检索结果-内蒙古大学图书馆

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Xueke Chi Da-Han Wang Yuefeng Wu Yun Wu Fujian Key Laboratory of Pattern Recognition and Image Understanding China and School of Computer and Information Engineering Xiamen University of Technology China

ISBN: (纸本)9781450385053

Attention-based encoder-decoder models have made great success on handwritten mathematical expression recognition in recent years. However, this kind of method has the problem of attention drift, because under the local attention mechanism based on RNN, the high similarity between coding features can cause attention confusion. To settle this problem, we propose an encoder-decoder model with self-attention, which captures the global information of the feature map and fuses the local information of the CNN as complementary features. Experiments are conducted on the CROHME2014 and CROHME 2016 competition datasets. The experimental results show that, when only using the official training dataset, the proposed method achieves recognition accuracies of 51.98% and 50.74% on the CROHME2014 and CROHME2016 competition datasets, respectively, which outperforms the other methods significantly. The improvements demonstrate the effectiveness of the self-attention module.

关键词： handwritten mathematical expression offline recognition non-local self-attention

来源：评论

学校读者我要写书评

暂无评论

Stain-Adaptive Self-Supervised Learning for Histopathology Image Analysis

arXiv

引用

arXiv 2022年

作者： Ye, Hai-Li Wang, Da-Han Department of Computer and Information Engineering Xiamen University of Technology Xiamen361000 China Fujian Provincial Key Laboratory of Pattern Recognition and Image Understanding Xiamen361000 China

It is commonly recognized that color variations caused by differences in stains is a critical issue for histopathology image analysis. Existing methods adopt color matching, stain separation, stain transfer or the combination of them to alleviate the stain variation problem. In this paper, we propose a novel Stain-Adaptive Self-Supervised Learning(SASSL) method for histopathology image analysis. Our SASSL integrates a domain-adversarial training module into the SSL framework to learn distinctive features that are robust to both various transformations and stain variations. The proposed SASSL is regarded as a general method for domain-invariant feature extraction which can be flexibly combined with arbitrary downstream histopathology image analysis modules (e.g. nuclei/tissue segmentation) by fine-tuning the features for specific downstream tasks. We conducted experiments on publicly available pathological image analysis datasets including the PANDA, BreastPathQ, and CAMELYON16 datasets, achieving the state-of-the-art performance. Experimental results demonstrate that the proposed method can robustly improve the feature extraction ability of the model, and achieve stable performance improvement in downstream tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Anomaly Handwritten Text Detection for Automatic Descriptive Answer Evaluation 11

Anomaly Handwritten Text Detection for Automatic Descriptive...

引用

11th International Conference on Computing and pattern recognition, ICCPR 2022

作者： Chatterjee, Nilanjana Shivakumara, Palaiahnaakote Pal, Umapada Lu, Tong Lu, Yue Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia National Key Lab for Novel Software Technology Nanjing University Nanjing China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China

ISBN: (纸本)9781450397056

Although there are advanced technologies for character recognition, automatic descriptive answer evaluation is an open challenge for the document image analysis community due to large diversified handwritten text and answers to the question. This paper presents a novel method for detecting anomaly handwritten text in the responses written by the students to the questions. The method is proposed based on the fact that when the students are confident in answering questions, the students usually write answers legibly and neatly while they are not confident, they write sloppy writing which may not be easy for the reader to understand. To detect such anomaly handwritten text, we explore a new combination of Fourier transform and deep learning model for detecting edges. This result preserves the structure of handwritten text. For extracting features for classification of anomaly text and normal text, the proposed method studies the behavior of writing style, especially the variation at ascenders and descenders. Therefore, the proposed work draws principal axis which is invariant to rotation, scaling and some extent to distortion for the edge images. With respect to principal axis, the proposed method draws medial axis using uppermost and lowermost points. The distance between the medial axis and principal axis points are considered as feature vector. Further, the feature vector is passed to Artificial Neural Network for classification of anomaly text. The proposed method is evaluated by testing on our own dataset, standard dataset of gender identification (IAM) and handwritten forgery detection dataset (ACPR 2019). The results on different datasets show that the proposed work outperforms the existing methods. © 2022 ACM.

关键词： Students

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

Hierarchical Local Global Transformer for Point Clouds Analysis

SSRN

引用

SSRN 2023年

作者： Li, Dilong Zheng, Shenghong Chen, Ziyi Li, Xiang Wang, Lanying Du, Jixiang College of Computer Science and Technology Fujian Key Laboratory of Big Data Intelligence and Security Xiamen Key Laboratory of Computer Vision and Pattern Recognition Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University FJ Xiamen361021 China School of Economics and Finance Huaqiao University FJ Quanzhou362021 China Department of Geography and Environmental Management University of Waterloo WaterlooONN2L 3G1 Canada

Transformer networks have demonstrated remarkable performance in point cloud analysis. However, achieving a balance between local regional context and global long-range context learning remains a significant challenge. In this paper, we propose a Hierarchical Local Global Transformer Network (LGTNet), designed to capture local and global contexts in a hierarchical manner. Specifically, we employ serial local and global Transformers to learn the inner-group and cross-group self-attention, respectively. Besides, we propose a geometric moment-based position encoding for local Transformer, enabling the embedding of comprehensive local geometric relationship. Additionally, we also introduce a global feature pooling module that extracts the global features from each encoder layers. Extensive experimental results demonstrate that LGTNet achieves state-of-the-art performance on ShapeNetPart and ScanObjectNN datasets. This approach effectively enhances the understanding of point cloud scenes, thereby facilitating the use of point cloud data in remote sensing applications. © 2023, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Fast Algorithm for Parallel Solving Inversion of Large Scale Small Matrices Based on Gpu

SSRN

引用

SSRN 2022年

作者： Jin, Xuebin Chen, Yewang Fan, Wentao Zhang, Yong Du, Jixiang The College of Computer Science and Technology Huaqiao University Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China College of Mechanical Engineering and Automation Huaqiao University Xiamen China

Inverting a matrix is time-consuming, and many works focus on accelerating inverting a single large matrix by GPU. However, the problem of inverting large-scale small matrices has little attention. In this paper, we propose a Revised In-Place Inversion algorithm for inverting large-scale small matrices, which runs on the CUDA platform and utilizes multicore GPUs. The proposed algorithm is well-suited for large-scale-small matrices (dimension $n \leq 32$), which can invert millions of small matrices within tens of milliseconds. In addition, we find there is an upper bound of input data size for each GPU device, the performance will degrade if the input data size is too large. Hence, we improve the proposed method by dividing matrices into batches according to this finding. Experimental results show that this strategy can effectively alleviate the performance degradation for inverting large scale small matrices, and maintain the high-performance execution of the algorithm. © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Real-time 3D human pose estimation without skeletal a priori structures

引用

Image and vision Computing 2023年 132卷

作者： Bai, Guihu Luo, Yanmin Pan, Xueliang Wang, Jia Guo, Jing-Ming College of Computer Science and Technology Huaqiao University 668 Jimei Avenue Jimei District Fujian Xiamen361021 China Key Laboratory for Computer Vision and Pattern Recognition Huaqiao University 668 Jimei Avenue Jimei District Fujian Xiamen361021 China The Department of Electrical Engineering National Taiwan University of Science and Technology Taipei10607 Taiwan

This study is about real-time 2D-3D human pose estimation without using the a priori structure of the skeleton and with a low number of parameters for regression tasks. Current graph convolution-based 3D human pose tasks require structural knowledge of the skeleton, which limits the exploration of pose estimation for unknown structures. Inspired by tyre rotation and circular convolution, weights rotation is used to fully learn the potential connections between the human joints. We refer to this process as the weight cyclic sharing mechanism, a novel method for updating features. It does not require knowledge of the structure of the human skeleton and learns different constraints between joints with a low number of parameters. We propose an end-to-end weight circular sharing network (WCirSNet) based on the weight circular sharing mechanism. We propose a simple and efficient weighted residual block in this WCirSNet. The superiorities of the weight circular sharing mechanism and weighted residual block were verified by abundant ablation studies. Extensive evaluations on two challenging benchmark datasets (Human 3.6 M, MPI-INF-3DHP) show that the performance and generalization capabilities of our framework are superior to the results of many previously advanced methods. © 2023 Elsevier B.V.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Local Neighbor Propagation on Graphs for Robust Feature Matching

SSRN

引用

SSRN 2023年

作者： Guo, Hanlin Xiao, Guobao Su, Lumei Zhou, Jiaxing Wang, Dahan Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control School of Electrical Engineering and Automation Xiamen University of Technology China Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Information Science and Engineering Xiamen University China College of Computer and Control Engineering Minjiang University China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology China

Establishing reliable correspondences between two sets of feature points is a critical preprocessing step in many computer vision and pattern recognition tasks. In this paper, we propose a novel robust Local Neighbor Propagation on Graphs based feature matching (LNPG) method, to obtain good correspondences for feature matching. LNPG starts from a novel neighborhood graph construction strategy. The strategy leverages the spatial consistency constraint to generate a series of neighborhood sets, and employs the residual information to preserve the local neighborhood relationships of potential inliers (i.e., true matches). Subsequently, LNPG incorporates local neighbor propagation into the graph to enhance connections between data in different neighborhoods, by using the path-based similarity measurement and the adaptive graph partition. In addition, LNPG includes a novel consistency-filtering-based clustering algorithm for robust feature matching. This clustering algorithm introduces a reliable neighborhood consistency measure function and an effective cluster merging criterion for cluster detection and cluster merging during the clustering process, respectively. Overall, LNPG not only effectively distinguishes inliers from outliers, but also reliably classifies inliers into different transformation models between pairs of images. Experiments on publicly available datasets with different types of image transformations show the superiority of our LNPG in comparison with other state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

Activating More Pixels in Image Super-Resolution Transformer

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Xiangyu Chen Xintao Wang Jiantao Zhou Yu Qiao Chao Dong State Key Laboratory of Internet of Things for Smart City University of Macau Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory ARC Lab Tencent PCG

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UNIFORMER: UNIFIED TRANSFORMER FOR EFFICIENT SPATIOTEMPORAL REPRESENTATION LEARNING 10

UNIFORMER: UNIFIED TRANSFORMER FOR EFFICIENT SPATIOTEMPORAL ...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Li, Kunchang Wang, Yali Gao, Peng Song, Guanglu Liu, Yu Li, Hongsheng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory Shanghai China SenseTime Research The Chinese University of Hong Kong Hong Kong

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been mainly driven by 3D convolutional neural networks and vision transformers. Although 3D convolution can efficiently aggregate local context to suppress local redundancy from a small 3D neighborhood, it lacks the capability to capture global dependency because of the limited receptive field. Alternatively, vision transformers can effectively capture long-range dependency by self-attention mechanism, while having the limitation on reducing local redundancy with blind similarity comparison among all the tokens in each layer. Based on these observations, we propose a novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy. Different from traditional transformers, our relation aggregator can tackle both spatiotemporal redundancy and dependency, by learning local and global token affinity respectively in shallow and deep layers. We conduct extensive experiments on the popular video benchmarks, e.g., Kinetics-400, Kinetics-600, and Something-Something V1&V2. With only ImageNet-1K pretraining, our UniFormer achieves 82.9%/84.8% top-1 accuracy on Kinetics-400/Kinetics-600, while requiring 10× fewer GFLOPs than other state-of-the-art methods. For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60.9% and 71.2% top-1 accuracy respectively. Code is available at https://***/Sense-X/UniFormer. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Redundancy

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：