检索结果-内蒙古大学图书馆

17th European Conference on computer vision, ECCV 2022

作者： Zhou, Lin Cai, Haoming Gu, Jinjin Li, Zheyuan Liu, Yingqi Chen, Xiangyu Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shanghai AI Laboratory Shanghai China The University of Sydney Sydney Australia University of Macau Zhuhai China

ISBN: (纸本)9783031250620

The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually modify it to achieve better super-resolution performance with reduced parameters. The specific approaches include: (1) increasing the receptive field of the attention branch, (2) replacing large dense convolution kernels with depthwise separable convolutions, and (3) introducing pixel normalization. These approaches paint a clear evolutionary roadmap for the design of attention mechanisms. Based on these observations, we propose VapSR, the Vast-receptive-field Pixel attention network. Experiments demonstrate the superior performance of VapSR. VapSR outperforms the present lightweight networks with even fewer parameters. And the light version of VapSR can use only 21.68% and 28.18% parameters of IMDB and RFDN to achieve similar performances to those networks. The code and models are availab.e at https://***/zhoumumu/VapSR. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Modified quantization index modulation watermarking adaptive to contrast masking thresholds

Modified quantization index modulation watermarking adaptive...

引用

1st International Conference on Communications and Networking in China, ChinaCom '06

作者： Guoxi, Wang Lihong, Ma. Kang, Cai Hanqing, Lu GD Key Lab. of Computer Network Dept.of Electronic Engineering South China Univ. of Tech. Guangzhou 510641 China National Lab. of Pattern Recognition Inst. Automation China Academy of Science Beijing 100080 China Guangdong Telecom.

ISBN: (纸本)1424404630

In this paper, we suggest an adaptive watermarking method to improve both transparence and robustness of quantization index modulation (QIM) scheme. Instead of a fixed quantization step size, we apply a step size adapted to image content in each 8×8 block to make a balance of the robustness extraction and the transparence of embedding. The modified steps are determined by the contrast masking thresholds of Watson's perceptual model. From normalized cross correlation between the original watermark and the detected watermark, we observe that it is robust to attacks of additive white Gaussian noise, salt & pepper noise, JPEG compression than the original QIM. © 2006 IEEE.

关键词： Digital watermarking

来源：评论

学校读者我要写书评

暂无评论

EfficientFCN: Holistically-Guided Decoding for Semantic Segmentation 1

引用

16th European Conference on computer vision, ECCV 2020

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

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

GEMI: A high performance and high flexibility memory interface architecture for complex embedded SOC

GEMI: A high performance and high flexibility memory interfa...

引用

International Conference on computer Science and Software Engineering, CSSE 2008

作者： Hualong, Zhao Hongshi, Sang Tianxu, Zhang Yebin, Fan State Key Lab. for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China Department of Computer Science Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769533360

Two of the most significant factors in the success of today's system-on-chip (SoC) designs are the ability to deliver efficient access to off-chip high speed memory and the ability to be compatible with several different interface-timings of several different sorts of memories. And the scheduling scheme of data streams for multi-master and multi-outstanding requests situation in complex SoC should be considered carefully, too. This paper introduces a novel general external memory interface (GEMI) architecture for the high performance and high flexibility memory interface. Several techniques and methods, i.e. data and command buffers based on asynchronous FIFO, optimized bank management, multi-port access scheduler, request reorder unit, are proposed in this paper for fulfilling the requirements mentioned above. Some techniques are specially proposed for data streams scheduling in complex SoC. At the end of the paper, the simulation and tape-out results are provided. The whole implementation of architecture is proven to be not only functional and efficient, but also flexible and reusable by simulation and silicon verification. © 2008 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Adaptive classification for person re-identification driven by change detection 4

Adaptive classification for person re-identification driven ...

引用

4th International Conference on pattern recognition Applications and Methods, ICPRAM 2015

作者： Pagano, C. Granger, E. Sabourin, R. Marcialis, G.L. Roli, F. Lab. d'Imagerie de Vision et d'Intelligence Artificielle École de Technologie Supérieure Université du Qué bec Montreal Canada Pattern Recognition and Applications Group Dept. of Electrical and Electronic Engineering University of Cagliari Cagliari Italy

ISBN: (纸本)9789897580765

Person re-identification from facial captures remains a challenging problem in video surveillance, in large part due to variations in capture conditions over time. The facial model of a target individual is typically designed during an enrolment phase, using a limited number of reference samples, and may be adapted as new reference videos become availab.e. However incremental learning of classifiers in changing capture conditions may lead to knowledge corruption. This paper presents an active framework for an adaptive multi-classifier system for video-to-video face recognition in changing surveillance environments. To estimate a facial model during the enrolment of an individual, facial captures extracted from a reference video are employed to train an individual-specific incremental classifier. To sustain a high level of performance over time, a facial model is adapted in response to new reference videos according the type of concept change. If the system detects that the facial captures of an individual incorporate a gradual pattern of change, the corresponding classifier(s) are adapted through incremental learning. In contrast, to avoid knowledge corruption, if an abrupt pattern of change is detected, a new classifier is trained on the new video data, and combined with the individual's previously-trained classifiers. For validation, a specific implementation is proposed, with ARTMAP classifiers updated using an incremental learning strategy based on Particle Swarm Optimization, and the Hellinger Drift Detection Method is used for change detection. Simulation results produced with Faces in Action video data indicate that the proposed system allows for scalab.e architectures that maintains a significantly higher level of accuracy over time than a reference passive system and an adaptive Transduction Confidence Machine-kNN classifier, while controlling computational complexity.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Balancing usability and security in a video CAPTCHA 09

Balancing usability and security in a video CAPTCHA

引用

5th Symposium On Usable Privacy and Security, SOUPS 2009

作者： Kluever, Kurt Alfred Zanibbi, Richard Google Inc. 76 Ninth Ave. New York NY 10011 United States Document and Pattern Recognition Lab. Department of Computer Science Rochester Institute of Technology Rochester NY 14623 United States

ISBN: (纸本)9781605587363

We present a technique for using content-based video lab.ling as a CAPTCHA task. Our CAPTCHAs are generated from YouTube videos, which contain lab.ls (tags) supplied by the person that uploaded the video. They are graded using a video's tags, as well as tags from related videos. In a user study involving 184 participants, we were able to increase the human success rate on our video CAPTCHA from roughly 70% to 90%, while keeping the success rate of a tag frequency-based attack fixed at around 13%. Through a different parameterization of the challenge generation and grading algorithms, we were able to reduce the success rate of the same attack to 2%, while still increasing the human success rate from 70% to 75%. The usability and security of our video CAPTCHA appears to be comparable to existing CAPTCHAs, and a majority of participants (60%) indicated that they found the video CAPTCHAs more enjoyable than traditional CAPTCHAs in which distorted text must be transcribed.

关键词： Grading

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

UDC-UNet: Under-Display Camera Image Restoration via U-shape Dynamic Network 17th

UDC-UNet: Under-Display Camera Image Restoration via U-shap...

引用

17th European Conference on computer vision, ECCV 2022

作者： Liu, Xina Hu, Jinfan Chen, Xiangyu Dong, Chao Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China University of Macau Zhuhai China Shanghai AI Laboratory Shanghai China

ISBN: (纸本)9783031250712

Under-Display Camera (UDC) has been widely exploited to help smartphones realize full-screen displays. However, as the screen could inevitably affect the light propagation process, the images captured by the UDC system usually contain flare, haze, blur, and noise. Particularly, flare and blur in UDC images could severely deteriorate the user experience in high dynamic range (HDR) scenes. In this paper, we propose a new deep model, namely UDC-UNet, to address the UDC image restoration problem with an estimated PSF in HDR scenes. Our network consists of three parts, including a U-shape base network to utilize multi-scale information, a condition branch to perform spatially variant modulation, and a kernel branch to leverage the prior knowledge of the PSF. According to the characteristics of HDR data, we additionally design a tone mapping loss to stabilize network optimization and achieve better visual quality. Experimental results show that the proposed UDC-UNet outperforms the state-of-the-art methods in quantitative and qualitative comparisons. Our approach won second place in the UDC image restoration track of the MIPI challenge. Codes and models are availab.e at https://***/J-FHu/UDCUNet. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Text scanner with text detection technology on image sequences

Text scanner with text detection technology on image sequenc...

引用

16th International Conference on pattern recognition, ICPR 2002

作者： Jung, Keechul Kim, Kwang In Kurata, Takeshi Kourogi, Masakastu Han, Junghyun Pattern Recognition and Image Processing Lab. Michigan State Univerisity United States Artificial Intelligence Lab. KAIST Korea Republic of National Institute of Advanced Industrial Science and Technology Japan School of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

ISBN: (纸本)0769516963

We propose a text scanner, which detects wide text strings in a sequence of scene images. For scene text detection, we use a multiple-CAMShift algorithm on a text probability image produced by a multi-layer perceptron. To provide enhanced resolution of the extracted text images, we perform the text detection process after generating a mosaic image in a fast and robust image registration method. © 2002 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

THE HIDDEN MARKOV MODEL OF CO-ARTICULATION AND ITS APPLICATION TO THE CONTINUOUS SPEECH recognition

引用

Journal of Electronics(China) 2000年第3期17卷 242-247页

作者： Lee Tranzai Zheng Fang Wu Wenhu Chen Daowen(Speech lab., Dept. of computer Sciences and Technology, Tsinghua University, Beijing 100084) (National lab. of pattern recognition, Inst. of Automation, Chinese Academy of Sci., Beijing 100080) Speech Lab. Dept. of Computer Sciences and Technology Tsinghua University Beijing National Lab. of Pattern Recognition Inst. of Automation Chinese Academy of Sci. Beijing

The co-articulation is one of the main reasons that makes the speech recognition difficult. However, the traditional Hidden Markov Models(HMM) can not model the co-articulation, because they depend on the first-order assumption. In this paper, for modeling the co-articulation, a more perfect HMM than traditional first order HMM is proposed on the basis of the authors’ previous works(1997, 1998) and they give a method in that this HMM is used in continuous speech recognition by means of multilayer perceptrons(MLP), i.e. the hybrid HMM/MLP method with triple MLP structure. The experimental result shows that this new hybrid HMM/MLP method decreases error rate in comparison with authors’ previous works.

关键词： Speech recognition High-order HMM Hybrid HMM/MLP

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：