检索结果-内蒙古大学图书馆

17th International symposium on Visual Computing, ISVC 2022

ISBN: (纸本)9783031207129

The proceedings contain 69 papers. The special focus in this conference is on Visual Computing. The topics include: Recognition of Aquatic Invasive Species Larvae Using Autoencoder-Based Feature Averaging;subspace Analysis for Multi-temporal Disaster Mapping Using Satellite imagery;open-Set Plankton Recognition Using Similarity Learning;sensor Fusion Operators for Multimodal 2D Object Detection;learning When to Say "I Don’t Know";Multi-class Detection and Tracking of Intracorporeal Suturing Instruments in an FLS Laparoscopic Box Trainer Using Scaled-YOLOv4;A New Approach to Visual Classification Using Concatenated Deep Learning for Multimode Fusion of EEG and image Data;deep Learning-Based Classification of Plant Xylem Tissue from Light Micrographs;vampNet: Unsupervised Vampirizing of Convolutional Networks;learning Representations for Masked Facial Recovery;RSI-Grad-CAM: Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-Based Localization;Deep Labeling of fMRI Brain Networks Using Cloud Based processing;semantic Segmentation Using Neural Ordinary Differential Equations;graphing the Future: Activity and Next Active Object Prediction Using Graph-Based Activity Representations;detecting Fall Actions of Videos by Using Weakly-Supervised Learning and Unsupervised Clustering Learning;multi-property Tensor-Based Learning for Abnormal Event Detection;depth-Based vs. Color-Based Pose Estimation in Human Action Recognition;Cross-Domain Learning in Deep HAR Models via Natural Language processing on Action Labels;visualizing Data Flows in computer graphics Programs for Code Comprehension and Debugging;a Practical Algorithm for Degree-k Voronoi Domains of Three-Dimensional Periodic Point Sets;deep Learning Based Shrimp Classification;end-to-End Deep Neural Network for Illumination Consistency and Global Illumination;pruning-Based Topology Refinement of 3D Mesh Using a 2D Alpha Mask;ConnectedUNets++: Mass Segmentation from Whole Mammographic images

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Semantic image Editing with Feature Shared Spatially-Adaptive Normalization

Efficient Semantic Image Editing with Feature Shared Spatial...

引用

International symposium on Advanced Computing and Communication (ISACC)

作者： Nishant Halagatti Bhuvan M C Abhishek N Jadhav Sai Pradyumna Chermala Padmashree Desai Venkat Ramana Peddigari Roopa Sheshadri Computer Science & Engineering KLE Technological University Hubballi India Visual Intelligence Samsung Research Institute Bangalore India

Recent advancements in GAN (Generative Adversarial Network) based image synthesis and image editing gave rise to powerful tools. One such tool for semantic image editing is SESAME (Semantic Editing of Scenes by Adding, Manipulating or Erasing objects). SESAME leverages SPADE (Spatially Adaptive Normalization) normalization and a novel two stream discriminator to set a new state-of-the-art. But the extensive use of computationally intensive SPADE layers makes it difficult to use in an interactive environment. We propose optimizations to reduce the redundancy in the network and improve the inference time. With our approach, we reduce the operations (in terms of MACs (Multiply-Accumulate)) of SESAME on Cityscapes dataset by about 5% and on ADE20k dataset by about 7%. Inference time is decreased by about 13% without much difference in the quality of the images produced.

关键词： Visualization image synthesis Semantics Redundancy graphics processing units Streaming media Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Benchmark Dataset for Repetitive Pattern Recognition on Textured 3D Surfaces

引用

computer graphics FORUM 2021年第5期40卷 1-8页

作者： Lengauer, Stefan Sipiran, Ivan Preiner, Reinhold Schreck, Tobias Bustos, Benjamin Graz Univ Technol Inst Comp Graph & Knowledge Visualizat Graz Austria Univ Chile Dept Comp Sci Santiago Chile

In digital archaeology, a large research area is concerned with the computer-aided analysis of 3D captured ancient pottery objects. A key aspect thereby is the analysis of motifs and patterns that were painted on these objects' surfaces. In particular, the automatic identification and segmentation of repetitive patterns is an important task serving different applications such as documentation, analysis and retrieval. Such patterns typically contain distinctive geometric features and often appear in repetitive ornaments or friezes, thus exhibiting a significant amount of symmetry and structure. At the same time, they can occur at varying sizes, orientations and irregular placements, posing a particular challenge for the detection of similarities. A key prerequisite to develop and evaluate new detection approaches for such repetitive patterns is the availability of an expressive dataset of 3D models, defining ground truth sets of similar patterns occurring on their surfaces. Unfortunately, such a dataset has not been available so far for this particular problem. We present an annotated dataset of 82 different 3D models of painted ancient Peruvian vessels, exhibiting different levels of repetitiveness in their surface patterns. To serve the evaluation of detection techniques of similar patterns, our dataset was labeled by archaeologists who identified clearly definable pattern classes. Those given, we manually annotated their respective occurrences on the mesh surfaces. Along with the data, we introduce an evaluation benchmark that can rank different recognition techniques for repetitive patterns based on the mean average precision of correctly segmented 3D mesh faces. An evaluation of different incremental sampling-based detection approaches, as well as a domain specific technique, demonstrates the applicability of our benchmark. With this benchmark we especially want to address the geometry processing community, and expect it will induce novel approaches for pattern

关键词： CCS Concepts center dot Information systems -> Evaluation of retrieval results Retrieval efficiency center dot General and reference -> Metrics center dot Computing methodologies -> image processing

来源：评论

学校读者我要写书评

暂无评论

GPU-Driven Optimization of Web-Based Volume Rendering in Peripheral Artery Disease CT Imaging

GPU-Driven Optimization of Web-Based Volume Rendering in Per...

引用

IEEE symposium on Bioinformatics and Bioengineering (BIBE)

作者： Mohammed A. AboArab Vassiliki T. Potsika Fragiska Sigala Alexis Theodorou Sylvia Vagena Dimitrios I. Fotiadis Unit of Medical Technology and Intelligent Information Systems University of Ioannina Ioannina Greece Electronics and Electrical Communication Engineering Dept. Faculty of Engineering Tanta Egypt First Propaedeutic Dept. of Surgery National and Kapodistrian University of Athens Athens Greece Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece

ISBN: (数字)9798331518622

ISBN: (纸本)9798331518639

This paper presents significant advancements in GPU-driven optimization for web-based volume rendering, which is specifically applied to peripheral artery disease (PAD) CT imaging. The proposed method enhances rendering efficiency and image quality, addressing the critical need for real-time, high-quality visualization of complex anatomical structures of PAD. Key improvements in the preprocessing pipeline, such as efficient chunking of large datasets, contribute to better GPU performance. The results demonstrate a substantial improvement over existing tools, with 95.37% reduction in render time, and 96.87% decrease in GPU memory usage compared with BlueLight, and significant memory optimization over Glance. These enhancements facilitate the detailed and interactive 3D visualization of vascular structures, which is crucial for accurate diagnosis and surgical planning. This paper highlights the potential of the proposed method to transform medical imaging practices, improving clinical outcomes for patients with PAD.

关键词： Visualization Three-dimensional displays Computed tomography graphics processing units Surgery Rendering (computer graphics) Real-time systems Optimization Arteries Diseases

来源：评论

学校读者我要写书评

暂无评论

EXION: Exploiting Inter-and Intra-Iteration Output Sparsity for Diffusion Models

EXION: Exploiting Inter-and Intra-Iteration Output Sparsity ...

引用

IEEE symposium on High-Performance computer Architecture

作者： Jaehoon Heo Adiwena Putra Jieon Yoon Sungwoong Yune Hangyeol Lee Ji-Hoon Kim Joo-Young Kim KAIST Daejeon Republic of Korea

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Over the past few years, diffusion models have emerged as novel solutions in AI industries, offering the capability to generate diverse, multi-modal outputs such as images, videos, and motions from input prompts (i.e., text). Despite their impressive capabilities, diffusion models face significant challenges in computing, including excessive latency and energy consumption due to the numerous iterations in model architecture. Although prior works specialized in transformer acceleration can be applied to diffusion models, given that transformers are key components, the problem of the iterative nature of diffusion models still needs to be *** this paper, we present EXION, the first software-hardware co-designed diffusion accelerator that solves the computation challenges of excessive iterations by exploiting the unique inter-and intra-iteration output sparsity in diffusion models. To this end, we propose two software-level optimizations in EXION. First, we introduce the FFN-Reuse algorithm that identifies and skips redundant computations in FFN layers across different iterations (i.e., inter-iteration sparsity). Second, we use a modified eager prediction method that employs two-step leading-one detection to accurately predict the attention score in diffusion models, skipping unnecessary computations within an iteration (i.e., intra-iteration sparsity). We also introduce a novel data compaction mechanism named ConMerge, which can enhance hardware utilization by condensing and merging large and sparse matrices into small and compact forms. Finally, EXION has a dedicated hardware architecture that supports the above sparsity-inducing algorithms, translating high output sparsity into improved energy efficiency and performance. To verify the feasibility of the EXION accelerator, we first demonstrate that it has no impact on accuracy in various types of multi-modal diffusion models, including text-to-motion, -audio, -image, and -video. We then instantiate EXION in b

关键词： graphics processing units computer architecture Prediction methods Diffusion models Transformers Prediction algorithms Energy efficiency Sparse matrices Servers Optimization

来源：评论

学校读者我要写书评

暂无评论

A Method to Improve the Precision of 2-Dimensioanl Size Measurement of Objects through image processing

A Method to Improve the Precision of 2-Dimensioanl Size Meas...

引用

International symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)

作者： Erbing Yang Meiqing Wang Hang Cheng Rong Liu Fei Chen College of Mathematics and Statistics Fuzhou University Fuzhou China College of Computer Science and Big Data Fuzhou University Fuzhou China

ISBN: (纸本)9781665454636

Aiming at the problem of two-dimensional size measurement of objects, in this paper, an image-based measurement model with a reference object is first proposed. The bounding boxes of the target objects and the reference are obtained through image processing technology which give the lengths of edges in pixel of objects. The reference object with known length of the edge is used to calculate the pixel unit, the actual size of a pixel and then the size of the target objects are obtained accordingly. Further, a correction model with four small reference objects is proposed to improve the measurement precision. The experimental results show the validity of the proposed models.

关键词： graphics Geometry image processing image edge detection Computational modeling Size measurement Calibration

来源：评论

学校读者我要写书评

暂无评论

GauSPU: 3D Gaussian Splatting Processor for Real-Time SLAM Systems

GauSPU: 3D Gaussian Splatting Processor for Real-Time SLAM S...

引用

IEEE/ACM International symposium on Microarchitecture (MICRO)

作者： Lizhou Wu Haozhe Zhu Siqi He Jiapei Zheng Chixiao Chen Xiaoyang Zeng State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

3D Gaussian Splatting (3DGS) has recently emerged as a promising technique in the realms of 3D vision and robotics. Its capacity for rapid rendering and high-fidelity reconstruction makes it an attractive candidate for integration into Simultaneous Localization and Mapping (SLAM) systems. However, existing 3DGS-based SLAM systems still suffer from inadequate tracking throughput due to tremendous recursion in volume rendering and irregular memory access for gradient backpropagation. To address these challenges, this paper proposes GauSPU, an algorithm-hardware co-designed accelerator for supporting real-time 3DGS-based SLAM. On the algorithm side, we present a sparse-tile-sampling (STS) method for efficient pose tracking. The STS focuses on informative image regions, discarding the rest to alleviate computational workload while maintaining accuracy. At the hardware level, we make twofold efforts. Firstly, we design a sparsity-adaptive ray recursion unit (SA-RRU) to accelerate volume rendering by leveraging irregular spatial sparsity. The SA-RRU introduces a sub-tile-wise execution pattern and a Morton-based thread allocation scheme to optimize sparsity utilization. Additionally, a sparsity-aware task dispatcher ensures efficient fine-grained task scheduling. Secondly, we propose a memory-access-relaxed backpropagation engine (MAR-BE) for efficient gradient aggregation. It comprises a gradient buffer unit (GBU) for coalescing partial gradients and a pose backward unit (PBU) for pipeline-fused backpropagation, collaboratively eliminating the costly atomic operations. Sufficient experiments demonstrate that, through the integration of GauSPU and GPU, the system achieves a throughput of 33.6 FPS for real-time pose tracking in 3DGS-SLAM, presenting a significant $63.9\times$ improvement in energy efficiency compared to the RTX3090 baseline.

关键词： Backpropagation Simultaneous localization and mapping Three-dimensional displays Instruction sets graphics processing units Rendering (computer graphics) Throughput Real-time systems Energy efficiency image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Controllable Motion-Blur Effects in Still images

引用

IEEE TRANSACTIONS ON VISUALIZATION AND computer graphics 2020年第7期26卷 2362-2372页

作者： Luo, Xuejiao Salamon, Nestor Z. Eisemann, Elmar Delft Univ Technol Comp Graph & Visualizat Lab CGV NL-2628 Delft Netherlands

Motion blur in a photo is the consequence of object motion during the image acquisition. It results in a visible trail along the motion of a recorded object and can be used by photographers to convey a sense of motion. Nevertheless, it is very challenging to acquire this effect as intended and requires much experience from the photographer. To achieve actual control over the motion blur, one could be added in a post process but current solutions require complex manual intervention and can lead to artifacts that mix moving and static objects incorrectly. In this paper, we propose a novel method to add motion blur to a single image that generates the illusion of a photographed motion. Relying on a minimal user input, a filtering process is employed to produce a virtual motion effect. It carefully handles object boundaries to avoid artifacts produced by standard filtering methods. We illustrate the effectiveness of our solution with various complex examples, including multi-directional blur, reflections, multiple objects, and illustrate how several motion-related artistic effects can be achieved. Our post-processing solution is an alternative to capturing the intended real-world motion blur directly and enables fine-grained control of the motion-blur effect.

关键词： Cameras Kernel image segmentation Motion segmentation image edge detection Trajectory Tools Motion blur long exposure image processing post-production

来源：评论

学校读者我要写书评

暂无评论

Efficient Heuristic Algorithm to Speed up GraphCut in GPU for image Stitching

Efficient Heuristic Algorithm to Speed up GraphCut in GPU fo...

引用

International symposium on Parallel Architectures, Algorithms and Programming (PAAP)

作者： Tai Nguyen Minh Bui Huong Ninh Tu Nguyen Hai Tien Tran Viettel Aerospace Institute Viettel Group

ISBN: (纸本)9781665452199

GraphCut algorithm has been widely utilized to solve various types of computer vision problems. Its expensive computational cost encouraged many researchers to improve the speed of the algorithm. Recent works proposed schemes that work on parallel computing platforms such as CUDA. However, the problem of low convergence speed prevents the usage of GraphCut for real time applications. In this paper, we propose global suppression heuristic to boost the convergence process of the algorithm. A parallel implementation of GraphCut algorithm on CUDA designed for the image stitching problem is introduced. Our method achieves up to 3× time boost on the graph of size 80×480 compared to the best sequential GraphCut algorithm while achieving satisfactory stitched images, suitable for panorama applications. Our source code will be soon available for further research.

关键词： computer vision Heuristic algorithms Source coding graphics processing units Programming Parallel processing Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Source Academy: A Web-based Environment for Learning Programming with SICP 2023

Source Academy: A Web-based Environment for Learning Program...

引用

Proceedings of the 54th ACM Technical symposium on computer Science Education V. 2

作者： Martin Henz National University of Singapore Singapore Singapore

ISBN: (纸本)9781450394338

The Source Academy is a community-built immersive online environment for learning computing with the book Structure and Interpretation of computer Programs (SICP). An interactive version of the textbook is integrated into the system, and the programming environment of the Source Academy allows learners to focus on SICP-specific sublanguages of JavaScript (Python and Scheme versions in preparation). The environment includes tools to support SICP's mental models for computational processes and data, including a stepper that animates the substitution model of Chapter 1, a data visualizer that supports the box-and-pointer diagrams of Chapter 2, and a visualizer for the environment model of Chapter *** system is web-based (no software installation required) and supports dynamically loadable plugins (modules) for programming with graphics, audio, image, and video processing. An extension called Source Academy @ X provides Learning Management System features such as the management of programming assessments and their manual and automatic grading. Source Academy @ X includes gamification components such as achievements, contests, levels, and a game that offers a narrative to contextualize the *** 45-minute demo provides CS educators with an overview of the Source Academy, including its tools, modules, and textbook integration, the Source Academy @ X extension for course management and a preview of Python and Scheme versions.

关键词： learning management systems structure and interpretation of computer programs computational thinking

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：