检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Fan, Cunhang Xue, Jun Tao, Jianhua Yi, Jiangyan Wang, Chenglong Zheng, Chengshi Lv, Zhao Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Department of Automation Tsinghua University Beijing100190 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Key Laboratory of Noise and Vibration Research Institute of Acoustics Chinese Academy of Sciences Beijing100190 China

The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband so as to improve the performance of FSD, the spatial reconstructed local attention Res2Net (SR-LA Res2Net) is proposed. Specifically, Res2Net is used as a backbone network to obtain multiscale information, and enhanced with a spatial reconstruction mechanism to avoid losing important information when the channel group is constantly superimposed. In addition, local attention is designed to make the model focus on the local information of the F0 subband. Experimental results on the ASVspoof 2019 LA dataset show that our proposed method obtains an equal error rate (EER) of 0.47% and a minimum tandem detection cost function (min t-DCF) of 0.0159, achieving the state-of-the-art performance among all of the single systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Enhanced Quadratic Video Interpolation 16th

Enhanced Quadratic Video Interpolation

引用

Workshops held at the 16th European Conference on computer vision, ECCV 2020

作者： Liu, Yihao Xie, Liangbin Siyao, Li Sun, Wenxiu 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 University of Chinese Academy of Sciences Beijing China SenseTime Research Beijing China

ISBN: (纸本)9783030668228

With the prosperity of digital video industry, video frame interpolation has arisen continuous attention in computer vision community and become a new upsurge in industry. Many learning-based methods have been proposed and achieved progressive results. Among them, a recent algorithm named quadratic video interpolation (QVI) achieves appealing performance. It exploits higher-order motion information (e.g. acceleration) and successfully models the estimation of interpolated flow. However, its produced intermediate frames still contain some unsatisfactory ghosting, artifacts and inaccurate motion, especially when large and complex motion occurs. In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model. In particular, we adopt a rectified quadratic flow prediction (RQFP) formulation with least squares method to estimate the motion more accurately. Complementary with image pixel-level blending, we introduce a residual contextual synthesis network (RCSN) to employ contextual information in high-dimensional feature space, which could help the model handle more complicated scenes and motion patterns. Moreover, to further boost the performance, we devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process. The proposed EQVI model won the first place in the AIM2020 Video Temporal Super-Resolution Challenge. Codes are available at https://***/lyh-18/EQVI. © 2020, Springer Nature Switzerland AG.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning of Fuzzy Spatio-Temporal Rules in the NeuCube Brain-Inspired Spiking Neural Network: A Case Study on EEG Spatio-temporal Data

TechRxiv

引用

TechRxiv 2022年

作者： Kasabov, Nikola K. Tan, Yongyao Doborjeh, Maryam Tu, Enmei Yang, Jie School of Engineering Computer and Mathematical Science KEDRI Auckland University of Technology New Zealand Intelligent Systems Research Centre University of Ulster United Kingdom Bulgarian Academy of Sciences Bulgaria Institute of Image Processing and Pattern Recognition Shanghai Jiao Tiong University China

The paper demonstrates for the first time that a brain-inspired spiking neural network (SNN) architecture can be used not only to learn spatio-temporal data, but also to extract fuzzy spatio-temporal rules from such data and to update these rules incrementally in a transfer learning mode. We propose a method, where a SNN model learns incrementally new time-space data related to new classes/tasks/categories, always utilising some previously learned knowledge, and presents the evolved knowledge as fuzzy spatio-temporal rules. Similarly, to how the brain manifests transfer learning, these SNN models do not need to be restricted in number of layers, neurons in each layer, etc. as they adopt self-organising learning principles. The continuously evolved fuzzy rules from spatio-temporal data are interpretable for a better understanding of the processes that generate the data. The proposed method is based on a brain-inspired SNN architecture NeuCube and is illustrated on tasks of incremental and transfer learning and knowledge transfer using spatio-temporal EEG data measuring brain activity, when persons performing tasks in space and time. The method is a general one and opens the field to create new types of adaptable and explainable AI systems for applications across domain areas, e.g. brain-machine interfaces, robotics, speech and sound processing, cognitive studies and the creation of lifelong-learning cognitive machines. © 2022, CC BY.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and computer vision Techniques in Continuous Beehive Monitoring Applications: A Survey

arXiv

引用

arXiv 2022年

作者： Bilik, Simon Zemcik, Tomas Kratochvila, Lukas Ricanek, Dominik Richter, Miloslav Zambanini, Sebastian Horak, Karel Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3058/10 Brno61600 Czech Republic Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Yliopistonkatu 34 Lappeenranta53850 Finland Computer Vision Lab Institute of Visual Computing & Human-Centered Technology Faculty of Informatics TU Wien Favoritenstr. 9/193-1 ViennaA-1040 Austria

Wide use and availability of machine learning and computer vision techniques allows development of relatively complex monitoring systems in many domains. Besides the traditional industrial domain, new applications appears also in biology and agriculture, where they may be used to detect infections, parasites and weeds, but also for automated monitoring and early warning systems. This goes in concordance with the introduction of the easily accessible hardware and development kits such as the Arduino, or RaspberryPi families. In this paper, we survey 50 papers focusing on the methods of automated beehive monitoring using computer vision techniques. Particularly on the pollen and Varroa mite detection together with the bee traffic monitoring. Such systems could also be used for monitoring of honeybee colonies and for the inspection of their health state, which could potentially identify dangerous states before the situation is critical, or to better plan periodic bee colony inspections and therefore save significant costs. Further on, we also include analysis of the research trends in this application field and we outline the possible directions of new development. Our paper is also aimed at veterinary and apidology professionals and experts, who may not be familiar with machine learning to introduce them to its capabilities, hence each family of techniques is prefaced by a brief theoretical introduction and motivation related to its base method. We hope that this paper will inspire other scientists to use machine learning techniques for other applications in beehive monitoring. © 2022, CC BY.

关键词： computer vision

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

Proceedings of 3rd International Conference on computer vision and Image Processing 1

引用

丛书名： Advances in Intelligent Systems and Computing

2020年

作者： Bidyut B. Chaudhuri Masaki Nakagawa Pritee Khanna Sanjeev Kumar

来源：评论

学校读者我要写书评

暂无评论

UniFormer: Unifying Convolution and Self-attention for Visual recognition

arXiv

引用

arXiv 2022年

作者： Li, Kunchang Wang, Yali Zhang, Junhao Gao, Peng Song, Guanglu Liu, Yu Li, Hongsheng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China National University of Singapore Singapore Shanghai Artificial Intelligence Laboratory China SenseTime Research China The Chinese University of Hong Kong Hong Kong

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing tackling both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification task. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks. It obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Moreover, we build an efficient UniFormer with a concise hourglass design of token shrinking and recovering, which achieves 2-4× higher throughput than the recent lightweight models. Code is av

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A new journey from SDRTV to HDRTV

arXiv

引用

arXiv 2021年

作者： Chen, Xiangyu Zhang, Zhengwen Ren, Jimmy S. Tian, Lynhoo Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai China SenseTime Research Shanghai China Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China Shanghai AI Laboratory Shanghai China

Nowadays modern displays are capable to render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most available resources are still in standard dynamic range (SDR). Therefore, there is an urgent demand to transform existing SDR-TV contents into their HDR-TV versions. In this paper, we conduct an analysis of SDRTV-to-HDRTV task by modeling the formation of SDRTV/HDRTV content. Base on the analysis, we propose a three-step solution pipeline including adaptive global color mapping, local enhancement and highlight generation. Moreover, the above analysis inspires us to present a lightweight network that utilizes global statistics as guidance to conduct image-adaptive color mapping. In addition, we construct a dataset using HDR videos in HDR10 standard, named HDRTV1K, and select five metrics to evaluate the results of SDRTV-to-HDRTV algorithms. Furthermore, our final results achieve state-of-the-art performance in quantitative comparisons and visual quality. The code and dataset are available at https://***/ chxy95/HDRTVNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Varicolored Image De-Hazing

Varicolored Image De-Hazing

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Akshay Dudhane Kuldeep M. Biradar Prashant W. Patil Praful Hambarde Subrahmanyam Murala Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar INDIA Indian Institute of Technology Ropar Ropar India

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

The quality of images captured in bad weather is often affected by chromatic casts and low visibility due to the presence of atmospheric particles. Restoration of the color balance is often ignored in most of the existing image de-hazing methods. In this paper, we propose a varicolored end-to-end image de-hazing network which restores the color balance in a given varicolored hazy image and recovers the haze-free image. The proposed network comprises of 1) Haze color correction (HCC) module and 2) Visibility improvement (VI) module. The proposed HCC module provides required attention to each color channel and generates a color balanced hazy image. While the proposed VI module processes the color balanced hazy image through novel inception attention block to recover the haze-free image. We also propose a novel approach to generate a large-scale varicolored synthetic hazy image database. An ablation study has been carried out to demonstrate the effect of different factors on the performance of the proposed network for image de-hazing. Three benchmark synthetic datasets have been used for quantitative analysis of the proposed network. Visual results on a set of real-world hazy images captured in different weather conditions demonstrate the effectiveness of the proposed approach for varicolored image de-hazing.

关键词： Image color analysis Atmospheric modeling Image restoration Meteorology Scattering Feature extraction Generators

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 1

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: (数字)9783030598303

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

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：