检索结果-内蒙古大学图书馆

arXiv 2017年

作者： He, Jingwu Wang, Linbo Zhou, Wenzhe Zhang, Hongjie Cui, Xiufen Guo, Yanwen National Key Lab for Novel Software Technology Nanjing University NanJing210023 China MOE Key Laboratory of Intelligent Computing and Signal Processing Institute of Media Computing Anhui University HeFei230039 China Samsung Electronics R&D China

—This paper studies the problem of how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from professional photographs of world famous landmarks that are available on the Internet. Unlike previous efforts devoted to photo quality assessment which mainly rely on 2D image features, we show in this paper combining 2D image features extracted from images with 3D geometric features computed on the 3D models can result in more reliable evaluation of viewpoint quality. Specifically, we collect a set of photographs for each of 15 world famous architectures as well as their 3D models from the Internet. Viewpoint recovery for images is carried out through an image-model registration process, after which a newly proposed viewpoint clustering strategy is exploited to validate users’ viewpoint preferences when photographing landmarks. Finally, we extract a number of 2D and 3D features for each image based on multiple visual and geometric cues and perform viewpoint recommendation by learning from both 2D and 3D features using a specifically designed SVM-2K multi-view learner, achieving superior performance over using solely 2D or 3D features. We show the effectiveness of the proposed approach through extensive experiments. The experiments also demonstrate that our system can be used to recommend viewpoints for rendering textured 3D models of buildings for the use of architectural design, in addition to viewpoint evaluation of photographs and recommendation of viewpoints for photographing architectures in practice. Copyright © 2017, The Authors. All rights reserved.

关键词： Photography

来源：评论

学校读者我要写书评

暂无评论

Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification

arXiv

引用

arXiv 2024年

作者： Guo, Yuxuan Peng, Shaohui Guo, Jiaming Huang, Di Zhang, Xishan Zhang, Rui Hao, Yifan Li, Ling Tian, Zikang Gao, Mingju Li, Yutai Gan, Yiming Liang, Shuai Zhang, Zihao Du, Zidong Guo, Qi Hu, Xing Chen, Yunji University of Science and Technology of China China State Key Lab of Processors Institute of Computing Technology CAS China Cambricon Technologies China University of Chinese Academy of Sciences China Shanghai Innovation Center for Processor Technologies China Intelligent Software Research Center Institute of Software CAS China Institute of Computing Technology CAS China

Building open agents has always been the ultimate goal in AI research, and creative agents are the more enticing. Existing LLM agents excel at long-horizon tasks with well-defined goals (e.g., ‘mine diamonds’ in Minecraft). However, they encounter difficulties on creative tasks with open goals and abstract criteria due to the inability to bridge the gap between them, thus lacking feedback for self-improvement in solving the task. In this work, we introduce autonomous embodied verification techniques for agents to fill the gap, laying the groundwork for creative tasks. Specifically, we propose the Luban agent target creative building tasks in Minecraft, which equips with two-level autonomous embodied verification inspired by human design practices: (1) visual verification of 3D structural speculates, which comes from agent synthesized CAD modeling programs;(2) pragmatic verification of the creation by generating and verifying environment-relevant functionality programs based on the abstract criteria. Extensive multi-dimensional human studies and Elo ratings show that the Luban completes diverse creative building tasks in our proposed benchmark and outperforms other baselines (33% to 100%) in both visualization and pragmatism. Additional demos on the real-world robotic arm show the creation potential of the Luban in the physical world. © 2024, CC BY-NC-SA.

关键词： Computer aided design

来源：评论

学校读者我要写书评

暂无评论

SPA: a graph spectral alignment perspective for domain adaptation 23

SPA: a graph spectral alignment perspective for domain adapt...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zhiqing Xiao Haobo Wang Ying Jin Lei Feng Gang Chen Fei Huang Junbo Zhao College of Computer Science and Technology Zhejiang University and Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University School of Software Technology Zhejiang University and Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University CUHK-SenseTime Joint Lab The Chinese University of Hong Kong School of Computer Science and Engineering Nanyang Technological University Alibaba Group

Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment mechanism with a novel spectral regularizer towards aligning the domain graphs in eigenspaces; (ii)-we further develop a finegrained message propagation module — upon a novel neighbor-aware self-training mechanism — in order for enhanced discriminability in the target domain. On standardized benchmarks, the extensive experiments of SPA demonstrate that its performance has surpassed the existing cutting-edge DA methods. Coupled with dense model analysis, we conclude that our approach indeed possesses superior efficacy, robustness, discriminability, and transferability. Code and data are available at: https://***/CrownX/SPA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A consistent pixel-wise blur measure for partially blurred images

A consistent pixel-wise blur measure for partially blurred i...

引用

IEEE International Conference on Image Processing

作者： Xianyong Fang Feng Shen Yanwen Guo Christian Jacquemin Jian Zhou Shanchun Huang Anhui University Hefei Anhui CN Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei China State Key Lab. for Novel Software Technology Nanjing University Nanjing China AMI LIMSI-CNRS Orsay France

Despite numerous efforts on blur measurement of partially blurred images, there still lacks an effective blur measure that is both pixel-wise and locally sharp consistent. The paper proposes a novel method with two contributions to overcome this limitation: 1) A new pixel-based blur metric, Multi-resolution Singular Value (MSV), which leverages the average singular value of high frequency bands to measure the blur of each pixel, and 2) a locally continuous strategy, maximum-likelihood estimation (MLE) based refinement, that ensures local continuity by imposing the local sharp consistency on pixel blur in a local correcting process. Experimental results show that our method is effective to smoothly measure the partially blurred images without local discontinuity.

关键词： Maximum likelihood estimation Equations Frequency measurement Image edge detection Mathematical model Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Learning domain-aware detection head with prompt tuning 23

Learning domain-aware detection head with prompt tuning

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Haochen Li Rui Zhang Hantao Yao Xinkai Song Yifan Hao Yongwei Zhao Ling Li Yunji Chen Intelligent Software Research Center Institute of Software CAS Beijing China and University of Chinese Academy of Sciences Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China and University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a discriminative visual encoder, while ignoring the domain bias in the detection head. Inspired by the high generalization of vision-language models (VLMs), applying a VLM as the robust detection backbone following a domain-aware detection head is a reasonable way to learn the discriminative detector for each domain, rather than reducing the domain bias in traditional methods. To achieve the above issue, we thus propose a novel DAOD framework named Domain-Aware detection head with Prompt tuning (DA-Pro), which applies the learnable domain-adaptive prompt to generate the dynamic detection head for each domain. Formally, the domain-adaptive prompt consists of the domain-invariant tokens, domain-specific tokens, and the domain-related textual description along with the class label. Furthermore, two constraints between the source and target domains are applied to ensure that the domain-adaptive prompt can capture the domains-shared and domain-specific knowledge. A prompt ensemble strategy is also proposed to reduce the effect of prompt disturbance. Comprehensive experiments over multiple cross-domain adaptation tasks demonstrate that using the domain-adaptive prompt can produce an effectively domain-related detection head for boosting domain-adaptive object detection. Our code is available at https://***/Therock90421/DA-Pro.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

引用

IEEE Transactions on Circuits and Systems for Video technology 2023年第2期33卷 713-727页

作者： Li, Jiawei Liu, Jinyuan Zhou, Shihua Zhang, Qiang Kasabov, Nikola K. Ministry of Education School of Software Engineering Dalian University Key Laboratory of Advanced Design and Intelligent Computing Dalian116622 China Dalian University of Technology School of Software Technology Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1010 New Zealand Ulster University Intelligent Systems Research Center LondonderryBT52 1SA United Kingdom

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an end-to-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-of-the-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://***/lok-18/LCNDR. © 1991-2012 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

DNS Covert Channel Attack Detection Based on Spatio-Temporal Feature Fusion

DNS Covert Channel Attack Detection Based on Spatio-Temporal...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Wei You Chunlei Zhao Chao Shan Guozhong Dong Jie Yu Yong Guan Tianjin Key Laboratory of Intelligent Computing and Software New Technology Tianjin University of Technology Tianjin China Hubei Branch of National Computer Network Emergency Response Technical Team Coordination Center of China HuBei China Department of New Networks Pengcheng Laboratory Shenzhen China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

An increasing number of Advanced Persistent Threat (APT) organizations are utilizing DNS (Domain Name System) covert channels to evade network intrusion detection systems and establish private authoritative servers for remote attacks. However, current detection models for DNS covert channels often have poor performance and limited generalization ability. To address these challenges, we propose a DNS covert channel attack detection method based on spatiotemporal feature fusion. This method combines the Interaction timing sequence features of DNS traffic with the spatial statistical features of domain names, and constructs a detection model called ConvSLSTM, which integrates a Convolutional Neural Network (CNN) with a stacked Long Short Term Memory (LSTM) network. CNN extracts local spatial features from traffic, while stacked LSTM captures Interaction timing sequence features, significantly improving detection accuracy. This article uses three typical public datasets for experiments, which contain a total of 440000 DNS covert channel attack data. Comparative experiments show that our method is significantly superior to existing methods and exhibits stronger generalization ability in detecting DNS covert channel attacks constructed by unknown tools.

关键词： Accuracy Protocols Feature extraction Timing Spatiotemporal phenomena Domain Name System Convolutional neural networks Servers Computer crime Long short term memory

来源：评论

学校读者我要写书评

暂无评论

BLOCKY ARTIFACT REMOVAL WITH LOW-RANK MATRIX RECOVERY

BLOCKY ARTIFACT REMOVAL WITH LOW-RANK MATRIX RECOVERY

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Ming Yin Junbin Gao Yanfeng Sun Shuting Cai School of Automation Guangdong University of Technology Guangzhou 510006 China School of Computing and Mathematics Charles Sturt University Bathurst NSW 2795 Australia Beijing Municipal Key Lab of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing 100124 China

ISBN: (纸本)9781479928941

In this paper, a novel image blocky artifact removal scheme based on low-rank matrix recovery is proposed. The problem of suppressing blocky artifacts is formulated as recovering a low-rank matrix from corrupted observations. During the deblocking processing, we do not directly recover the whole clean image but only its high-frequency component and then synthesize the clean image by incorporating the low-frequency component of blocky image. To take advantage of the low-rank matrix recovery paradigm, we first cluster the similar patches of the high-frequency component of image via local pixel clustering, then the clean high-frequency component of image is recovered by formulating an optimization problem of the nuclear norm and l_1-norm. The experimental results show that the proposed algorithm can achieve competitive performance in terms of both quantitative and subjective quality.

关键词： Imagery (Psychotherapy) images Image High frequency rank of matrix Artifacts matrix matrices

来源：评论

学校读者我要写书评

暂无评论

A Representation Learning Framework for Stock Movement Prediction

SSRN

引用

SSRN 2022年

作者： Feng, Wenzhi Ma, Xiang Li, Xuemei Zhang, Caiming School of Software Shandong University Jinan250101 China Shandong Co-Innovation Center of Future Intelligent Computing Yantai264025 China Digital Media Technology Key Lab of Shandong Province Jinan250014 China

The learning of high-quality stock representations is one of the keys to predicting stock movements effectively. Current studies have been negatively impacted by stochasticity in stock prices, resulting in inadequate representation learnt by the models. We present an end-to-end stock movement prediction framework (CLSR) utilizing contrastive learning to exploit the correlation between intra-day data and enhance stock representation in order to improve the accuracy of stock movement prediction. In addition, a hybrid encoding network is developed to extract long-range dependencies and local contextual features in stock data, making the feature representation more complete. To further improve the prediction accuracy of the model, historical state information is added to the intra-day stock data. Our experiments on CSI-500 show that the proposed method outperforms state-of-the-art solutions. The proposed method is also validated by analyzing the representation space thoroughly © 2022, The Authors. All rights reserved.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection

arXiv

引用

arXiv 2024年

作者： Li, Haochen Zhang, Rui Yao, Hantao Zhang, Xin Hao, Yifan Song, Xinkai Li, Xiaqing Zhao, Yongwei Li, Ling Chen, Yunji Intelligent Software Research Center Institute of Software CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, ***-specific knowledge of the target domain. To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task. The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge. DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder. Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection. Our code is available at https://***/Therock90421/DA-Ada © 2024, CC BY-NC-SA.

关键词： Ada (programming language)

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：