检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of computer vision, WACV 2025

作者： Arrabi, Ahmad Zhang, Xiaohan Sultani, Waqas Chen, Chen Wshah, Safwan University of Vermont Vermont Artificial Intelligence Lab Department of Computer Science United States Information Technology University Intelligent Machines Lab Pakistan University of Central Florida Center for Research in Computer Vision United States

ISBN: (纸本)9798331510831

Aerial imagery analysis is critical for many research fields. However, obtaining frequent high-quality aerial images is not always accessible due to its high effort and cost requirements. One solution is to use the Ground-to-Aerial (G2A) technique to synthesize aerial images from easily collectible ground images. However, G2A is rarely studied, because of its challenges, including but not limited to, the drastic view changes, occlusion, and range of visibil-ity. In this paper, we present a novel Geometric Preserving Ground-to-Aerial (G2A) image synthesis (GPG2A) model that can generate realistic aerial images from ground images. GPG2A consists of two stages. The first stage predicts the Bird's Eye View (BEV) segmentation (referred to as the BEV layout map) from the ground image. The second stage synthesizes the aerial image from the predicted BEV layout map and text descriptions of the ground image. To train our model, we present a new multimodal cross-view dataset, namely VIGORv2, built upon VIGOR [64] with newly collected aerial images, maps, and text descriptions. Our extensive experiments illustrate that GPG2A synthesizes better geometry-preserved aerial images than existing models. We also present two applications, data augmentation for cross-view geo-localization and sketch-based region search, to further verify the effectiveness of our GPG2A. The code and dataset are available at https://***/AhmadArrabi/GPG2A. © 2025 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

On the Performance of CNN and GAN models for Melanoma Classification 2

On the Performance of CNN and GAN models for Melanoma Classi...

引用

2nd International Conference on Artificial intelligence and Signal Processing, AISP 2022

作者： Joson, Nikhil Nair, Madhu S. Artificial Intelligence & Computer Vision Lab Department of Computer Science Cochin University of Science and Technology Kerala Kochi682022 India

ISBN: (纸本)9781665442909

Melanoma is the most harmful form of skin cancer and they emerge from melanocytes, a type of pigment-producing cells. Melanomas usually occur on the skin;they mostly form around the back for men, whereas the common place for women are legs. Once formed, symptoms of melanoma might include an increase in the size of some mole with irregular edges, or itchiness or changes in its color, etc. This paper reviews the latest research works on melanoma classification using CNN. The performance analysis of the state-of-the-art methods is done focusing only on the binary classification of melanoma. The dataset used for the performance analysis is based on SIIM-ISIC Melanoma Classification Challenge 2020, where the task was to identify melanoma using images of skin lesions by predicting a binary target for each image. The main intent of this study is to review the state-of-the-art deployments which identifies the recent research trends, challenges, and newer domains, like Generative Adversarial Networks (GAN) for melanoma classification and scrutinize the existing solutions for melanoma detection. © 2022 IEEE.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection using Multi-path CNN and Convolutional Attention Mechanism 2

Deepfake Detection using Multi-path CNN and Convolutional At...

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Rineesh Babu, P. Nair, Madhu S. Cochin University of Science and Technology Artificial Intelligence & Computer Vision Lab Department of Computer Science Kerala Kochi682022 India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

Image and video forgery using cutting-edge deep learning techniques has become one of the major issues in the social networking era. Media manipulation in which one person's face is swapped out for another's or has additional features added is referred to as deepfakes. Despite the fact that it has many beneficial purposes, fraudsters generally utilise it to create celebrity porn, revenge porn, and fake news, among other things. One of the biggest risks that deepfake presents is that people's belief in the reality of many things may decline. The motivation behind deepfake detection is the need to prove that the real thing is real and the fake thing is fake. In this paper a multi-CNN approach for detecting deepfakes is being proposed. Here, a multipath convolutional neural network (CNN) with three modules is used, each of which is stacked with a convolutional block attention mechanism. The first two modules in the dual-path paradigm are a Resnet module and a Densenet module. The Resnet component enables for feature reuse while Densenet allows for the investigation of new features. The parallel InceptionResnet module contains a one-dimensional feature reduction module with residual connections. When the performance of the proposed model is compared with that of four deep learning based approaches, it is found that the proposed method gave the best outcomes, with an accuracy and F1-score of 0.940 and 0.939, respectively. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

PVT v2:Improved baselines with Pyramid vision Transformer

引用

Computational Visual Media 2022年第3期8卷 415-424页

作者： Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo Ling Shao Shanghai AI Laboratory Shanghai 200232China Department of Computer Science and Technology NanjingUniversityNanjing 210023China Department of Computer Science the University ofHong KongHong Kong 999077China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210014China Computer Vision Lab ETH ZurichZurich 8092Switzerland SenseTime Beijing 100080China Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Transformers have recently lead to encouraging progress in computer *** this work,we present new baselines by improving the original Pyramid vision Transformer(PVT v1)by adding three designs:(i)a linear complexity attention layer,(ii)an overlapping patch embedding,and(iii)a convolutional feed-forward *** these modifications,PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification,detection,and *** particular,PVT v2 achieves comparable or better performance than recent work such as the Swin *** hope this work will facilitate state-ofthe-art transformer research in computer *** is available at https://***/whai362/PVT.

关键词： transformers dense prediction image classification object detection semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Dual Encoder-Decoder U-Net Architecture for Polyp Segmentation in Colonoscopy Images with Shuffle Attention and Conditional Random Fields

Dual Encoder-Decoder U-Net Architecture for Polyp Segmentati...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Lijin P. Santhosh Kumar G. Madhu S. Nair Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi Kerala India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

Colonoscopy plays a pivotal role in detecting and diagnosing colorectal diseases, with polyp segmentation being a critical step for accurate diagnosis. In this study, we propose a novel approach for polyp segmentation in colonoscopy images, leveraging the Shuffle attention mechanism within the proposed architecture. Our method is rigorously evaluated across three diverse colonoscopy datasets, demonstrating promising results with an mean dice score of 0.93. Furthermore, to enhance segmentation accuracy, we employ a Conditional Random Field (CRF) post-processing method to refine the segmentation results. Through extensive experimentation and analysis, we showcase the effectiveness of our approach in achieving highly accurate polyp segmentation, thereby contributing to improved diagnostic outcomes in colorectal healthcare. Our method holds significant potential for enhancing computer-aided detection systems in clinical practice, facilitating early detection and treatment of colorectal abnormalities.

关键词： Measurement Image segmentation Accuracy Computational modeling Colonoscopy computer architecture Medical services

来源：评论

学校读者我要写书评

暂无评论

Classification on Compressed DNA Sequences: Correlation-Based Feature Extraction Using Self-Supervised Learning

Classification on Compressed DNA Sequences: Correlation-Base...

引用

IEEE EMBS Conference on Biomedical Engineering and sciences (IECBES)

作者： Sheena K. S. Madhu S. Nair Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi Kerala India

ISBN: (数字)9798350383409

ISBN: (纸本)9798350383416

Next-generation sequencing is producing data at an exponential rate, which creates immense computation hurdles for reliably and efficiently storing, transmitting, and analysing the data. Compression plays a vital role in managing the challenges associated with the growing volume of genomic data. Direct analysis over the compressed representations of DNA sequences can facilitate scalability, enabling the analysis of larger datasets within reasonable computational resources. The proposed scheme develops a methodology to extract meaningful features from compressed DNA sequences that maintain a high correlation with features from the original sequences. We employed deep learning techniques to maximize feature correlation between original and compressed sequence representations. This approach ensures that the features derived from compressed sequences are as informative and representative as those from the original sequences. We evaluated the proposed method with various state-of-the-art approaches for genomic sequence analysis using a dataset that includes genome sequences of different viruses. According to the results, the features extracted from compressed sequences are discriminative for the classification task; thus, downstream analysis of genomic sequences is possible without decompression.

关键词： Sequential analysis Correlation Sequences computer viruses Scalability Genomics Self-supervised learning Feature extraction Reliability Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Lossless DNA Sequence Compression: Exploring Spatial and Sequential Redundancies of DNA Sequence with 2-D CNN Autoencoder

Lossless DNA Sequence Compression: Exploring Spatial and Seq...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Sheena K. S. Madhu S. Nair Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi Kerala India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

The volume of genomic data being generated is growing due to the technological breakthroughs in genome sequencing and the economic affordability of sequencing. Consequently, the need for compression techniques that are specifically designed for genomic data is rising. Deep learning provides robust methods for reducing the data size and unlocking the full potential of genomic information. The proposed method minimizes storage requirements by applying a 2-D convolutional neural network autoencoder, which learns spatial and sequential redundancies in the sequence to compress the data losslessly. In contrast to conventional compression methods, which handle data as a one-dimensional sequence, the proposed approach uses the spatial structure of the data to produce more compact representations. We evaluated the proposed method with various compression approaches, including state-of-the-art DNA sequence compression algorithms, on two homo sapiens genomes. Experimental results indicate that the proposed method can compress the genomic data effectively, with an improvement of 31.3% compression over the best existing method.

关键词： Deep learning Sequential analysis Biological system modeling Redundancy Genomics DNA Data models

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-Assisted Feature-Type Distributed Clustering for Clinical and Biomedical Data Analysis

Autoencoder-Assisted Feature-Type Distributed Clustering for...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Lenat Thomas Madhu S. Nair Saptarshi Bej Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi India Department of Data Science Indian Institute of Science Education and Research Thiruvananthapuram India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

The Uniform Manifold Projection and Approximation (UMAP) assisted Feature-type Distributed Clustering (FDC) workflow, contrary to the traditional UMAP algorithm, was found to be more informative for dimensionality reduction in tabular Clinical and Biomedical Routine Data (CBRD) due to the presence of diverse feature-types in such datasets. However, the prospect of using powerful neural network models for the Feature-type distributed dimensionality reduction task is yet to be explored. Considering the broader applicative potential of neural networks, we compared some autoencoder-based neural networks as an alternative to the UMAP algorithm for the FDC workflow. The study uses standard objective measures such as Silhouette Score and DB-Index to compare the quality of clusters and embeddings generated by the Autoencoder-assisted FDC (FDC-AE) approaches with the established UMAP-assisted FDC (FDC-UMAP) workflow. The evaluation involved two datasets in each size category from the medical field. The results indicate that for a dimensionality reduction and cluster identification task, the FDC-AE can be more effective compared to the FDC-UMAP, especially on larger datasets. Our research opens up the possibility of feature-distributed multi-label supervised dimensionality reduction, as well as the usage of pre-trained networks for such complex dimensionality reduction tasks.

关键词： Dimensionality reduction Manifolds Biological system modeling Neural networks Clustering algorithms Distributed databases Biomedical measurement Communications technology Bioinformatics Standards

来源：评论

学校读者我要写书评

暂无评论

vision Transformer Based Automated Model for Enhancing Lung Cancer Classification

Vision Transformer Based Automated Model for Enhancing Lung ...

引用

2024 IEEE International Conference on Imaging Systems and Techniques, IST 2024

作者： Akbari, Akbar Sheikh Kumar, Arvind Reddy, B Ramachandra Singh, Koushlendra Kumar Takei, Masahiro Leeds Beckett University United Kingdom National Institute of Technology Machine Vision and Intelligence Lab Jharkhand Jamshedpur India Computer Science and Engineering National Institute of Technology Jharkhand Jamshedpur India Chiba University Department of Mechanical Engineering Chiba Japan

ISBN: (纸本)9798350378214

Lung cancer is one of the leading causes of cancer related mortality. The early detection and classification of the cancers tissues will reduce the mortalities rate. The present research focus on the development of automated classification model for lung and colon cancers tissues based on the histopathology images. The present work encompasses a vision transformer (ViT) based model to enhance diagnostic accuracy of lung cancers tissues. The proposed model utilizes the self-attention mechanism of ViT to focus on essential features present in histopathologicals images. The proposed model has been validated using two different dataset namely LC25000 & IQ-OTH/NCCD with 25000 & 1096 images respectively. The performance of proposed model is compared with traditional convolutional neural network (CNN) model and it has been observed the based model outforms better in terms of accuracy which - 98.80% & 99.09% respectively for datasets. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance

Cross-View Meets Diffusion: Aerial Image Synthesis with Geom...

引用

IEEE Workshop on Applications of computer vision (WACV)

作者： Ahmad Arrabi Xiaohan Zhang Waqas Sultani Chen Chen Safwan Wshah Department of Computer Science Vermont Artificial Intelligence Lab University of Vermont Intelligent Machines Lab Information Technology University Center for Research in Computer Vision University of Central Florida

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

关键词： Geometry Image segmentation computer vision Costs Image synthesis Geology Computational modeling Layout Diffusion models Data augmentation

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：