检索结果-内蒙古大学图书馆

7th Chinese conference on Pattern Recognition and Computer Vision

作者： Ye, Zongxin Li, Wenyu Liu, Sidun Qiao, Peng Dou, Yong Natl Univ Def Technol Coll Comp Natl Key Lab Parallel & Distributed Comp Changsha Peoples R China

ISBN: (纸本)9789819785070;9789819785087

Structure from Motion (SfM) is a fundamental computer vision technique that recovers scene structure and camera motion from multi-view images. When facing large-scale scenarios, cluster-based methods are commonly employed to improve reconstruction efficiency. However, these methods currently face challenges regarding their limited robustness, redundant computation, and drift. To address these issues, we propose a unified pipeline called ER-SfM, which enhances the three key aspects of cluster-based SfM: image clustering, local reconstruction, and merging. In terms of image clustering, we propose a three-stage image clustering method to ensure adequate and reliable connections between clusters. In the local reconstruction stage, we expedite the reconstruction process by eliminating duplicate point cloud computation. In the final merging stage, we introduce a global merging algorithm without scale ambiguity to address the drift problem. Extensive experimental results demonstrate the superior performance of our method in terms of both robustness and efficiency compared to state-of-the-art methods.

关键词： parallel structure from motion 3D Reconstruction image clustering Global averaging

来源：评论

学校读者我要写书评

暂无评论

Innovations in mathematical modeling, AI, and optimization techniques

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-4页

作者： Ohue, Masahito Yasuo, Nobuaki Takata, Masami Inst Sci Tokyo Sch Comp Dept Comp Sci Yokohama Kanagawa 2268501 Japan Inst Sci Tokyo Acad Convergence Mat & Informat TAC MI Tokyo 1528550 Japan Nara Womens Univ Res Grp Informat & Commun Technol Life Nara 6308506 Japan

This special issue is dedicated to examining the rapidly evolving fields of artificial intelligence, mathematical modeling, and optimization, with particular emphasis on their growing importance in computational science. It features the most notable papers from the "Mathematical Modeling and Problem Solving" workshop at PDPTA'24, the 30th International conference on parallel and distributed processing Techniques and Applications. The issue showcases pioneering research in areas such as natural language processing, system optimization, and high-performance computing. The nine selected studies include novel AI-driven methods for chemical compound generation, historical text recognition, and music recommendation, along with advancements in hardware optimization through reconfigurable accelerators and vector register sharing. Additionally, evolutionary and hyper-heuristic algorithms are explored for sophisticated problem-solving in engineering design, and innovative techniques are introduced for high-speed numerical methods in large-scale systems. Collectively, these contributions demonstrate the significance of AI, supercomputing, and advanced algorithms in driving the next generation of scientific discovery.

关键词： Mathematical modeling Artificial intelligence parallel and distributed computing Reconfigurable computing Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Reproducing Performance of Data-Centric Python by SCC Team From National Tsing Hua University

引用

IEEE TRANSACTIONS ON parallel AND distributed SYSTEMS 2025年第5期36卷 821-825页

作者： Chang, Fu-Chiang Huang, En-Ming Kuo, Pin-Yi Mou, Chan-Yu Ting, Hsu-Tzu Wu, Pang-Ning Chou, Jerry Natl Tsing Hua Univ Dept Comp Sci Hsinchu 300 Taiwan

As part of the Student Cluster Competition at the SC22 conference, this work aims to reproduce the performance evaluations of the Data Centric (DaCe) Python framework by leveraging Intel MKL and NVIDIA CUDA interface. The evaluations are conducted on a single CPU-based node, NVIDIA A100 GPUs, and an eight-node cloud supercomputer. Our experimental results successfully reproduce the performance evaluations on our cluster. Additionally, we provide insightful analysis and propose effective methods for achieving higher performance when utilizing DaCe as an acceleration library.

关键词： Graphics processing units Benchmark testing Libraries Python parallel processing Runtime Kernel parallel computing reproducibility Student Cluster Competition

来源：评论

学校读者我要写书评

暂无评论

Application of Various Novel Computer image processing (CIP) Algorithms in Digital Media Art images

Application of Various Novel Computer Image Processing (CIP)...

引用

2025 International conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Du, Xian Shanghai Institute of Visual Arts Shanghai201620 China

ISBN: (纸本)9798331509828

With the continuous development of digital image processing algorithms, its application scenarios have been integrated from the simple research of a single image and a single algorithm to a multi-algorithm fusion analysis paradigm. Therefore, this study proposes a digital media art image analysis framework that combines multiple computer image processing (CIP) algorithms. This breakthrough covers three core architectures: image edge extraction, image style transfer, and image compression. In the image edge extraction module, this study designed an improved edge detection algorithm based on de-noising auto-encoder. This algorithm improves the accuracy of edge detection through multi-directional feature extraction and (I, O)-fuzzy rough set optimization, while maintaining global stability. In the image style transfer module, this study proposed a dual-module network. The network includes a texture translation network and a perceptual loss network, and achieves cross-domain style transfer through a fusion model. At the same time, the algorithm optimizes the perceptual loss function to enhance semantic matching capabilities. In the image compression module, this study uses chaotic systems to construct an optimized measurement matrix. Specifically, through a distributed data parallel training framework, a compression method based on the LPAC gradient sparse algorithm is constructed. By testing the three modules separately, the experimental results confirm the effectiveness of the proposed algorithm. © 2025 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Improving Visual Question Answering by image Captioning

引用

IEEE ACCESS 2025年 13卷 46299-46311页

作者： Shao, Xiangjun Dong, Hongsong Wu, Guangsheng Hunan Univ Arts & Sci Sch Comp & Elect Engn Changde 415000 Peoples R China Key Lab Hunan Prov Control Technol Distributed Ele Changde 415000 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Lyuliang Univ Dept Comp Sci Luliang 033000 Peoples R China Xinyu Univ Sch Math & Comp Sci Xinyu 338004 Peoples R China

Visual Question Answering (VQA) is a challenging task that bridges the computer vision and natural language processing communities. It provide natural language answers to questions related to an associated image. Most existing VQA methods focus on the fusion and inference of visual features with the textual question. However, visual features often lack the necessary semantic information required to answer the questions accurately. To address this limitation, we propose a novel approach called Question-Guided parallel Attention (QGPA), which effectively leverages the semantic information provided by an embedded image captioning model to answer related questions. First, we introduce an Attention-Aware (AA) mechanism that extends the traditional attention mechanism, helping to filter out incorrect or irrelevant information during answer prediction. Second, QGPA incorporates AA, which simultaneously utilizes visual features and semantic information from the embedded image captioning model to answer questions. Experiments results demonstrate that the accuracy of "Overall" of our proposed model delivers 72.57% and 72.55% on the test-dev and test-std split set of VQA-v2.0 dataset, respectively, which outperforms most existing VQA methods. The experiment results and ablation studies demonstrate that the proposed method has good performance.

关键词： Visualization Semantics Long short term memory Question answering (information retrieval) Predictive models Accuracy Knowledge based systems Feature extraction Information filters Context modeling Deep learning image captioning multimodal learning visual question answering

来源：评论

学校读者我要写书评

暂无评论

24th International conference on Algorithms and Architectures for parallel processing, ICA3PP 2024

24th International Conference on Algorithms and Architecture...

引用

24th International conference on Algorithms and Architectures for parallel processing, ICA3PP 2024

ISBN: (纸本)9789819615278

The proceedings contain 131 papers. The special focus in this conference is on Algorithms and Architectures for parallel processing. The topics include: MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework;SSC: An SRAM-Based Silence Computing Design for On-chip Memory;TP-BFT: A Faster Asynchronous BFT Consensus with parallel Structure;LTP: A Lightweight On-Chip Temporary Prefetcher for Data-Dependent Memory Accesses;A Neural Network-Based PUF Protection Method Against Machine Learning Attack;Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs;multidimensional Intrinsic Identity Construction and Dynamic Seamless Authentication Schemes in IoT Environments;invisible Backdoor Attack with image Contours Triggers;finestra: Multi-aggregator Swarm Learning for Gradient Leakage Defense;DIsFU: Protecting Innocent Clients in Federated Unlearning;multiple-Round Aggregation of Abstract Semantics for Secure Heterogeneous Federated Learning;dynamic Privacy Protection with Large Language Model in Social Networks;a Dynamic Symmetric Searchable Encryption Scheme for Rapid Conjunctive Queries;a Data Watermark Scheme Base on Data Converted Bitmap for Data Trading;distributed Incentive Algorithm for Fine-Grained Offloading in Vehicular Ad Hoc Networks;mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation;AW-YOLOv9: Adverse Weather Conditions Adaptation for UAV Detection;efficient and Privacy-Preserving Ranking-Based Federated Learning;on-Chain Dynamic Policy Evaluation for Decentralized Access Control;DPG-FairFL: A Dual-Phase GAN-Based Defense Framework Against image-Based Fairness Data Poisoning Attacks in Federated Learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

24th International conference on Algorithms and Architectures for parallel processing, ICA3PP 2024

24th International Conference on Algorithms and Architecture...

引用

24th International conference on Algorithms and Architectures for parallel processing, ICA3PP 2024

ISBN: (纸本)9789819615476

关键词：

来源：评论

学校读者我要写书评