检索结果-内蒙古大学图书馆

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

A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement

arXiv

引用

arXiv 2023年

作者： Biswas, Risab Roy, Swalpa Kumar Pal, Umapada Maharashtra Mumbai400066 India Department of Computer Science and Engineering Alipurduar Government Engineering and Management College West Bengal 736206 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult to recognize and analyze them. In this paper, we propose T2T-BinFormer which is a novel document binarization encoder-decoder architecture based on a Tokens-to-token vision transformer. Each image is divided into a set of tokens with a defined length using the ViT model, which is then applied several times to model the global relationship between the tokens. However, the conventional tokenization of input data does not adequately reflect the crucial local structure between adjacent pixels of the input image, which results in low efficiency. Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokenization technique to capture this local information from an image to achieve more effective results. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods. In this research, the primary area of examination is the application of the proposed architecture to the task of document binarization. The source code will be made available at https://***/RisabBiswas/T2T-BinFormer. © 2023, CC BY-SA.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Tldsmi: Genetic Algorithm Based Network for Text Localization in Distorted Social Media Images

SSRN

引用

SSRN 2023年

作者： Palaiahnakote, Shivakumara Kumar, C. Pavan Aggarwal, Pranjal Sharma, Shubham Chandana, Pasupuleti Basavanna, M. Pal, Umapada Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia Indian Institute of Information Technology Dharwad India University of Davanagere Karnataka India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

This paper presents a novel model for understanding social image content through text localization. For text localization, we explore Maximally Stable Extremal Regions (MSER) for detecting components, that works by clustering pixels having similar properties. The output of component detection includes several non-text components due to degradations of social media images. To select the best components among many, we explore Genetic Algorithm by convolving different kernels with components, which results in a feature matrix which is further fed to EfficientNet for choosing actual text components. Therefore, the proposed model is called Genetic Algorithm based Network for Text Localization in Distorted Social Media Images (TLDSMI). For evaluating text localization, we consider the images of standard dataset of natural scene by uploading and downloading from different social media platforms, namely, WhatsApp, Telegram and Instagram. The effectiveness of our method is shown by testing on original and distorted standard datasets. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

LADDER: Revisiting the Cosmic Distance Ladder with Deep Learning Approaches and Exploring its Applications

arXiv

引用

arXiv 2024年

作者： Shah, Rahul Saha, Soumadeep Mukherjee, Purba Garain, Utpal Pal, Supratik Physics and Applied Mathematics Unit Indian Statistical Institute 203 B.T. Road Kolkata700 108 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B.T. Road Kolkata700 108 India

We investigate the prospect of reconstructing the "cosmic distance ladder" of the Universe using a novel deep learning framework called LADDER - Learning Algorithm for Deep Distance Estimation and Reconstruction. LADDER is trained on the apparent magnitude data from the Pantheon Type Ia supernovae compilation, incorporating the full covariance information among data points, to produce predictions along with corresponding errors. After employing several validation tests with a number of deep learning models, we pick LADDER as the best performing one. We then demonstrate applications of our method in the cosmological context, including serving as a model-independent tool for consistency checks for other datasets like baryon acoustic oscillations, calibration of high-redshift datasets such as gamma ray bursts, and use as a model-independent mock catalog generator for future probes. Our analysis advocates for careful consideration of machine learning techniques applied to cosmological contexts. Copyright © 2024, The Authors. All rights reserved.

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

Endafd: An End-to-End System for Ecg Based Atrial Fibrillation Detection

SSRN

引用

SSRN 2022年

作者： Basak, Shubham Das, Sudip Dasgupta, Subhrajyoti Bhattacharya, Ujjwal Narayan, Pradeep Computer Vision and Pattern Recognition Unit Indian Statistical Institute WB Kolkata India Rabindranath Tagore International Institute of Cardiac Sciences WB Kolkata India

Atrial fibrillation is one of the most common arrhythmias with significant clinical implications. When it comes to detecting and categorising different types of heart diseases, machine learning and deep learning techniques have shown great results. There is a tendency to use convolution-based neural networks, as they have been specifically designed to categorise and recognise images. Image classification entails extracting image attributes in order to identify certain patterns in the dataset. The use of a basic ANN for this classifications would be computationally costly due to the large number of trainable parameters. Traditional convolution-based detection approaches, on the other hand, occasionally provided skewed findings since they had to integrate all 12 ecg leads to acquire the result. They will occasionally overlook the findings of a single lead abnormality if no other leads are shown to be defective. However, in the instance of a transformer, they take a single lead value at a time and check to see if there is any irregularity within that lead. Although the training may not always be successful owing to the small number of input samples, the results are typically rigged in favor of the negative since the number of negative samples is considerably larger than the positive ones We need a way to generate a larger number of balanced samples via the model, and then train the model to evaluate the original input. This is where the model comes in. A unique end-to-end model is suggested, consisting of two vision transformers connected by a generative adversarial network. © 2022, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Survey of Automatic Plankton Image recognition: Challenges, Existing Solutions and Future Perspectives

arXiv

引用

arXiv 2023年

作者： Eerola, Tuomas Batrakhanov, Daniel Barazandeh, Nastaran Vatankhah Kraft, Kaisa Haraguchi, Lumi Lensu, Lasse Suikkanen, Sanna Seppälä, Jukka Tamminen, Timo Kälviäinen, Heikki Computer Vision and Pattern Recognition Laboratory LUT University Yliopistonkatu 34 Lappeenranta53850 Finland Marine Ecology Measurements Finnish Environment Institute Agnes Sjöbergin Katu 2 Helsinki00790 Finland

Planktonic organisms are key components of aquatic ecosystems and respond quickly to changes in the environment, therefore their monitoring is vital to follow and understand the changes in the environment. Yet, monitoring plankton at appropriate scales still remains a challenge, limiting our understanding of functioning of aquatic systems and their response to changes, which reduces the effectiveness of mitigation measures. Modern plankton imaging instruments can be utilized to sample at high frequencies, producing large amounts of images and enabling novel possibilities to study plankton populations. However, manual analysis of the data is costly, time consuming and expert based, making such approach unsuitable for large-scale application and urging for automatic solutions. The key problem related to the utilization of plankton datasets through image analysis is plankton recognition, i.e., classification of the images. Despite the large amount of research done on automatic plankton recognition, these methods have not been widely adopted for operational use. In this paper, a comprehensive survey on existing solutions for automatic plankton recognition is presented. First, we identify the most notable challenges that make the development of plankton recognition systems difficult and restrict the deployment of these systems for large-scale operational use. Then, we provide a detailed description of solutions for these challenges proposed in plankton recognition literature. Finally, we propose a workflow to identify the specific challenges in new datasets and the recommended approaches to address them. For many of the challenges, applicable solutions exist. This is not the case for all and important challenges remain unsolved: 1) the domain shift between the datasets hindering the development of a general plankton recognition system that would work across different imaging instruments, 2) the difficulty to identify and process the images of previously unseen classes (e

关键词： Plankton

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

Artist-Aware Image Style Transfer Via Text Guided Contrastive Learning

SSRN

引用

SSRN 2023年

作者： Liu, Zhi-Song Wang, Li-Wen Siu, Wan-Chi Kalogeiton, Vicky Computer Vision and Pattern Recognition Laboratory LUT University Finland Caritas Institute of Higher Education Hong Kong The Hong Kong Polytechnic University Hong Kong LIX Ecole Polytechnique IP Paris France

Image style transfer has attracted widespread attention in the past few years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using text is the most natural way to describe the style. More importantly, text can describe implicit abstract styles, like styles of specific artists or art movements. In this paper, we propose a text-driven image style transfer (TxST) that leverages advanced image-text encoders to control arbitrary style transfer. We introduce a contrastive training strategy to effectively extract style descriptions from the image-text model (i.e., CLIP), which aligns stylization with the text description. To this end, we also propose a novel and efficient attention module that explores cross-attentions to fuse style and content features. Finally, we achieve an arbitrary artist-aware image style transfer that can use either image or text for stylization. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods on both image and text-guided style transfer. Moreover, it can mimic the styles of multiple artists to achieve attractive results, thus highlighting a promising direction in image style transfer. © 2023, The Authors. All rights reserved.

关键词： Abstracting

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

Split-net: Dual transformer encoder with splitting scene text image for script identification

引用

pattern recognition Letters 2025年 196卷 100-108页

作者： Ayush Roy Shivakumara Palaiahnakote Umapada Pal Cheng-Lin Liu Department of Computer Science and Engineering State University of New York Buffalo United States School of Science Engineering and Environment University of Salford Manchester United Kingdom Computer Vision and Pattern Recognition Indian Statistical Institute Kolkata India State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of the Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Script identification is vital for understanding scenes and video images. It is challenging due to high variations in physical appearance, typeface design, complex background, distortion, and significant overlap in the characteristics of different scripts. Unlike existing models, which aim to tackle the script images utilizing the scene text image as a whole, we propose to split the image into upper and lower halves to capture the intricate differences in stroke and style of various scripts. Motivated by the accomplishments of the transformer, a modified script-style-aware Mobile-vision Transformer (M-ViT) is explored for encoding visual features of the images. To enrich the features of the transformer blocks, a novel Edge Enhanced Style Aware Channel Attention Module (EESA-CAM) has been integrated with M-ViT. Furthermore, the model fuses the features of the dual encoders (extracting features from the upper and the lower half of the images) by a dynamic weighted average procedure utilizing the gradient information of the encoders as the weights. In experiments on three standard datasets, MLe2e, CVSI2015, and SIW-13, the proposed model yielded superior performance compared to state-of-the-art models.

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：