检索结果-内蒙古大学图书馆

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Kumar, Abhinav Gupta, Shantanu Kozitsky, Vladimir Madhvanath, Sriganesh Univ Utah Salt Lake City UT 84112 USA Univ Wisconsin Madison WI USA MKS Instruments Andover MA USA eBay New York NY USA Conduent Labs Res Triangle Pk NC USA

ISBN: (纸本)9781450366151

We consider the license plate re-identification task, treated here as a one-shot image retrieval problem. Our objective is to learn a feature representation for license plate images, such that a single training image of a given license plate (referred to as a template image) is sufficient to perform nearest-neighbour retrieval with high accuracy at test time. Also, the feature representation should ideally be generalisable across datasets and should be extractable in real-time on resource-constrained embedded hardware or a moderately powerful cellphone. We evaluate representations from person re-identification (re-id) literature, learned from a trained deep convolutional network as well with those derived from a trained Fisher vector. While the convolutional network features perform better than the Fisher vector, we obtain comparable results from a hybrid model projecting the Fisher vector into a lower-dimensional space via two fully connected layers called f2nn using the triplet loss. The proposed hybrid model f2nn generates features which outperform and generalise better than convolutional features on datasets dissimilar to the training corpus. The model can be trained in stages and takes significantly less time to extract features. Further, it uses much smaller feature dimensions for license plate images resulting in faster re-identification, and is therefore well-suited for resource-constrained platforms such as mobile devices.

关键词： image Retrieval Feature Generation Fisher Vectors Neural Networks Triplet Loss Signature Matching Generalisation Dimensionality Reduction License Plate Re-identification Optical Character Recognition

来源：评论

学校读者我要写书评

暂无评论

Leveraging information from imperfect examples : Common action sequence mining from a mix of incorrect performances 11

Leveraging information from imperfect examples : Common acti...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Jain, Hiteshi Harit, Gaurav Indian Inst Technol Jodhpur Jodhpur Rajasthan India

ISBN: (纸本)9781450366151

As much as good representation and theory are needed to explain human actions, so are the action videos used for learning good segmentation techniques. To accurately model complex actions such as diving, figure skating, and yoga practices, videos depicting action by human experts are required. Lack of experts in any domain leads to reduced number of videos and hence an improper learning. In this work we attempt to utilize imperfect amateur performances to get more confident representations of human action sequences. We introduce a novel Community Detection based unsupervised framework that provides mechanisms to interpret video data and address its limitations to produce better action representation. Human actions are composed of distinguishable key poses which form dense communities in graph structures. Anomalous poses performed for a longer duration can also form such dense communities but can be identified based on their rare occurrence across action videos and be rejected. Further, we propose a technique to learn the temporal order of these key poses from these imperfect videos, where the inter community links help reduce the search space of many possible pose sequences. Our framework is seen to improve the segmentation performance of complex human actions with the help of some imperfect performances. The efficacy of our approach has been illustrated over two complex action datasets - Sun Salutation and Warm-up exercise, that have been developed using random executions from amateur performers.

关键词： Unsupervised Anomaly Detection network modeling community detection human action segmentation

来源：评论

学校读者我要写书评

暂无评论

HSD-CNN: Hierarchically self decomposing CNN architecture using class specific filter sensitivity analysis 11

HSD-CNN: Hierarchically self decomposing CNN architecture us...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： SaiRam, K. Mukherjee, Jayanta Patra, Amit Das, Partha Pratim Indian Inst Technol Kharagpur Kharagpur W Bengal India

ISBN: (纸本)9781450366151

Conventional convolutional neural networks (CNN) are trained on large domain datasets and are hence typically over-represented and inefficient in limited class applications. An efficient way to convert such large many-class pre-trained networks into small few-class networks is through a hierarchical decomposition of its feature maps. To alleviate this issue, we propose an automated framework for such decomposition in Hierarchically Self Decomposing CNN (HSD-CNN), in four steps. HSD-CNN is derived automatically using a class-specific filter sensitivity analysis that quantifies the impact of specific features on a class prediction. The decomposed hierarchical network can be utilized and deployed directly to obtain sub-networks for a subset of classes, and it is shown to perform better without the requirement of retraining these sub-networks. Experimental results show that HSD-CNN generally does not degrade accuracy if the full set of classes is used. Interestingly, when operating on known subsets of classes, HSD-CNN has an improvement in accuracy with a much smaller model size requiring much fewer operations. HSD-CNN flow is verified on the CIFAR10, CIFAR100 and CALTECH101 datasets. We report accuracies up to 85.6% ( 94.75%) on scenarios with 13 ( 4) classes of CIFAR100, using a pre-trained VGG-16 network on the full dataset. In this case, the proposed HSD-CNN requires 3.97x fewer parameters and has 71.22% savings in operations, in comparison to baseline VGG-16 containing features for all 100 classes.

关键词： CNN hierarchical neural networks classification clustering model transfer sub-networks

来源：评论

学校读者我要写书评

暂无评论

Preface

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2020年 1249卷 v-vi页

作者： Venkatesh Babu, R. Prasanna, Mahadeva Namboodiri, Vinay P. Department of Computational and Data Sciences Indian Institute of Science Bangalore Bangalore India Department of Electrical Engineering Indian Institute of Technology Dharwad Dharwad India Indian Institute of Technology Kanpur Kanpur India

来源：评论

学校读者我要写书评

暂无评论

Subspace segmentation based metric learning 25

Subspace segmentation based metric learning

引用

25th IEEE International conference on image processing, ICIP 2018

作者： Dutta, Ujjal Kr Chandra Sekhar, C. Department of Computer Science and Engineering Indian Institute of Technology Madras India

ISBN: (纸本)9781479970612

Distance Metric Learning (DML) has been successfully applied in a variety of computer vision and image processing tasks. Laplacian Regularized Metric Learning (LRML) computes a distance metric by satisfying given sets of pairwise similarity and dissimilarity constraints while preserving the topological structure of the given data via a Laplacian regularizer which is dependent on an affinity matrix. This paper addresses the problem of semi-supervised DML using LRML for image data sampled from a union of low-dimensional subspaces by computing the affinity matrix using a self-representation based graph instead of traditional graph used in LRML, resulting in two variants of LRML called as L-NNLRS and L-NLSP. © 2018 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

computer vision, Pattern Recognition, image processing, and graphics 1st ed. 2018

引用

丛书名： Communications in computer and Information Science

2018年

作者： Renu Rameshan Chetan Arora Sumantra Dutta Roy

ISBN: (数字)9789811300202

ISBN: (纸本)9789811300196

This book constitutes the refereed proceedings of the 6th National conference on computer vision, Pattern Recognition, image processing, and graphics, NCVPRIPG 2017, held in Mandi, India, in December 2017. The 48 revised full papers presented in this volume were carefully reviewed and selected from 147 submissions. The papers are organized in topical sections on video processing; image and signal processing; segmentation, retrieval, captioning; pattern recognition applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep neural network for foreground object segmentation: An unsupervised approach 6th

Deep neural network for foreground object segmentation: An u...

引用

6th National conference on computer vision, Pattern Recognition, image processing and graphics, NCVPRIPG 2017

作者： Majumder, Avishek Venkatesh Babu, R. Indian Institute of Science BangaloreKarnataka560012 India

ISBN: (纸本)9789811300196

Saliency plays a key role in various computer vision tasks. Extracting salient regions from images and videos have been a well established problem of computer vision. While segmenting salient objects from images depend only on static information, temporal information in a video can make non salient objects be salient due to movement. Besides the temporal information, there are other challenges involved with video segmentation, such as 3D parallax, camera shake, motion blur, etc. In this work, we propose a novel unsupervised end to end trainable, fully convolutional deep neural network for object segmentation. Our model is robust and scalable across scenes, as it is tested unsupervisedly and can easily infer which objects constitute the foreground of the image. We run various tests on two well established benchmarks of video object segmentation, DAVIS and FBMS-59 datasets. We report our results and compare them against the state of the art methods. © Springer Nature Singapore Pte Ltd. 2018.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Classification of indian monuments into architectural styles 6th

Classification of indian monuments into architectural styles

引用

6th National conference on computer vision, Pattern Recognition, image processing and graphics, NCVPRIPG 2017

作者： Sharma, Saurabh Aggarwal, Priyal Bhattacharyya, Akanksha N. Indu, S. Department of Computer Science and Engineering Delhi Technological University Delhi India Department of Electronics and Communication Engineering Delhi Technological University Delhi India

ISBN: (纸本)9789811300196

We propose two novel approaches to classify indian monuments according to their distinct architectural styles. While the historical significance of most indian monuments is well documented, the details of their architectural styles are not as well recorded. Different indian architectural styles often show certain similar features which makes classification a difficult task. Previous work has focused on European architecture and standard datasets are available for the same, but no standard dataset exists for indian architecture. Therefore, we have curated a dataset of indian monuments. In this paper, we propose two approaches to classify monuments according to their styles: Radon Barcodes and Convolutional Neural Networks. The first approach is fast and consumes less memory, but the second approach gives an accuracy of 82%, which is better than the 76% accuracy of the first method. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

FACE-Face at classroom environment: Dataset and exploration 8

FACE-Face at classroom environment: Dataset and exploration

引用

8th International conference on image processing Theory, Tools and Applications, IPTA 2018

作者： Karnalim, Oscar Budi, Setia Santoso, Sulaeman Handoyo, Erico D. Toba, Hapnes Nguyen, Huyen Malhotra, Vishv Faculty of Information Technology Maranatha Christian University Indonesia UNSW Art Design University of New South Wales Sydney Australia Department of Computer Science and Engineering Indian Institute of Technology Guwahati India

ISBN: (纸本)9781538664278

The rapid development in face detection study has been greatly supported by the availability of large image datasets, which provide detailed annotations of faces on images. However, among a number of publicly accessible datasets, to our best knowledge, none of them are specifically created for academic applications. In this paper, we propose a systematic method in forming an image dataset tailored for classroom environment. We also made our dataset and its exploratory analyses publicly available. Studies in computer vision for academic application, such as an automated student attendance system, would benefit from our dataset. © 2018 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network 31

Eye in the Sky: Real-time Drone Surveillance System (DSS) fo...

引用

IEEE/CVF conference on computer vision and Pattern Recognition (CVPR)

作者： Singh, Amarjot Patil, Devendra Omkar, S. N. Univ Cambridge Dept Engn Cambridge England Natl Inst Technol Warangal Andhra Pradesh India Indian Inst Sci Bangalore Karnataka India

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Drone systems have been deployed by various law enforcement agencies to monitor hostiles, spy on foreign drug cartels, conduct border control operations, etc. This paper introduces a real-time drone surveillance system to identify violent individuals in public areas. The system first uses the Feature Pyramid Network to detect humans from aerial images. The image region with the human is used by the proposed ScatterNet Hybrid Deep Learning (SHDL) network for human pose estimation. The orientations between the limbs of the estimated pose are next used to identify the violent individuals. The proposed deep network can learn meaningful representations quickly using ScatterNet and structural priors with relatively fewer labeled examples. The system detects the violent individuals in real-time by processing the drone images in the cloud. This research also introduces the aerial violent individual dataset used for training the deep network which hopefully may encourage researchers interested in using deep learning for aerial surveillance. The pose estimation and violent individuals identification performance is compared with the state-of-the-art techniques.

关键词： Personal area networks Drones Feature extraction Surveillance Pose estimation Training

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：