检索结果-内蒙古大学图书馆

A New DCT-FFT Fusion Based Method for Caption and Scene Text Classification in Action Video Images 1

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

作者： Nandanwar, Lokesh Shivakumara, Palaiahnakote Manna, Suvojit Pal, Umapada Lu, Tong Blumenstein, Michael Faculty of Computer Science and Information Technology University of Malayasia Kuala Lumpur Malaysia Department of Computer Science and Engineering Jalpaiguri Government Engineering College Jalpaiguri India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China University of Technology Sydney Ultimo Australia

ISBN: (数字)9783030598303

ISBN: (纸本)9783030598297

Achieving better recognition rate for text in video action images is challenging due to multi-type texts with unpredictable backgrounds. We propose a new method for the classification of captions (which is edited text) and scene texts (which is part of an image in video images of Yoga, Concert, Teleshopping, Craft, and Recipe classes). The proposed method introduces a new fusion criterion-based on DCT and Fourier coefficients to extract features that represent good clarity and visibility of captions to separate them from scene texts. The variances for coefficients of corresponding pixels of DCT and Fourier images are computed to derive the respective weights. The weights and coefficients are further used to generate a fused image. Furthermore, the proposed method estimates sparsity in Canny edge image of each fused image to derive rules for classifying caption and scene texts. Lastly, the proposed method is evaluated on images of five above-mentioned action image classes to validate the derived rules. Comparative studies with the state-of-the-art methods on the standard databases show that the proposed method outperforms the existing methods in terms of classification. The recognition experiments before and after classification show that the recognition performance rate improves significantly after classification. © 2020, Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Local gradient difference features for classification of 2D-3D natural scene text images 25

Local gradient difference features for classification of 2D-...

引用

25th International Conference on pattern recognition, ICPR 2020

作者： Nandanwar, Lokesh Shivakumara, Palaiahnakote Raghavendra, Ramachandra Lu, Tong Pal, Umapada Lopresti, Daniel Anuar, Nor Badrul Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Faculty of Information Technology and Electrical Engineering IIK NTNU Norway National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Computer Science and Engineering Lehigh University BethlehemPA United States

ISBN: (纸本)9781728188089

Methods developed for normal 2D text detection do not work well for text that is rendered using decorative, 3D effects, etc. This paper proposes a new method for classification of 2D and 3D natural scene text images so that an appropriate recognition method can be chosen accordingly based on the classification results for better performance. The proposed method explores local gradient differences for obtaining candidate pixels, which represent a stroke. To study the spatial distribution of candidate pixels, we propose a measure, called COLD, which is denser for pixels toward the center of strokes and scattered for non-stroke pixels. This observation leads us to introduce mass features for extracting the regular spatial pattern of COLD, which indicates a 2D text image. The extracted features are fed into a Neural Network (NN) for classification. The proposed method is tested on (i) a new dataset introduced in this work (ii) a second dataset assembled from standard natural scene datasets (iii) Non-Text Image datasets which does not contain text, rather it contains objects. Experimental results of the proposed method on images with text and non-text show that the proposed method is independent of text. The proposed approach improves text detection and recognition performance significantly after classification. © 2020 IEEE

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Tensor Low-Rank Reconstruction for Semantic Segmentation 1

引用

16th European Conference on computer vision, ECCV 2020

作者： Chen, Wanli Zhu, Xinge Sun, Ruoqi He, Junjun Li, Ruiyu Shen, Xiaoyong Yu, Bei The Chinese University of Hong Kong New Territories Hong Kong Shanghai Jiao Tong University Shanghai China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SmartMore Shenzhen China

ISBN: (数字)9783030585204

ISBN: (纸本)9783030585198

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since the desired context consists of spatial-wise and channel-wise attentions, 3D representation is an appropriate formulation. However, these non-local methods describe 3D context information based on a 2D similarity matrix, where space compression may lead to channel-wise attention missing. An alternative is to model the contextual information directly without compression. However, this effort confronts a fundamental difficulty, namely the high-rank property of context information. In this paper, we propose a new approach to model the 3D context representations, which not only avoids the space compression but also tackles the high-rank difficulty. Here, inspired by tensor canonical-polyadic decomposition theory (i.e, a high-rank tensor can be expressed as a combination of rank-1 tensors.), we design a low-rank-to-high-rank context reconstruction framework (i.e, RecoNet). Specifically, we first introduce the tensor generation module (TGM), which generates a number of rank-1 tensors to capture fragments of context feature. Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM). Extensive experiments show that our method achieves state-of-the-art on various public datasets. Additionally, our proposed method has more than 100 times less computational cost compared with conventional non-local-based methods. © 2020, Springer Nature Switzerland AG.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

PPT Fusion: Pyramid Patch Transformer for a Case Study in Image Fusion

arXiv

引用

arXiv 2021年

作者： Fu, Yu Xu, Tianyang Wu, Xiao-Jun Kittler, Josef Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the vision Transformers (ViT) for image classification. However, existing visual transformer models aim to extract semantic information for high-level tasks, such as classification and detection. These methods ignore the importance of the spatial resolution of the input image, thus sacrificing the local correlation information of neighboring pixels. In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues. Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations. In addition, we construct a Pyramid Transformer to effectively extract the non-local information from the entire image. After obtaining a set of multi-scale, multi-dimensional, and multi-angle features of the original image, we design the image reconstruction network to ensure that the features can be reconstructed into the original input. To validate the effectiveness, we apply the proposed Patch Pyramid Transformer to image fusion tasks. The experimental results demonstrate its superior performance, compared to the state-of-the-art fusion approaches, achieving the best results on several evaluation indicators. Thanks to the underlying representational capacity of the PPT network, it can directly be applied to different image fusion tasks without redesigning or retraining the network. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

2D+3D facial expression recognition via embedded tensor manifold regularization

arXiv

引用

arXiv 2022年

作者： Fu, Yunfang Ruan, Qiuqi Luo, Ziyan An, Gaoyun Jin, Yi Wan, Jun School of Computer Science and Engineering Shijiazhuang University Shijiazhuang050035 China Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Department of Mathematics Beijing Jiaotong University Beijing100044 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed. Firstly, 3D tensors are constructed from 2D face images and 3D face shape models to keep the structural information and correlations. To maintain the local structure (geometric information) of 3D tensor samples in the low-dimensional tensors space during the dimensionality reduction, the l0-norm of the core tensors and a tensor manifold regularization scheme embedded on core tensors are adopted via a low-rank truncated Tucker decomposition on the generated tensors. As a result, the obtained factor matrices will be used for facial expression classification prediction. To make the resulting tensor optimization more tractable, l1-norm surrogate is employed to relax l0-norm and hence the resulting tensor optimization problem has a nonsmooth objective function due to the l1-norm and orthogonal constraints from the orthogonal Tucker decomposition. To efficiently tackle this tensor optimization problem, we establish the first-order optimality condition in terms of stationary points, and then design a block coordinate descent (BCD) algorithm with convergence analysis and the computational complexity. Numerical results on BU-3DFE database and Bosphorus databases demonstrate the effectiveness of our proposed approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

RFN-Nest: An end-to-end residual fusion network for infrared and visible images

arXiv

引用

arXiv 2021年

作者： Li, Hui Wu, Xiao-Jun Kittler, Josef Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China The Center for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

In the image fusion field, the design of deep learning-based fusion methods is far from routine. It is invariably fusion-task specific and requires a careful consideration. The most difficult part of the design is to choose an appropriate strategy to generate the fused image for a specific task in hand. Thus, devising learnable fusion strategy is a very challenging problem in the community of image fusion. To address this problem, a novel end-to-end fusion network architecture (RFN-Nest) is developed for infrared and visible image fusion. We propose a residual fusion network (RFN) which is based on a residual architecture to replace the traditional fusion approach. A novel detail-preserving loss function, and a feature enhancing loss function are proposed to train RFN. The fusion model learning is accomplished by a novel two-stage training strategy. In the first stage, we train an auto-encoder based on an innovative nest connection (Nest) concept. Next, the RFN is trained using the proposed loss functions. The experimental results on public domain data sets show that, compared with the existing methods, our end-to-end fusion network delivers a better performance than the state-of-the-art methods in both subjective and objective evaluation. The code of our fusion method is available at https://***/hli1221/imagefusion-rfn-nest. © 2021, CC BY-NC-ND.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

EDEN: Deep feature distribution pooling for Saimaa ringed seals pattern matching

arXiv

引用

arXiv 2021年

作者： Chelak, Ilia Nepovinnykh, Ekaterina Eerola, Tuomas Kälviäinen, Heikki Belykh, Igor Peter the Great St. Petersburg Polytechnic University Saint Petersburg Russia Lappeenranta-Lahti University of Technology LUT School of Engineering Science Department of Computational Engineering Computer Vision and Pattern Recognition Laboratory P.O.Box 20 Lappeenranta53850 Finland

In this paper, pelage pattern matching is considered to solve the individual re-identification of the Saimaa ringed seals. Animal re-identification together with the access to large amount of image material through camera traps and crowd-sourcing provide novel possibilities for animal monitoring and conservation. We propose a novel feature pooling approach that allow aggregating the local pattern features to get a fixed size embedding vector that incorporate global features by taking into account the spatial distribution of features. This is obtained by eigen decomposition of covariances computed for probability mass functions representing feature maps. Embedding vectors can then be used to find the best match in the database of known individuals allowing animal re-identification. The results show that the proposed pooling method outperforms the existing methods on the challenging Saimaa ringed seal image data. © 2021, CC BY-NC-ND.

关键词： pattern matching

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

A win-win deal: towards sparse and robust pre-trained language models 22

A win-win deal: towards sparse and robust pre-trained langua...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Yuanxin Liu Fandong Meng Zheng Lin Jiangnan Li Peng Fu Yanan Cao Weiping Wang Jie Zhou Institute of Information Engineering Chinese Academy of Sciences and MOE Key Laboratory of Computational Linguistics Peking University and School of Computer Science Peking University Pattern Recognition Center WeChat AI Tencent Inc China Institute of Information Engineering Chinese Academy of Sciences and School of Cyber Security University of Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences

ISBN: (纸本)9781713871088

Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely on the dataset bias and struggle to generalize to out-of-distribution (OOD) data. In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance. Such subnetworks can be found in three scenarios: 1) the fine-tuned PLMs, 2) the raw PLMs and then fine-tuned in isolation, and even inside 3) PLMs without any parameter fine-tuning. However, these results are only obtained in the indistribution (ID) setting. In this paper, we extend the study on PLMs subnetworks to the OOD setting, investigating whether sparsity and robustness to dataset bias can be achieved simultaneously. To this end, we conduct extensive experiments with the pre-trained BERT model on three natural language understanding (NLU) tasks. Our results demonstrate that sparse and robust subnetworks (SRNets) can consistently be found in BERT, across the aforementioned three scenarios, using different training and compression methods. Furthermore, we explore the upper bound of SRNets using the OOD information and show that there exist sparse and almost unbiased BERT subnetworks. Finally, we present 1) an analytical study that provides insights on how to promote the efficiency of SRNets searching process and 2) a solution to improve subnetworks' performance at high sparsity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-slimmed vision Transformer

arXiv

引用

arXiv 2021年

作者： Zong, Zhuofan Li, Kunchang Song, Guanglu Wang, Yali Qiao, Yu Leng, Biao Liu, Yu School of Computer Science and Engineering Beihang University China SenseTime Research China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Shanghai AI Laboratory China

vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting token-to-token comparison. The previous works focus on dropping insignificant tokens to reduce the computational cost of ViTs. But when the dropping ratio increases, this hard manner will inevitably discard the vital tokens, which limits its efficiency. To solve the issue, we propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation. As a general method of token hard dropping, our TSM softly integrates redundant tokens into fewer informative ones. It can dynamically zoom visual attention without cutting off discriminative token relations in the images, even with a high slimming ratio. Furthermore, we introduce a concise Feature Recalibration Distillation (FRD) framework, wherein we design a reverse version of TSM (RTSM) to recalibrate the unstructured token in a flexible auto-encoder manner. Due to the similar structure between teacher and student, our FRD can effectively leverage structure knowledge for better convergence. Finally, we conduct extensive experiments to evaluate our SiT. It demonstrates that our method can speed up ViTs by 1.7× with negligible accuracy drop, and even speed up ViTs by 3.6× while maintaining 97% of their performance. Surprisingly, by simply arming LV-ViT with our SiT, we achieve new state-of-the-art performance on ImageNet. Code is available at https://***/Sense-X/SiT. © 2021, CC BY.

关键词： Distillation

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：