检索结果-内蒙古大学图书馆

Swin3D: A pretrained transformer backbone for 3D indoor scene understanding

Computational Visual Media 2025年第1期11卷 83-101页

作者： Yu-Qi Yang Yu-Xiao Guo Jian-Yu Xiong Yang Liu Hao Pan Peng-Shuai Wang Xin Tong Baining Guo Institute for Advanced Study Tsinghua UniversityBeijing 100084China Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Internet Graphics Group Microsoft Research AsiaBeijing 100080China Wangxuan Institute of Computer Technology Peking UniversityBeijing 100080China

The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific *** this paper,we introduce a pretrained 3D backbone,called Swin3D,for 3D indoor scene *** designed a 3D Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and *** also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network *** pretrained a large Swin3D model on a synthetic Structured3D dataset,which is an order of magnitude larger than the ScanNet *** model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3DIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.

关键词： 3D pretraining ponitcloud analysis trans-former backbone Swin Transformer 3D semantic segmentation 3D object detection

来源：评论

学校读者我要写书评

暂无评论

Engaging with emotions - The role of emotion in HCI 20

Engaging with emotions - The role of emotion in HCI

引用

20th British computer Society Conference on Human-computer Interaction: Engage, HCI 2006

作者： Peter, Christian Crane, Elizabeth Axelrod, Lesley Beale, Russell Fraunhofer Institute for Computer Graphics Joachim Jungius Str. 11 Rostock18059 Germany University of Michigan 401 Washtenaw Ave Ann ArborMI48108 United States School of Information Systems Computing and Mathematics Brunel University Uxbridge MiddlesexUB8 3PH United Kingdom Advanced Interaction Group School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

Emotions are of increasing interest to the HCI community and there is an enthusiastic spirit of adventure amongst researchers exploring this area. Much technical research has been done focussing on development of various proof-of-possibility studies and prototypical emotion components, but work done to date has been fragmented and lacks coherence. The goal of this workshop is to share information among researchers and practitioners working in this field through organized discussion and thematic working groups. This workshop will continue bringing people together, forming a community, supporting networking and collaboration to advocate coordinated work in this fascinating field of research. © BCS HCI group Conference: Engage, HCI *** right reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

arXiv

引用

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

A High-Dimensional Data Quality Metric using Pareto Optimality

A High-Dimensional Data Quality Metric using Pareto Optimali...

引用

19th Eurographics / IEEE VGTC Conference on Visualization, EuroVis 2017

作者： Post, Tobias Wischgoll, Thomas Hamann, Bernd Hagen, Hans Computer Graphics and HCI Group University of Kaiserslautern Germany Advanced Visual Data Analysis Group Wright State University United States Department of Computer Science University of California Davis United States

ISBN: (纸本)9783038680444

The representation of data quality within established high-dimensional data visualization techniques such as scatterplots and parallel coordinates is still an open problem. This work offers a scale-invariant measure based on Pareto optimality that is able to indicate the quality of data points with respect to the Pareto front. In cases where datasets contain noise or parameters that cannot easily be expressed or evaluated mathematically, the presented measure provides a visual encoding of the environment of a Pareto front to enable an enhanced visual inspection. © 2017 The Author(s) Eurographics Proceedings © 2017 The Eurographics Association.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Fast 3D Thinning of Medical Image Data based on Local Neighborhood Lookups

Fast 3D Thinning of Medical Image Data based on Local Neighb...

引用

18th Eurographics/IEEE VGTC Conference on Visualization, EuroVis 2016

作者： Post, Tobias Gillmann, Christina Wischgoll, Thomas Hagen, Hans Computer Graphics and HCI Group University of Kaiserslautern Germany Advanced Visual Data Analysis Group Wright State University United States

ISBN: (纸本)9783038680147

Three-dimensional thinning is an important task in medical image processing when performing quantitative analysis on structures, such as bones and vessels. For researchers of this domain a fast, robust and easy to access implementation is required. The Insight Segmentation and Registration Toolkit (ITK) is often used in medical image processing and visualization as it offers a wide range of ready to use algorithms. Unfortunately, its thinning implementation is computationally expensive and can introduce errors in the thinning process. This paper presents an implementation that is ready to use for thinning of medical image data. The implemented algorithm evaluates a moving local neighborhood window to find deletable voxels in the medical image. To reduce the computational effort, all possible combinations of a local neighborhood are stored in a precomputed lookup table. To show the effectiveness of this approach, the presented implementation is compared to the performance of the ITK library. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Enabling task-level scheduling on heterogeneous platforms 5

Enabling task-level scheduling on heterogeneous platforms

引用

5th Workshop on General-Purpose Computation on graphics Processing Units, GPGPU-5 - Held in Cooperation with ACM ASPLOS XVII

作者： Sun, Enqiang Schaa, Dana Bagley, Richard Rubin, Norman Kaeli, David Department of Electrical and Computer Engineering Northeastern University Boston MA United States Graphics Product Group Advanced Micro Devices Boxborough MA United States

ISBN: (纸本)9781450312332

OpenCL is an industry standard for parallel programming on heterogeneous devices. With OpenCL, compute-intensive portions of an application can be offloaded to a variety of processing units within a system. OpenCL is the first standard that focuses on portability, allowing programs to be written once and run seamlessly on multiple, heterogeneous devices, regardless of vendor. While OpenCL has been widely adopted, there still remains a lack of support for automatic task scheduling and data consistency when multiple devices appear in the system. To address this need, we have designed a task queueing extension for OpenCL that provides a high-level, unified execution model tightly coupled with a resource management facility. The main motivation for developing this extension is to provide OpenCL programmers with a convenient programming paradigm to fully utilize all possible devices in a system and incorporate flexible scheduling schemes. To demonstrate the value and utility of this extension, we have utilized an advanced OpenCL-based imaging toolkit called clSURF. Using our task queueing extension, we demonstrate the potential performance opportunities and limitations given current vendor implementations of OpenCL. Using a state-of-art implementation on a single GPU device as the baseline, our task queueing extension achieves a speedup up to 72.4%. Our extension also achieves scalable performance gains on multiple heterogeneous GPU devices. The performance trade-offs of using the host CPU as an accelerator are also evaluated. © 2012 ACM.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

CPU-assisted GPGPU on fused CPU-GPU architectures

CPU-assisted GPGPU on fused CPU-GPU architectures

引用

IEEE Symposium on High-Performance computer Architecture

作者： Yi Yang Ping Xiang Mike Mantor Huiyang Zhou Department of Electrical and Computer Engineering North Carolina State University USA Graphics Products Group Advanced Micro Devices Inc. Canada

This paper presents a novel approach to utilize the CPU resource to facilitate the execution of GPGPU programs on fused CPU-GPU architectures. In our model of fused architectures, the GPU and the CPU are integrated on the same die and share the on-chip L3 cache and off-chip memory, similar to the latest Intel Sandy Bridge and AMD accelerated processing unit (APU) platforms. In our proposed CPU-assisted GPGPU, after the CPU launches a GPU program, it executes a pre-execution program, which is generated automatically from the GPU kernel using our proposed compiler algorithms and contains memory access instructions of the GPU kernel for multiple thread-blocks. The CPU pre-execution program runs ahead of GPU threads because (1) the CPU pre-execution thread only contains memory fetch instructions from GPU kernels and not floating-point computations, and (2) the CPU runs at higher frequencies and exploits higher degrees of instruction-level parallelism than GPU scalar cores. We also leverage the prefetcher at the L2-cache on the CPU side to increase the memory traffic from CPU. As a result, the memory accesses of GPU threads hit in the L3 cache and their latency can be drastically reduced. Since our pre-execution is directly controlled by user-level applications, it enjoys both high accuracy and flexibility. Our experiments on a set of benchmarks show that our proposed pre-execution improves the performance by up to 113% and 21.4% on average.

关键词： graphics processing unit Prefetching Kernel Central Processing Unit computer architecture System-on-a-chip

来源：评论

学校读者我要写书评

暂无评论

Practicing what we preach: IEEE VR 2009 virtual program committee meeting

Practicing what we preach: IEEE VR 2009 virtual program comm...

引用

作者： Lindeman, Robert W. Reiners, Dirk Steed, Anthony Human Interaction in Virtual Environments Lab Department of Computer Science Worcester Polytechnic Institute Worcester MA United States Center for Advanced Computer Studies University of Louisiana Lafayette LA United States Virtual Environments and Computer Graphics Group Department of Computer Science University College London London United Kingdom

This article reports on the experience of conducting the program committee (PC) meeting for the IEEE VR 2009 conference in Second Life. More than 50 PC members from around the globe met virtually over a two-day period to decide which papers to accept for presentation at the conference. Survey responses from 42 of the PC members indicate generally positive feelings toward this meeting format, although several alterations will help improve interaction between attendees in future meetings. © 2009 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

The role of affect and emotion in HCI

The role of affect and emotion in HCI

引用

Lecture Notes in computer Science

作者： Beale, Russell Peter, Christian Advanced Interaction Group School of Computer Science University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom Fraunhofer Institute for Computer Graphics J. Jungius Str. 11 Rostock 18059 Germany

ISBN: (纸本)3540850988

Affect and emotion play an important role in our everyday lives: they are present whatever we do, wherever we are, wherever we go, without us being aware of them for much of the time. When it comes to interaction, be it with humans, technology, or humans via technology, we suddenly become more aware of emotion, either by seeing the other's emotional expression, or by not getting an emotional response while anticipating it. Given this, it seems only sensible to commit to affect and emotion in human-computer interaction, to investigate the underlying principles, to study the role they play, to develop methods to quantify them, and to finally build applications that make use of them. In this introductory chapter we discuss and give short accounts on present developments in the field, covering theoretical issues, user experience and design aspects, sensing issues, and report on some affective applications that have been developed. © 2008 Springer-Verlag Berlin Heidelberg.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Robust occupancy detection from stereo images

Robust occupancy detection from stereo images

引用

International Conference on Intelligent Transportation

作者： B. Alefs M. Clabian H. Bischof W. Kropatsch F. Khairallah Advanced Computer Vision GmbH-ACV Vienna Austria Advanced Computer Vision GmbH-ACV Austria Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group Institute of Computer Aided Automation Computer Science Department University of Technology Vienna Vienna Austria TRW Automotive GmbH Farmington Hills MI USA

Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occupant and the position of the occupant's head. This work presents a method for classification and occupant's head detection based on passive stereo vision. The proposed system uses depth surface analysis and scene statistics together with support vector machines for classification and selection of head candidates. Evaluation of the method shows 99% correct for classification and 98% correct for head detection, using large sets of image data, and image sequences recorded in a driving vehicle.

关键词： Robustness Magnetic heads Vehicle crash testing Sensor systems Stereo vision Layout Statistical analysis Support vector machines Support vector machine classification Vehicle detection

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：