检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ding, Yanbo Zhuang, Shaobin Li, Kunchang Yue, Zhengrong Qiao, Yu Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllab.e image generation from user queries. Specifically, our MUSES develops a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collab.ration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllab.e objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, existing benchmarks lack detailed descriptions of complex Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation

arXiv

引用

arXiv 2023年

作者： Shen, Haoran Zhang, Yifu Wang, Wenxuan Chen, Chen Liu, Jing Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet [44]) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

OSRT: Omnidirectional Image Super-Resolution with Distortion...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Fanghua Yu Xintao Wang Mingdeng Cao Gen Li Ying Shan Chao Dong ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences ARC Tencent PCG The University of Tokyo Platform Technologies Tencent Online Video Shanghai Artificial Intelligence Laboratory

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous methods attempt to solve this issue by image super-resolution (SR) on equirectangular projection (ERP) images. However, they omit geometric properties of ERP in the degradation process, and their models can hardly generalize to real ERP images. In this paper, we propose Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples. Then we design a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively. Without a cumbersome process, OSRT outperforms previous methods by about 0.2dB on PSNR. Moreover, we propose a convenient data augmentation strategy, which synthesizes pseudo ERP images from plain images. This simple strategy can alleviate the over-fitting problem of large networks and significantly boost the performance of ODISR. Extensive experiments have demonstrated the state-of-the-art performance of our OSRT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework

arXiv

引用

arXiv 2022年

作者： Mo, Ningkai Gan, Wanshui Yokoya, Naoto Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The University of Tokyo Japan RIKEN Japan

In this paper, a computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects. This framework is designed in a simple architecture that efficiently extracts point-wise features from RGB-D data using a fully convolutional network, called XYZNet, and directly regresses the 6D pose without any post refinement. In the case of symmetric object, one object has multiple ground-truth poses, and this one-to-many relationship may lead to estimation ambiguity. In order to solve this ambiguity problem, we design a symmetry-invariant pose distance metric, called average (maximum) grouped primitives distance or A(M)GPD. The proposed A(M)GPD loss can make the regression network converge to the correct state, i.e., all minima in the A(M)GPD loss surface are mapped to the correct poses. Extensive experiments on YCB-Video and TLESS datasets demonstrate the proposed framework's substantially superior performance in top accuracy and low computational cost. The relevant code is availab.e in https://***/GANWANSHUI/***. Copyright © 2022, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Consumption For Smart Homes Using Fused Machine-Learning Technique

引用

computers, Materials & Continua 2023年第1期74卷 2261-2278页

作者： Hanadi AlZaabi Khaled Shaalan Taher M.Ghazal Muhammad A.Khan Sagheer Abbas Beenu Mago Mohsen A.A.Tomh Munir Ahmad Faculty of Engineering and IT The British University in DubaiUnited Arab Emirates Center for Cyber Security Faculty of Information Science and TechnologyUniversity Kebangsaan Malaysia(UKM)Bangi43600SelangorMalaysia School of Information Technology Skyline University CollegeUniversity City SharjahSharjah1797United Arab Emirates Riphah School of Computing&Innovation Faculty of ComputingRiphah International University Lahore CampusLahore54000Pakistan Pattern Recognition and Machine Learning Lab. Department of SoftwareGachon UniversitySeongnamGyeonggido13120Korea Faculty of Computer Science NCBA&ELahore54660Pakistan

Energy is essential to practically all exercises and is imperative for the development of personal ***,valuable energy has been in great demand for many years,especially for using smart homes and structures,as individuals quickly improve their way of life depending on current ***,there is a shortage of energy,as the energy required is higher than that *** new plans are being designed to meet the consumer’s energy *** many regions,energy utilization in the housing area is 30%–40%.The growth of smart homes has raised the requirement for intelligence in applications such as asset management,energy-efficient automation,security,and healthcare monitoring to learn about residents’actions and forecast their future *** overcome the challenges of energy consumption optimization,in this study,we apply an energy management *** fusion has recently attracted much energy efficiency in buildings,where numerous types of information are *** proposed research developed a data fusion model to predict energy consumption for accuracy and miss *** results of the proposed approach are compared with those of the previously published techniques and found that the prediction accuracy of the proposed method is 92%,which is higher than the previously published approaches.

关键词： Energy consumption intelligent machine learning technique smart homes prediction

来源：评论

学校读者我要写书评

暂无评论

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC SEGMENTATION

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Shi, Guangchen Wu, Yirui Palaiahnakote, Shivakumara Pal, Umapada Lu, Tong College of Computer and Information Hohai University China Department of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India National Key Lab for Novel Software Technology Nanjing University China

ISBN: (纸本)9781665438643

To make predictions on unseen classes, few-shot segmentation becomes a research focus recently. However, most methods build on pixel-level annotation requiring quantity of manual work. Moreover, inherent information on same-category objects to guide segmentation could have large diversity in feature representation due to differences in size, appearance, layout, and so on. To tackle these problems, we present an active-reference network (ARNet) for few-shot segmentation. The proposed active-reference mechanism not only supports accurately co-occurrent objects in either support or query images, but also relaxes high constraint on pixel-level lab.ling, allowing for weakly boundary lab.ling. To extract more intrinsic feature representation, a category-modulation module (CMM) is further applied to fuse features extracted from multiple support images, thus forgetting useless and enhancing contributive information. Experiments on PASCAL-5i dataset show the proposed method achieves a m-IOU score of 56.5% for 1-shot and 59.8% for 5-shot segmentation, being 0.5% and 1.3% higher than current state-of-the-art method. © 2021 IEEE

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

Activating More Pixels in Image Super-Resolution Transformer

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Xiangyu Chen Xintao Wang Jiantao Zhou Yu Qiao Chao Dong State Key Laboratory of Internet of Things for Smart City University of Macau Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory ARC Lab Tencent PCG

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image compression with recurrent neural network and generalized divisive normalization

arXiv

引用

arXiv 2021年

作者： Islam, Khawar Dang, L. Minh Lee, Sujin Moon, Hyeonjoon Computer Vision and Pattern Recognition Lab. Sejong University Korea Republic of Department of Artificial Intelligence Sejong University Korea Republic of

Image compression is a method to remove spatial redundancy between adjacent pixels and reconstruct a high-quality image. In the past few years, deep learning has gained huge attention from the research community and produced promising image reconstruction results. Therefore, recent methods focused on developing deeper and more complex networks, which significantly increased network complexity. In this paper, two effective novel blocks are developed: analysis and synthesis block that employs the convolution layer and Generalized Divisive Normalization (GDN) in the variable-rate encoder and decoder side. Our network utilizes a pixel RNN approach for quantization. Furthermore, to improve the whole network, we encode a residual image using LSTM cells to reduce unnecessary information. Experimental results demonstrated that the proposed variable-rate framework with novel blocks outperforms existing methods and standard image codecs, such as George’s [11] and JPEG in terms of image similarity. © 2021, CC BY.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

Isoform Function Prediction Based on Heterogeneous Graph Att...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Guo, Kuo Li, Yifan Chen, Hao Shen, Hong-Bin Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Image Processing and Pattern Recognition Shanghai200240 China Carnegie Mellon University School of Computer Science Computational Biology Department PittsburghPA15213 United States

ISBN: (纸本)9798350337488

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function lab.ls are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific lab.ls, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function lab.ls at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function. © 2023 IEEE.

关键词： alternative splicing gene ontology heterogeneous graph attention network isoform function prediction protein language model

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT ONLINE lab.L CONSISTENT HASHING FOR LARGE-SCALE CROSS-MODAL RETRIEVAL

EFFICIENT ONLINE LABEL CONSISTENT HASHING FOR LARGE-SCALE CR...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yi, Jinhan Liu, Xin Cheung, Yiu-Ming Xu, Xing Fan, Wentao He, Yi Department of Computer Science and Technology Huaqiao University Xiamen361021 China Xiamen Key Lab. of Computer Vision and Pattern Recognition Fujian Key Lab. of Big Data Intelligence and Security China Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781665438643

Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic association, while lacking flexibility to learn the hash functions for varying streaming data. (3) Existing supervised methods always require much computation time or accumulate large quantization loss to learn hash codes. To address above challenges, we present an efficient Online lab.l Consistent Hashing (OLCH) for cross-modal retrieval, which aims to incrementally learn hash codes for the current arriving data, while updating the hash functions at a streaming manner. To be specific, an online semantic representation learning framework is designed to adaptively preserve the semantic similarity across different modalities, and a mini-batch online gradient descent approach associated with forward-backward splitting is developed to optimize the hash functions. Accordingly, the hash codes are adaptively learned online with the high discriminative capability, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts. © 2021 IEEE computer Society. All rights reserved.

关键词： Hash functions

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：