检索结果-内蒙古大学图书馆

PVT v2:Improved baselines with Pyramid vision Transformer

Computational Visual Media 2022年第3期8卷 415-424页

作者： Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo Ling Shao Shanghai AI Laboratory Shanghai 200232China Department of Computer Science and Technology NanjingUniversityNanjing 210023China Department of Computer Science the University ofHong KongHong Kong 999077China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210014China Computer Vision Lab ETH ZurichZurich 8092Switzerland SenseTime Beijing 100080China Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Transformers have recently lead to encouraging progress in computer *** this work,we present new baselines by improving the original Pyramid vision Transformer(PVT v1)by adding three designs:(i)a linear complexity attention layer,(ii)an overlapping patch embedding,and(iii)a convolutional feed-forward *** these modifications,PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification,detection,and *** particular,PVT v2 achieves comparable or better performance than recent work such as the Swin *** hope this work will facilitate state-ofthe-art transformer research in computer *** is available at https://***/whai362/PVT.

关键词： transformers dense prediction image classification object detection semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

ALO-SBD: A Hybrid Shot Boundary Detection Technique for Video Surveillance System 26th

ALO-SBD: A Hybrid Shot Boundary Detection Technique for Vi...

引用

26th annual International Conference on Advanced Computing and Communications, ADCOM 2020

作者： Chakraborty, Saptarshi Thounaujam, Dalton Meitei Singh, Alok Pal, Gautam Computer Vision Laboratory Computer Science and Engineering Department National Institute of Technology Silchar India Tripura Institute of Technology Agartala India

ISBN: (纸本)9789811900181

A novel shot boundary detection (SBD) method is proposed using nature-inspired algorithm called ant lion optimizer (ALO). Here, ALO is used to optimize the weights of the feed-forward neural network (FNN) which in turn enhances the performance of the system. A hybrid technique is formulated using the aid of continuity matrix () and an outlier to fetch possible set of transition frames. Using a threshold δ1, the actual transition frames are drawn out from all the possible transition frames. For the experimentation, some challenging videos from TRECVid 2001 and 2007 datasets are selected. ALO-SBD generates better performance in terms of F1 score and outperforms recent state-of-the-art techniques in the field of SBD. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Low 3D-HEVC Depth Map Intra Modes Selection Complexity Based on Clustering Algorithm and an Efficient Edge Detection 1st

Low 3D-HEVC Depth Map Intra Modes Selection Complexity Based...

引用

1st edition of the International Conference on Artificial Intelligence and Green Computing, ICAIGC 2023

作者： Hamout, Hamza Elyousfi, Abderrahmane Computer Systems and Vision Laboratory Faculty of Sciences Ibn-Zohr University Agadir80000 Morocco Department of Computer Science National Engineering School of Applied Sciences Ibn-Zohr University Agadir80000 Morocco

ISBN: (纸本)9783031465833

In 2016, ITU-T Video Coding Experts Group (VCEG) and ISO/IEC MPEG finalize the recent 3-dimensional video coding standard founded on Multi-view texture Videos plus Depth maps (MVD) format called, the 3D extension of High-Efficiency Video Coding (3D-HEVC). In the current design of 3D-HEVC, the conventional intra-prediction modes and Depth Modeling Modes are exploited sophistically to improve the depth map coding performance. However, the coding efficiency improvement is achieved at the cost of computational complexity load, which obstructs 3D-High Efficiency Video Coding standards from practical world applications. In the 3D-HEVC, the depth maps are described by enormous homogeneous regions, and it is observed that for most of the cases, the DMMs and all or the majority of angular intra modes could be skipped for the homogenous area. Thus, we propose an efficient intra-coding model decision for a depth map founded on the clustering algorithm and edge detection to resolve the above-mentioned complexity increase. Experimental results demonstrate that the proposed intra-coding model decision for depth map can decrease the encoding time up to 41.35%, with insignificant loss of rate-distortion performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

CSDNet: cross-sketch with dual gated attention for fine-grained image captioning network

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Hossain, Md. Shamim Aktar, Shamima Hossen, Md. Bipul Hossain, Mohammad Alamgir Gu, Naijie Huang, Zhangjin School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230027 China Deqing Alpha Innovation Institute Huzhou313299 China Department of Mathematics Jashore University of Science and Technology Jashore7408 Bangladesh Department of Statistics Begum Rokeya University Rangpur5404 Bangladesh National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Anhui Hefei230027 China

In the realm of extracting inter and intra-modal interactions, contemporary models often face challenges such as reduced computational efficiency, particularly when dealing with lengthy visual sequences. To address these issues, this study introduces an innovative model, the Cross-Sketch with Dual Gated Attention Network (CSDNet), designed to handle second-order intra- and inter-modal interactions by integrating a couple of attention modules. Leveraging bilinear pooling to effectively capture these second-order interactions typically requires substantial computational resources due to the processing of large-dimensional tensors. Due to these resource demands, the first module Cross-Sketch Attention (CSA) is proposed, which employs Cross-Tensor Sketch Pooling on attention features to reduce dimensionality while preserving crucial information without sacrificing caption quality. Furthermore, to enhance caption by integrating another novel attention module, Dual Gated Attention (DGA), which contributes additional spatial and channel-wise attention distributions to improve caption generation performance. Our method demonstrates significant computational efficiency improvements, reducing computation time per epoch by an average of 13.54% compared to the base model, which leads to expedited convergence and improved performance metrics. Additionally, we observe a 0.07% enhancement in the METEOR score compared to the base model. Through the application of reinforcement learning optimization, our model achieves a remarkable CIDEr-D score of 132.2% on the MS-COCO dataset. This consistently outperforms baseline performance across a comprehensive range of evaluation metrics. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

Feature Correlation Aggregation: on the Path to Better Graph...

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Zhou, Jieming Zhang, Tong Fang, Pengfei Petersson, Lars Harandi, Mehrtash Australian National University College of Engineering and Computer Science Canberra Australia Image and Visual Representation Laboratory Epfl Lausanne Switzerland Imaging and Computer Vision Group Csiro Canberra Australia Monash University Department of Electrical and Computer Systems Engineering Melbourne Australia

ISBN: (纸本)9798350382204

Prior to the introduction of Graph Neural Networks (GNNs), modelling and analyzing irregular data, particularly graphs, was thought to be the Achilles' heel of deep learning. The core concept of GNNs is to find a representation by recursively aggregating the representations of a central node and those of its neighbor, and many GNNs' designs have demonstrated its success. However, most only focus on using the first-order information between a node and its neighbors. In this paper, we introduce a central node permutation variant function through a frustratingly simple and innocent-looking modification to the core operation of a GNN, namely the Feature cOrrelation aGgregation (FOG) module, which learns the second-order information from feature correlation between a node and its neighbors in the pipeline. By adding FOG into existing variants of GNNs, we empirically verify this second-order information complements the features generated by original GNNs across a broad set of benchmarks. A tangible boost in the model's performance is observed where the model surpasses previous state-of-the-art results by a significant margin while employing fewer parameters. e.g., 26.202% improvement on a real-world molecular dataset using graph convolutional networks. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Video Polyp Segmentation: A Deep Learning Perspective

引用

Machine Intelligence Research 2022年第6期19卷 531-549页

作者： Ge-Peng Ji Guobao Xiao Yu-Cheng Chou Deng-Ping Fan Kai Zhao Geng Chen Luc Van Gool Research School of Engineering Australian National UniversityCanberra 2601Australia College of Computer and Control Engineering Minjiang UniversityFuzhou 350108China Department of Computer Science Johns Hopkins UniversityBaltimore 21218USA Computer Vision Laboratory ETH ZürichZürich 8092Switzerland Department of Radiological Sciences University of CaliforniaLos Angeles 90095USA School of Computer Science and Engineering Northwestern Polytechnical UniversityXi′an 710072China

We present the first comprehensive video polyp segmentation(VPS)study in the deep learning *** the years,developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation *** address this issue,we first introduce a high-quality frame-by-frame annotated VPS dataset,named SUN-SEG,which contains 158690colonoscopy video frames from the well-known *** provide additional annotation covering diverse types,i.e.,attribute,object mask,boundary,scribble,and ***,we design a simple but efficient baseline,named PNS+,which consists of a global encoder,a local encoder,and normalized self-attention(NS)*** global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations,which are then progressively refined by two NS *** experiments show that PNS+achieves the best performance and real-time inference speed(170 fps),making it a promising solution for the VPS ***,we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based ***,we discuss several open issues and suggest possible research directions for the VPS *** project and dataset are publicly available at https://***/GewelsJI/VPS.

关键词： Video polyp segmentation(VPS) dataset self-attention colonoscopy abdomen

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Dependency-Aware Tasks Offloading in Digital Twin Edge Networks

Reinforcement Learning for Dependency-Aware Tasks Offloading...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Xiong, Jiaxin Chen, Lingxiao Zhao, Liang Chang, Wei China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology Yichang China Saint Joseph's University Computer Science Department United States

ISBN: (纸本)9798350312270

Mobile Edge Computing (MEC) and Digital Twin (DT) technologies are crucial to meet the quality of service (QoS) of emerging applications. MEC sinks the processing power of the cloud to the edge and responds to users' requests in real time. DT can collect and analyze a large amount of data to make the optimal decision. However, the combination of MEC and DT is always ignored. Furthermore, it is more challenging to offload dependency-aware tasks efficiently. Therefore, this paper aims to present a more comprehensive survey of DT edge networks (DTEN). We first discuss prior knowledge about DTEN, such as its basic concepts, advantages, and application scenarios. Then, we highlight the research challenges for dependency-aware task offloading in recent years, including computation offloading, resource allocation, service caching, and edge collaboration. Furthermore, we introduce Reinforcement Learning (RL) for networking systems in detail. Finally, we conduct a typical dependency-aware task offloading case study to understand DTEN more deeply. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generalized Few-shot 3D Point Cloud Segmentation with vision-Language Model

arXiv

引用

arXiv 2025年

作者： An, Zhaochong Sun, Guolei Liu, Yun Li, Runjia Han, Junlin Konukoglu, Ender Belongie, Serge Department of Computer Science University of Copenhagen Denmark Computer Vision Laboratory ETH Zurich Switzerland College of Computer Science Nankai University China Department of Engineering Science University of Oxford United Kingdom

Generalized few-shot 3D point cloud segmentation (GFS-PCS) adapts models to new classes with few support samples while retaining base class segmentation. Existing GFS-PCS methods enhance prototypes via interacting with support or query features but remain limited by sparse knowledge from few-shot samples. Meanwhile, 3D vision-language models (3D VLMs), generalizing across open-world novel classes, contain rich but noisy novel class knowledge. In this work, we introduce a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL. Specifically, we present a prototype-guided pseudo-label selection to filter low-quality regions, followed by an adaptive infilling strategy that combines knowledge from pseudo-label contexts and few-shot samples to adaptively label the filtered, unlabeled areas. Additionally, we design a novel-base mix strategy to embed few-shot samples into training scenes, preserving essential context for improved novel class learning. Moreover, recognizing the limited diversity in current GFS-PCS benchmarks, we introduce two challenging benchmarks with diverse novel classes for comprehensive generalization evaluation. Experiments validate the effectiveness of our framework across models and datasets. Our approach and benchmarks provide a solid foundation for advancing GFS-PCS in the real world. The code is at here. © 2025, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Introduction to the Special Section on Video and Language

引用

IEEE Transactions on Circuits and Systems for Video Technology 2022年第1期32卷 1-4页

作者： Mei, Tao Corso, Jason J. Kim, Gunhee Luo, Jiebo Shen, Chunhua Zhang, Hanwang Computer Vision and Multimedia Laboratory Jd Explore Academy *** Beijing100101 China Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Department of Computer Science and Engineering Seoul National University Gwanak-gu Seoul08826 Korea Republic of Department of Computer Science University of Rochester RochesterNY14627 United States College of Computer Science and Technology Zhejiang University Hangzhou310058 China School of Computer Science and Engineering Nanyang Technological University 639798 Singapore

computer vision (CV) and Natural Language Processing (NLP) are two most fundamental disciplines under a broad area of artificial intelligence (AI). CV is regarded as a field of research that explores the techniques to teach computers to see and understand digital content such as images and videos. NLP is a branch of linguistics that enables computers to process, interpret, and even generate human language. With the rise and development of deep learning over the past decade, there has been a steady momentum of innovation and breakthroughs that convincingly push the limits and improve the state-of-the-art of both vision and language modeling. An interesting observation is that the research in the two areas starts to interact, with a significant growth in both the volume of publications and extensive applications. Meanwhile, many previous experiences have shown that this can naturally build up the circle of human intelligence.

关键词： Special issues and sections computer vision Question answering (information retrieval) Natural language processing Visual captioning

来源：评论

学校读者我要写书评

暂无评论

Autonomous UAV-Based Monitoring of Fuel Tanks Using YOLOv8 for Global Energy Management

Autonomous UAV-Based Monitoring of Fuel Tanks Using YOLOv8 f...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Nesli S. Azdavay Leslawa M. Nowakowska Zofia G. Zajac İlayda Boz Computer Engineering Department Alanya Alaaddin Keykubat University Antalya Turkey Computer Vision Laboratory Department of Computer Science Faculty of Engineering University of Radom Masovian Voivodeship Poland Aerospace Engineering Department Tarsus University Mersin Turkey

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

In this study, we investigate the detection of fuel tanks, critical components of global energy management and infrastructure security, from UAV-acquired images using the YOLOv8 algorithm. The synergy between UAVs and the YOLOv8 object detector is highlighted, demonstrating its capacity to automate detection and monitoring processes for industrial control applications. YOLOv8's advanced architecture, featuring a robust backbone and efficient neck design, enables accurate detection of objects across various sizes and conditions, even within complex scenes. As the latest iteration of the YOLO series, YOLOv8 surpasses its predecessors in accuracy and processing speed, incorporating advanced features that enhance its detection capabilities. The study evaluates YOLOv8's performance in detecting fuel tanks under diverse scenarios. Key results include a sensitivity rate of 0.888, indicating high precision in positive predictions, and a recall rate of 0.896, reflecting a low target miss rate. The mean average precision (mAP) of 0.891 and F1 score of 0.892 underscore the algorithm's balanced optimization of accuracy and sensitivity. Additionally, YOLOv8 achieves a rapid processing time of 41 ms per image, highlighting its suitability for real-time applications. These findings contribute significantly to the adoption of innovative technologies in energy and industrial control sectors, demonstrating YOLOv8's effectiveness and reliability for automated monitoring tasks.

关键词： YOLO Accuracy Sensitivity Service robots Fuel storage Security Reliability Energy management Monitoring Optimization

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：