检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Xu, Hongbin Zhou, Zhipeng Qiao, Yu Kang, Wenxiong Wu, Qiuxia ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shanghai AI Lab Shanghai China South China University of Technology Guangzhou China

Recent studies have witnessed that self-supervised methods based on view synthesis obtain clear progress on multiview stereo (MVS). However, existing methods rely on the assumption that the corresponding points among different views share the same color, which may not always be true in practice. This may lead to unreliable self-supervised signal and harm the final reconstruction performance. To address the issue, we propose a framework integrated with more reliable supervision guided by semantic co-segmentation and data-augmentation. Specially, we excavate mutual semantic from multi-view images to guide the semantic consistency. And we devise effective data-augmentation mechanism which ensures the transformation robustness by treating the prediction of regular samples as pseudo ground truth to regularize the prediction of augmented samples. Experimental results on DTU dataset show that our proposed methods achieve the state-of-the-art performance among unsupervised methods, and even compete on par with supervised methods. Furthermore, extensive experiments on Tanks&Temples dataset demonstrate the effective generalization ability of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution

arXiv

引用

arXiv 2022年

作者： Xie, Liangbin Wang, Xintao Zhang, Honglun Dong, Chao Shan, Ying Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China ARC Lab Tencent PCG China

Most of the existing video face super-resolution (VFSR) methods are trained and evaluated on VoxCeleb1, which is designed specifically for speaker identification and the frames in this dataset are of low quality. As a consequence, the VFSR models trained on this dataset can not output visual-pleasing results. In this paper, we develop an automatic and scalable pipeline to collect a high-quality video face dataset (VFHQ), which contains over 16, 000 high-fidelity clips of diverse interview scenarios. To verify the necessity of VFHQ, we further conduct experiments and demonstrate that VFSR models trained on our VFHQ dataset can generate results with sharper edges and finer textures than those trained on VoxCeleb1. In addition, we show that the temporal information plays a pivotal role in eliminating video consistency issues as well as further improving visual performance. Based on VFHQ, by analyzing the benchmarking study of several state-of-the-art algorithms under bicubic and blind settings. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models

Generate Like Experts: Multi-Stage Font Generation by Incorp...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Bin Fu Fanghua Yu Anran Liu Zixuan Wang Jie Wen Junjun He Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The University of Hong Kong Harbin Institute of Technology Shenzhen Shanghai Artificial Intelligence Laboratory

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Few-shot font generation (FFG) produces stylized font images with a limited number of reference samples, which can significantly reduce labor costs in manual font designs. Most existing FFG methods follow the style-content dis-entanglement paradigm and employ the Generative Adver-sarial Network (GAN) to generate target fonts by combining the decoupled content and style representations. The complicated structure and detailed style are simultaneously generated in those methods, which may be the sub-optimal solutions for FFG task. Inspired by most manual font design processes of expert designers, in this paper, we model font generation as a multi-stage generative process. Specifically, as the injected noise and the data distribution in diffusion models can be well-separated into different sub-spaces, we are able to incorporate the font transfer process into these models. Based on this observation, we generalize diffusion methods to modelfont generative process by separating the reverse diffusion process into three stages with different functions: The structure construction stage first generates the structure information for the target character based on the source image, and the font transfer stage subsequently transforms the source font to the target font. Finally, the font refinement stage enhances the appearances and local details of the target font images. Based on the above multi-stage generative process, we construct our font generation framework. named MSD-Font, with a dual-network approach to generate font images. The superior performance demonstrates the effectiveness of our model. The code is available at: https://***/fubinfbIMSD-Font.

关键词： Costs Noise Diffusion processes Transforms Manuals Diffusion models Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Compressed sensing ensemble classifier for human detection

Compressed sensing ensemble classifier for human detection

引用

4th International Conference on Intelligence Science and Big Data Engineering, IScIDE 2013

作者： Zhang, Baochang Liu, Juan Gao, Yongsheng Liu, Jianzhuang Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering BeiHang University Beijing 100191 China School of Engineering Griffith University Australia Shenzhen Key Lab for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9783642420566

This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selection of base classifiers. The major contributions of this paper are: 1) a novel principled framework for ensemble classifier design based on compressed sensing;2) a new concept of considering both the simplicity of ensemble classifier and irrelevance of base classifiers towards optimal classifier design;and 3) a quadratic function for CSEC optimization which includes a new optimizable positive semi-definite relevance matrix to simultaneously select appropriate base classifiers with minimized relevance. Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Robust Text Line Detection in Equipment Nameplate Images*

Robust Text Line Detection in Equipment Nameplate Images*

引用

IEEE International Conference on Robotics and Biomimetics

作者： Jiangyu Lai Lanqing Guo Yu Qiao Xiaolong Chen Zhengfu Zhang Canping Liu Ying Li Bin Fu Guangzhou Power Supply Bureau Co. Ltd. Guangzhou China ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

Scene text detection for equipment nameplates in the wild is important for equipment inspection robot since it enables inspection robot to take specific actions for different equipment's. Although text detection in images has achieved great progress in recent years, the detection for equipment nameplates faces several challenges such as extreme illumination and distortion which significantly decrease the detection performance. In this paper, we propose a deep text detection model Robust Text Line Detection (RTLD) for locating word level text instances in equipment cards. Specifically, the proposed model first employs a corner detection module to determine the four corner points of each nameplate, and then a carefully designed image transformed module transforms the irregular nameplate region into a rectangular region. Finally, text detection module is introduced to locate every word level text instance in the transformed images. We conduct extensive experiments to examine our proposed methods on real equipment nameplate images. Our model achieves 91 . 2% precision and 92 . 6% recall on Equipment Nameplate Dataset. The experimental results demonstrate the effectiveness of our models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text-Video Knowledge Guided Prompting for Weakly Supervised Temporal Action Localization

引用

IEEE Transactions on Circuits and Systems for Video Technology 2024年第5期35卷 4184-4197页

作者： Shao, Yuxiang Zhang, Feifei Xu, Changsheng Tianjin University of Technology Tianjin300384 China Tianjin University of Technology School of Computer Science and Engineering Tianjin300384 China Tianjin University of Technology Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Peng Cheng Laboratory Shenzhen518066 China

Weakly supervised temporal action localization (WTAL) aims to localize action instances with only video-level labels for supervision. Recent methods convert category labels to natural language through prompting and utilize pre-trained vision-language models to generate text representation from natural language for supervision. This is because natural language can provide more prosperous and generalized semantic supervision to compensate for the lack of supervision in weakly supervised scenarios. However, it should be noted that current prompting methods face limitations in generating dynamic prompts that adapt to each video, which leads to difficulties in accurately aligning text and video representations. In this work, we propose a novel Text-Video Knowledge Guided Prompting (TVKP) framework for WTAL, which generates video-aware prompts based on text-video knowledge to enhance semantic alignment between text and video representations and introduce more video-related external category labels to enrich semantic supervision. We introduce the video-aware prompting (VAP) module to learn text-video knowledge from the joint distribution of text and video representations to generate video-aware text representation. Meanwhile, to make VAP more effectively learn text-video knowledge, a text-video contrastive loss is proposed to ensure semantic consistency between text and video representations. In addition, we propose the external knowledge prompting (EKP) module to introduce more video-related text labels from an external knowledge base to enrich prompts for accurate semantic alignment. Extensive experiments are conducted on three public datasets, THUMOS14, ActivityNet1.2, and ActivityNet1.3, demonstrating that our approach outperforms state-of-the-art methods. © 1991-2012 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

A New Method for Detecting Altered Text in Document Images 2nd

A New Method for Detecting Altered Text in Document Images

引用

2nd International Conference on pattern recognition and Artificial Intelligence, ICPRAI 2020

作者： Nandanwar, Lokesh Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Lopresti, Daniel Seraogi, Bhagesh Chaudhuri, Bidyut B. Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Science and Engineering Lehigh University BethlehemPA United States

ISBN: (纸本)9783030598297

As more and more office documents are captured, stored, and shared in digital format, and as image editing software becomes increasingly more powerful, there is a growing concern about document authenticity. For example, texts in property documents can be altered to make an illegal deal, or the date on an airline ticket can be altered to gain entry to airport terminals by breaching security. To prevent such illicit activities, this paper presents a new method for detecting altered text in a document. The proposed method explores the relationship between positive and negative coefficients of a DCT to extract the effect of distortions caused by tampering operations. Here we divide DCT coefficients into positive and negative classes, then reconstructs images from the inverse DCT of the respective positive and negative coefficients. Next, we perform Laplacian filtering over reconstructed images for widening the gap between the values of text and other pixels. Then filtered images of positive and negative coefficients are fused by an average operation. For a fused image, we generate Canny and Sobel edge images in order to investigate the effect of distortion through quality measures, namely, MSE, PSNR and SSIM used as features. In addition, for the fused image, the proposed method extracts features based on histograms over the residual images. The features are then passed on to a deep Convolutional Neural Network for classification. The proposed method is tested on our own dataset as well as two standard datasets, namely IMEI and the ICPR 2018 Fraud Contest dataset. The results show that the proposed method is effective and outperforms existing methods. © 2020, Springer Nature Switzerland AG.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Learning to predict context-adaptive convolution for semantic segmentation

arXiv

引用

arXiv 2020年

作者： Liu, Jianbo He, Junjun Ren, Jimmy S. Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods [34] demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Learning dynamical human-joint affinity for 3D pose estimation in videos

arXiv

引用

arXiv 2021年

作者： Zhang, Junhao Wang, Yali Zhou, Zhipeng Luan, Tianyu Wang, Zhe Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of California Irvine United States Shanghai AI Laboratory Shanghai China

Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human skeleton. This may reduce adaptation capacity of GCN to tackle complex spatio-temporal pose variations in videos. To alleviate this problem, we propose a novel Dynamical Graph Network (DG-Net), which can dynamically identify human-joint affinity, and estimate 3D pose by adaptively learning spatial/temporal joint relations from videos. Different from traditional graph convolution, we introduce Dynamical Spatial/Temporal Graph convolution (DSG/DTG) to discover spatial/temporal human-joint affinity for each video exemplar, depending on spatial distance/temporal movement similarity between human joints in this video. Hence, they can effectively understand which joints are spatially closer and/or have consistent motion, for reducing depth ambiguity and/or motion uncertainty when lifting 2D pose to 3D pose. We conduct extensive experiments on three popular benchmarks, e.g., Human3.6M, HumanEva-I, and MPI-INF-3DHP, where DG-Net outperforms a number of recent SOTA approaches with fewer input frames and model size. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

DegAE: A New Pretraining Paradigm for Low-Level vision

DegAE: A New Pretraining Paradigm for Low-Level Vision

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Yihao Liu Jingwen He Jinjin Gu Xiangtao Kong Yu Qiao Chao Dong Shanghai Artificial Intelligence Laboratory ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences The University of Sydney

Self-supervised pretraining has achieved remarkable success in high-level vision, but its application in low-level vision remains ambiguous and not well-established. What is the primitive intention of pretraining? What is the core problem of pretraining in low-level vision? In this paper, we aim to answer these essential questions and establish a new pretraining scheme for low-level vision. Specifically, we examine previous pretraining methods in both high-level and low-level vision, and categorize current low-level vision tasks into two groups based on the difficulty of data acqui-sition: low-cost and high-cost tasks. Existing literature has mainly focused on pretraining for low-cost tasks, where the observed performance improvement is often limited. However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging. To learn a general low-level vision representation that can improve the performance of various tasks, we propose a new pretraining paradigm called degradation autoencoder (De-gAE). DegAE follows the philosophy of designing pretext task for self-supervised pretraining and is elaborately tai-lored to low-level vision. With DegAE pretraining, SwinIR achieves a 6.88dB performance gain on image dehaze task, while Uformer obtains 3.22dB and 0.54dB improvement on dehaze and derain tasks, respectively.

关键词：

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：