and integrates the incremental potential contact method, offering unified dynamics simulation for both soft and rigid objects. It efficiently manages soft-rigid contact, operating 75x faster than baseline tools with similar methodologies like IPC-GraspSim. To demonstrate its applicability, we employ it for parallel grasp generation, penetrated grasp repair, and reinforcement learning for grasping, successfully transferring the trained RL policy to real-world scenarios. More experiments and videos can be found in the supplementary materials and on the website: https: //***/view/zema-ipc. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM Research

arXiv

引用

arXiv 2024年

作者： Cao, Qinglong Chen, Yuntian Lu, Lu Sun, Hao Zeng, Zhenzhong Yang, Xiaokang Zhang, Dongxiao MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315200 China Department of Statistics and Data Science Yale University New HavenCT06511 United States School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen China Gaoling School of Artificial Intelligence Renmin University of China Beijing China

Large-scale Vision-Language Models (VLMs) have demonstrated exceptional performance in natural vision tasks, motivating researchers across domains to explore domain-specific VLMs. However, the construction of powerful domain-specific VLMs demands vast amounts of annotated data, substantial electrical energy, and computing resources, primarily accessible to industry, yet hindering VLM research in academia. To address this challenge and foster sustainable and equitable VLM research, we present the Generalized Domain Prompt Learning (GDPL) framework. GDPL facilitates the transfer of VLMs’ robust recognition capabilities from natural vision to specialized domains, without the need for extensive data or resources. By leveraging small-scale domain-specific foundation models and minimal prompt samples, GDPL empowers the language branch with domain knowledge through quaternion networks, uncovering cross-modal relationships between domain-specific vision features and natural vision-based contextual embeddings. Simultaneously, GDPL guides the vision branch into specific domains through hierarchical propagation of generated vision prompt features, grounded in well-matched vision-language relations. Furthermore, to fully harness the domain adaptation potential of VLMs, we introduce a novel low-rank adaptation approach. Extensive experiments across diverse domains like remote sensing, medical imaging, geology, Synthetic Aperture Radar, and fluid dynamics, validate the efficacy of GDPL, demonstrating its ability to achieve state-of-the-art domain recognition performance in a prompt learning paradigm. Our framework paves the way for sustainable and inclusive VLM research, transcending the barriers between academia and industry. Copyright © 2024, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition

arXiv

引用

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Liu, Hongyan Lu, Zhiwu He, Jun Du, Xiaoyong Key Laboratory of Data Engineering Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China

Simultaneous Localization and Mapping (SLAM) and Autonomous Driving are becoming increasingly more important in recent years. Point cloud-based large scale place recognition is the spine of them. While many models have been proposed and have achieved acceptable performance by learning short-range local features, they always skip long-range contextual properties. Moreover, the model size also becomes a serious shackle for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net. On top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed respectively to learn both short-range local features and long-range contextual features. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art performance in terms of both recognition accuracy and running speed with a super-light model size (0.9M parameters). Meanwhile, for the purpose of further boosting efficiency, we introduce two simplified versions, which also achieve state-of-the-art performance and further reduce the model size to 0.8M and 0.4M respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Incrementally Zero-Shot Detection by an Extreme Value Analyzer

Incrementally Zero-Shot Detection by an Extreme Value Analyz...

引用

International Conference on Pattern Recognition

作者： Sixiao Zheng Yanwei Fu Yanxi Hou Academy for Engineering & Technology Fudan University Shanghai Engineering Research Center of AI& Robotics Engineering Research Center of AI & Robotics Ministry of Education School of Data Science MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University School of Data Science Fudan University

Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes. This paper introduces a novel and challenging task of Incrementally Zero-Shot Detection (IZSD), a practical strategy for both zero-shot learning and class-incremental learning in real-world object detection. An innovative end-to-end model - IZSD-EVer was proposed to tackle this task that requires incrementally detecting new classes and detecting the classes that have never been seen. Specifically, we propose a novel extreme value analyzer to detect objects from old seen, new seen, and unseen classes, simultaneously. Additionally and technically, we propose two innovative losses, i.e., background-foreground mean squared error loss alleviating the extreme imbalance of the background and foreground of images, and projection distance loss aligning the visual space and semantic spaces of old seen classes. Experiments demonstrate the efficacy of our model in detecting objects from both the seen and unseen classes, outperforming the alternative models on Pascal VOC and MSCOCO datasets.

关键词： Analytical models Visualization Semantics Object detection Pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

In-memory join algorithms on GPUs for large-data 21

In-memory join algorithms on GPUs for large-data

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Guo, Chengxin Chen, Hong Key Lab of Data Engineering and Knowledge Engineering of Ministry of Education School of Information Renmin University of China Beijing China

ISBN: (纸本)9781728120584

In traditional databases, join is one of the most computationally expensive operations in query processing. During the past years, GPU has been adopted to improve the performance of join processing because of the features of massive parallelism and high memory bandwidth. Limited by the capacity of GPU memory and the absence of virtual memory management, however, handling the relations that exceed the capacity of the GPU memory is a challenge for GPU-based join algorithms. Because of the high computing throughput provided by GPUs and the low bandwidth of data communication between the CPUs and the GPUs, data have to be partitioned to fit the features of GPUs and to reduce the cost of data transmission. Furthermore, a series of novel techniques have been developed on the GPUs, which can benefit the join algorithms. In this work, we focus on the optimizing of processing join operator on large relations and propose the designs of in-memory hash join and sort-merge join on GPUs. We present the data partition method on the GPUs implemented with a pipeline mechanism. Furthermore, the shuffle instructions and the CUDA streams are applied in our algorithms to best utilize the GPUs. Experimental results indicate that our hash join algorithm delivers up to 1.51X and 1.24X speedup over the state-of-the-art hash join algorithm on CPUs on NVIDIA GTX1080ti-Pascal GPU and TitanV-Volta GPU respectively. For sort-merge join, our algorithm achieves up to 3.52X and 2.21X improvements on the same GPUs respectively compared to the baselines on CPUs. © 2019 IEEE.

关键词： Graphics processing unit

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

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

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：