检索结果-内蒙古大学图书馆

12th International conference on Interfaces and Human computer Interaction 2018, 11th International conference on Game and Entertainment Technologies 2018 and 12th International conference on computer graphics, Visualization, computer vision and image processing 2018, part of the Multi conference on computer Science and Information Systems 2018, MCCSIS 2018

作者： Kordyaka, Bastian Jahn, Katharina Niehaves, Bjoern University of Siegen Kohlbettstraße 15 Siegen57072 Germany

ISBN: (纸本)9789898533791

Multiplayer Online Battle Arena (MOBA) is a computer game genre with increasing popularity and leaping revenues. the MOBA phenomenon is particularly interesting from an economic perspective since the majority of purchases consists of virtual items with hedonic value. Although research has already identified meaningful explanations, an answer to the question what motivates players to purchase virtual items in the specific context of the most successful MOBA game League of Legends (LoL) is still scarce. We build upon the assumptions of the social identity approach to explain purchases of virtual items. Additionally, we investigate individual and cultural antecedents of social identification. Results of our survey (n=181) indicate that social identification holds the potential to explain the intention to purchase virtual items and that cultural (patriotism) as well as individual (psychosocial development) factors predict social identification. © 2018.

关键词： computer games

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Detection of Surface Mine Sites using Sentinel Multi-spectral imagery and Dual-polarimetric SAR Data 11

Unsupervised Detection of Surface Mine Sites using Sentinel ...

引用

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

作者： Aswatha, Shashaank M. Saini, Vishnu Mukherjee, Jayanta Biswas, Prabir K. Aikat, Subhas Misra, Arundhati Indian Inst Technol Kharagpur Kharagpur W Bengal India Indian Space Res Org Space Applicat Ctr Ahmadabad Gujarat India

ISBN: (纸本)9781450366151

Detecting surface mine activities has been one of the major challenges of remote sensing community to monitor ecological balance in the vicinity of mine area. Towards addressing this issue, we propose an unsupervised mine-site detection technique using multi-modal remotely sensed data from Sentinel missions. We use Sentinel-1's dual polarized SAR data, and Sentinel-2's multi-spectral data for this purpose. An initial set of seed pixels is sampled using spectral slopes based rules on multi-spectral images, which are tailored to capture mining area pixels that exhibit common characteristics. then, we generate features using multi-spectral image indices and dual polarized SAR data Stokes' parameters. these features over locations sampled by slope based rules are used to train a one-class support vector machine to detect the land anomalies (mine activities). As observed from the experiments, multi-spectral features are efficient in separating mine region and built-up region from the rest of the land surface, and SAR image features discriminate built-up region from the rest of the image. We fuse both of these imagery features to encash their advantage in segregating mine sites in the considered study area. We demonstrate the efficiency of the proposed technique in detecting active coal mines over two study sites, Asansol region (in West bengal, India) and Jharia region (in Jharkhand, India), both of which exhibit common geographical characteristics. the average detection accuracy in our results is found to be around 94.8%.

关键词： Multi-spectral imagery synthetic aperture radar surface mining area detection multi-modal analysis spectral slopes

来源：评论

学校读者我要写书评

暂无评论

FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans 1

引用

15th European conference on computer vision (ECCV)

作者： Liu, Chen Wu, Jiaye Furukawa, Yasutaka Washington Univ St Louis MO 63130 USA Simon Fraser Univ Burnaby BC Canada

ISBN: (数字)9783030012311

ISBN: (纸本)9783030012311;9783030012304

this paper proposes a novel deep neural architecture that automatically reconstructs a floorplan by walking through a house with a smartphone, an ultimate goal of indoor mapping research. the challenge lies in the processing of RGBD streams spanning a large 3D space. the proposed neural architecture, dubbed FloorNet, effectively processes the data through three neural network branches: (1) PointNet with 3D points, exploiting 3D information;(2) CNN with a 2D point density image in a top-down view, enhancing local spatial reasoning;and (3) CNN with RGB images, utilizing full image information. FloorNet exchanges intermediate features across the branches to exploit all the architectures. We have created a benchmark for floorplan reconstruction by acquiring RGBD video streams for 155 residential houses or apartments with Google Tango phones and annotating complete floorplan information. Our qualitative and quantitative evaluations demonstrate that the fusion of three branches effectively improves the reconstruction quality. We hope that the paper together with the benchmark will be an important step towards solving a challenging vector-graphics floorplan reconstruction problem.

关键词： Floorplan reconstruction 3D computer vision 3D CNN

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

Fast and Generalisable License Plate Re-identification using Neural Embedding of Fisher Vectors 11

Fast and Generalisable License Plate Re-identification using...

引用

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

image-based algorithm for the catheter recognition based on GLCM 28

Image-based algorithm for the catheter recognition based on ...

引用

28th International conference on computer graphics and vision, GraphiCon 2018

作者： Danilov, V.V. Skirnevskiy, I.P. Manakov, R.A. Gerget, O.M. Melgani, F. Medical Devices Design Laboratory Tomsk Polytechnic University Tomsk Russia Signal Processing and Recognition Laboratory University of Trento Trento Italy

the focus of this study was to develop an image-based algorithm for the catheter detection. Epicardial full-volume 3D echocardiography datasets were used as an input data of the algorithm. In total, 9 datasets consisted of 15 three-dimensional timeframes were processed. To correctly detect the catheter, the feature-based approach was applied to recognition the catheter within the 3D echocardiography datasets. the algorithm based on gray-level co-occurrence matrix (GLCM) was applied as a feature extraction technique. Once the GLCM was computed, we obtained correlation, contrast, homogeneity and energy features. then we applied feature thresholds to the catheter detection. these thresholds were obtained using Support Vector Machine (SVM) with the linear kernel function and standardization the predictor data. the average segmentation and recognition accuracies of the algorithm equal 94.16% and 87.2% respectively. the processing time for one 2D slice and one 3D dataset are equal to 9±0.2 milliseconds and 1.96±0.045 seconds, respectively. though the algorithm is not time-consuming for 2D mode, it is still complicated to apply it for real-time surgery in 3D mode. © GraphiCon 2018 - 28th International conference on computer graphics and vision. All rights reserved.

关键词： Catheters

来源：评论

学校读者我要写书评

暂无评论

Single noisy image super resolution by minimizing nuclear norm in virtual sparse domain 6th

Single noisy image super resolution by minimizing nuclear no...

引用

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

作者： Mandal, Srimanta Rajagopalan, A.N. Image Processing and Computer Vision Lab Department of Electrical Engineering IIT Madras Chennai600036 India

ISBN: (纸本)9789811300196

Super-resolving a noisy image is a challenging problem, and needs special care as compared to the conventional super resolution approaches, when the power of noise is unknown. In this scenario, we propose an approach to super-resolve single noisy image by minimizing nuclear norm in a virtual sparse domain that tunes with the power of noise via parameter learning. the approach minimizes nuclear norm to explore the inherent low-rank structure of visual data, and is further augmented with coarse-to-fine information by adaptively re-aligning the data along the principal components of a dictionary in virtual sparse domain. the experimental results demonstrate the robustness of our approach across different powers of noise. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Optical resolving power

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

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：