检索结果-内蒙古大学图书馆

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

IEEE Transactions on Multimedia 2025年 27卷 3637-3649页

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Formal Verification Based Synthesis for Behavior Trees 9th

Formal Verification Based Synthesis for Behavior Trees

引用

9th International Symposium on Dependable Software Engineering: Theories, Tools and Applications, SETTA 2023

作者： Hong, Weijiang Chen, Zhenbang Li, Minglong Li, Yuhan Huang, Peishan Wang, Ji College of Computer National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China

ISBN: (纸本)9789819986637

Behavior trees (BTs) have been extensively applied in the area of both computer games and robotics, as the control architectures. However, the construction of BTs is labor-expensive, time-consuming, and even impossible as the complexity of task increases. In this work, we propose a formal verification based synthesis method to automatically construct BTs whose behaviors satisfy the given Linear Temporal Logic (LTL) specifications. Our method first explores candidate BTs by a grammar-based Monte Carlo Tree Search (MCTS), then the explored BTs are transformed into Communicating Sequential Processes (CSP) models. After that, we invoke the verifier to check the models’ correctness w.r.t. specifications, and provide feedback based on the verification result for guiding the search process. The application of our method on several representative robotic missions indicates its promising. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Behavior Trees CSP MCTS Synthesis

来源：评论

学校读者我要写书评

暂无评论

Boosting Meaningful Dependency Mining with Clustering and Covariance Analysis 40

Boosting Meaningful Dependency Mining with Clustering and Co...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Wang, Xi Jin, Ruochun Huang, Wanrong Tang, Yuhua Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Computer Science and Technology Department of Intelligent Data Science National University of Defense Technology Changsha China

ISBN: (纸本)9798350317152

Functional dependencies (FDs) form a valuable ingredient for various data management tasks. However, existing methods can hardly discover practical and interpretable FDs, especially in large noisy real-life datasets. This paper studies the problem of discovering meaningful functional dependencies (FDms) that utilize support and error parameters to capture interesting dependencies in such datasets and proposes an efficient discovery algorithm called FDM?. In order to scale with large datasets, FDM ? employs an efficient sampling method with accuracy guarantees to capture the differences between tuple pairs and to quantify the connection between support/error of dependencies on samples and those on the entire dataset. Moreover, it adopts a clustering-based correlated attributes extraction to divide the exponentially large search space into multiple small sub-spaces and proposes an easy-first traversal strategy with covariance-based guidance that quickly detects candidate dependencies and validates them. Additionally, we prove a covariance lower bound as an additional pruning criterion to reduce the search space. Extensive experiments on real-life and synthetic datasets demonstrate that FDM ? is 14 times faster than existing discovery algorithms on average, up to 31 times, and scales to larger datasets with the least memory cost. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

PancakeFS: A Write Efficiently and Read Optimized Filesystem 4

PancakeFS: A Write Efficiently and Read Optimized Filesystem

引用

4th International Conference on Consumer Electronics and computer Engineering, ICCECE 2024

作者： Wang, Yongkang Liu, Yang Chen, Zhiguang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Institute for Quantum Information College of Computer National University of Defense Technology State Key Laboratory of High-Performance Computing Changsha China

ISBN: (纸本)9798350384062

With the development of emerging technologies such as cloud computing and large AI models (such as LLM), many applications have placed higher demands on the intensive read and write processing of massive data. Addressing the limitations of traditional file systems, we propose PancakeFS, an LSM-Tree-based file system. Leveraging the write-friendly characteristics of LSM-Tree, PancakeFS exhibits efficient write performance. We improve read performance through the design of an inode allocation algorithm based on subtree partitioning and optimization of the disk layout for hot data reconstruction. Our experimental results demonstrate that PancakeFS outperforms Ext4 and TableFS in terms of both read and write performance. © 2024 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Medical image registration and its application in retinal images:a review

引用

Visual computing for Industry,Biomedicine,and Art 2024年第1期7卷 142-164页

作者： Qiushi Nie Xiaoqing Zhang Yan Hu Mingdao Gong Jiang Liu Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Singapore Eye Research Institute Singapore 169856Singapore State Key Laboratory of Ophthalmology Optometry and Visual ScienceEye HospitalWenzhou Medical UniversityWenzhou 325027China

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse informa-tion of images,which may be captured under different times,angles,or *** several surveys have reviewed the development of medical image registration,they have not systematically summarized the existing med-ical image registration *** this end,a comprehensive review of these methods is provided from traditional and deep-learning-based perspectives,aiming to help audiences quickly understand the development of medical image *** particular,we review recent advances in retinal image registration,which has not attracted much *** addition,current challenges in retinal image registration are discussed and insights and prospects for future research provided.

关键词： computer-aided diagnosis Medical image registration Deep learning Generative model Transformer Retina

来源：评论

学校读者我要写书评

暂无评论

SOOP: Efficient Distributed Graph Computation Supporting Second-Order Random Walks

引用

Journal of computer Science & technology 2021年第5期36卷 985-1001页

作者： Songjie Niu Dongyan Zhou State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China University of Chinese Academy of Sciences Beijing 100049China Bytedance Technology Beijing 100086China

The second-order random walk has recently been shown to effectively improve the accuracy in graph analysis *** work mainly focuses on centralized second-order random walk(SOW)*** algorithms rely on edge-to-edge transition probabilities to generate next random ***,it is prohibitively costly to store all the probabilities for large-scale graphs,and restricting the number of probabilities to consider can negatively impact the accuracy of graph analysis *** this paper,we propose and study an alternative approach,SOOP(second-order random walks with on-demand probability computation),that avoids the space overhead by computing the edge-to-edge transition probabilities on demand during the random ***,the same probabilities may be computed multiple times when the same edge appears multiple times in SOW,incurring extra cost for redundant computation and *** propose two optimization techniques that reduce the complexity of computing edge-to-edge transition probabilities to generate next random steps,and reduce the cost of communicating out-neighbors for the probability computation,*** experiments on real-world and synthetic graphs show that SOOP achieves orders of magnitude better performance than baseline precompute solutions,and it can efficiently computes SOW algorithms on billion-scale graphs.

关键词： second-order random walk(SOW) Node2Vec second-order PageRank distributed graph computation SOOP(second-order random walks with on-demand probability computation)

来源：评论

学校读者我要写书评

暂无评论

Bandwidth-tunable silicon nitride microring resonators

引用

Chinese Physics B 2022年第1期31卷 263-266页

作者： Jiacheng Liu Chao Wu Gongyu Xia Qilin Zheng Zhihong Zhu Ping Xu Hunan Provincial Key Laboratory of Novel Nano-Optoelectronic Information Materials and Device Institute for Quantum Information and State Key Laboratory of High Performance ComputingCollege of Advanced Interdisciplinary Studies&College of ComputerNational University of Defense TechnologyChangsha 410073China

We designed a reconfigurable dual-interferometer coupled silicon nitride microring *** tuning the integrated heater on interferometer's arms,the"critical coupling"bandwidth of resonant mode is continuously adjustable whose quality factor varies from 7.9×10^(4) to 1.9×10^(5) with the extinction ratio keeping higher than 25 *** a variety of coupling spanning from"under-coupling"to"over-coupling"were achieved,showing the ability to tune the quality factor from 6.0×10^(3) to 2.3×10^(5).Our design can provide an adjustable filtering method on silicon nitride photonic chip and contribute to optimize the nonlinear process for quantum photonics and all-optical signal processing.

关键词： silicon nitride microring resonators Mach-Zehnder interferometer ring filter nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models 38

FIRE: A Dataset for Feedback Integration and Refinement Eval...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MatGraph: An Energy-Efficient and Flexible CGRA Engine for Matrix-Based Graph Analytics 1

引用

22nd International Conference on Algorithms and architectures for Parallel Processing, ICA3PP 2022

作者： Tan, Long Yan, Mingyu Wang, Duo Li, Wenming Ye, Xiaochun Fan, Dongrui State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9783031226779

ISBN: (纸本)9783031226762

Graph analytics is increasingly important for solving problems in various fields. Matrix-based graph analytics has obtained much attention due to its high performance and ease of optimization. In the general architecture, due to the extremely high sparsity and complex connectedness of graphs, matrix-based graph analytics suffers from the deep and heavy pipeline as well as the low efficiency of the memory subsystem. Meanwhile, lots of accelerators based on application-specific integrated circuits (ASICs) for graph analytics are not flexible enough to support various matrix operations of diverse matrix-based graph algorithms, which have different graph semantics and dataflow. In this paper, we present MatGraph, an energy-efficient and flexible architecture to support matrix-based graph analytics efficiently. MatGraph is based on coarse-grained reconfigurable architectures (CGRAs) which have both high energy efficiency and flexibility. According to the matrix operations on graphs, we conduct an abstract from the operators to define reduced instructions and design a lightweight pipeline to achieve high parallelism of instructions in CGRAs. To eliminate the impact of the highly sparse graph data, we design a bitmap-aware instruction filtering unit to filter out invalid instructions for each PE and increase the on-chip reuse of instructions. Furthermore, we propose a bidirectional data-aware sparsity removing scheme to eliminate the sparsity and redundant off-chip data accesses. Overall, MatGraph achieves 9.35x, 2.28x speedup, and 11.17x, 7.15x energy savings on average compared to state-of-the-art (SOTA) CPU-based and GPGPU-based solutions respectively. Compared to the SOTA graph analytics accelerator, MatGraph also achieves 1.59x speedup and 1.61x less energy. © 2023, Springer Nature Switzerland AG.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

IVE: Accelerating Enumeration-Based Subgraph Matching via Exploring Isolated Vertices 40

IVE: Accelerating Enumeration-Based Subgraph Matching via Ex...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Jiang, Zite Zhang, Shuai Hou, Xingzhong Yuan, Mengting You, Haihang Institute of Computing Technology CAS State Key Lab of Processors Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijinz China Zhongguancun Laboratory Beijing China School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798350317152

The performance of the enumeration-based sub-graph matching, which searches all isomorphic subgraphs in the data graph, is crucial to various applications. The upper bound of the complexity for the enumeration-based method is exponential to the number of query graph vertices, denoted as n. We propose a novel subgraph matching algorithm called the Isolated Vertices Exploration (IVE). The IVE leverages isolated vertices during the reordering and enumeration phases, thereby significantly accelerating the subgraph matching process. During the enumeration, the isolated vertices can be matched by using a quick bipartite graph matching algorithm. Consequently, the complexity of matching the remaining non-isolated vertices is exponential to the number of non-isolated vertices, denoted as n'. For the reordering, we designed the Maximum Deleted Edges (MDE) to minimize n'. MDE iteratively selects the query vertex with the maximum edges. According to the experimental results, n' is less than 0.8n for 99.8% of arbitrary graphs. Moreover, IVE outperforms the state-of-the-art algorithms in various scenarios with different sizes, sparsities and fields, achieving a performance speedup of up to 80.3x. © 2024 IEEE.

关键词： Iterative methods

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：