检索结果-内蒙古大学图书馆

Detection of False Information in Digital Media Using Blockchain Technology

学校读者我要写书评

暂无评论

Detection of False Information in Digital Media Using Blockc...

Electrical Power Engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Aswini Kilaru L V Narasimha Prasad G S Pradeep Ghantasala U Ananthanagu Suresh Kallam Rajesh Sharma R Department of CSE Institute of Aeronautical Engineering Hyderabad Telangana Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Center of Excellence in Immersive Technologies Alliance University Bengaluru India School of Computer Science and Engineering Jain Deemed to be University Bengaluru India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

The spreading of false information over the internet, highly impacts society and causes social and economic loss to the nation. One of the most important factors for the increase in the number of misleading information is that all the users of any particular digital platform usually do not verify the authenticity of the information. The principal impartial of this proposed work is to afford a solution to society to reduce the social and economic losses caused by spreading false information circulated digitally. Blockchain is a disseminated, decentralized network that conducts peer-to-peer transactions, meaning that it does not have a central entity to operate. Here we present a literature survey on various approaches towards this problem statement and investigate a Blockchain-based solution that focuses on all types of digital content by providing the end user to validate the information along with the evidence for data that was collected at each step

关键词： Surveys Economics Power engineering Neural networks Machine learning Blockchains Peer-to-peer computing Security Reliability Fake news

Adaptive Memory Management for Video Object Segmentation

学校读者我要写书评

暂无评论

Adaptive Memory Management for Video Object Segmentation

Canadian Conference on computer and Robot Vision, CRV

作者： Ali Pourganjalikhan Charalambos Poullis Department of Computer Science and Software Engineering Immersive and Creative Technologies Lab Concordia University Montreal Canada

ISBN: (数字)9781665497749

ISBN: (纸本)9781665497756

Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides the network with richer cues for segmenting an object in the current frame. However, the size of the memory bank gradually increases with the length of the video, which slows down inference speed and makes it impractical to handle arbitrary length videos. This paper proposes an adaptive memory bank strategy for matching-based networks for semi-supervised video object segmentation (VOS) that can handle videos of arbitrary length by discarding obsolete features. Features are indexed based on their importance in the segmentation of the objects in previous frames. Based on the index, we discard unimportant features to accommodate new features. We present our experiments on DAVIS 2016, DAVIS 2017, and Youtube-VOS that demonstrate that our method outperforms state-of-the-art that employ first-and-latest strategy with fixed-sized memory banks and achieves comparable performance to the every-k strategy with increasing-sized memory banks. Furthermore, experiments show that our method increases inference speed by up to 80% over the every-k and 35% over first-and-latest strategies.

关键词： Adaptive systems Memory management Object segmentation Streaming media Indexes Task analysis Robots

Adaptive Memory Management for Video Object Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pourganjalikhan, Ali Poullis, Charalambos Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering Concordia University Montreal Canada

Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames’ predictions provides the network with richer cues for segmenting an object in the current frame. However, the size of the memory bank gradually increases with the length of the video, which slows down inference speed and makes it impractical to handle arbitrary length videos. This paper proposes an adaptive memory bank strategy for matching-based networks for semi-supervised video object segmentation (VOS) that can handle videos of arbitrary length by discarding obsolete features. Features are indexed based on their importance in the segmentation of the objects in previous frames. Based on the index, we discard unimportant features to accommodate new features. We present our experiments on DAVIS 2016, DAVIS 2017, and Youtube-VOS that demonstrate that our method outperforms state-of-the-art that employ first-and-latest strategy with fixed-sized memory banks and achieves comparable performance to the every-k strategy with increasing-sized memory banks. Furthermore, experiments show that our method increases inference speed by up to 80% over the every-k and 35% over first-and-latest strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Image segmentation

End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volumes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Qiao Poullis, Charalambos Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering Concordia University Quebec CA Montreal Canada

Image-based 3D reconstruction is one of the most important tasks in computer Vision with many solutions proposed over the last few decades. The objective is to extract metric information i.e. the geometry of scene objects directly from images. These can then be used in a wide range of applications such as film, games, virtual reality, etc. Recently, deep learning techniques have been proposed to tackle this problem. They rely on training on vast amounts of data to learn to associate features between images through deep convolutional neural networks and have been shown to outperform traditional procedural techniques. In this paper, we improve on the state-of-the-art two-view structure-from-motion(SfM) approach of [11] by incorporating 4D correlation volume for more accurate feature matching and reconstruction. Furthermore, we extend it to the general multi-view case and evaluate it on the complex benchmark dataset DTU [5]. Quantitative evaluations and comparisons with state-of-the-art multi-view 3D reconstruction methods demonstrate its superiority in terms of the accuracy of reconstructions. © 2022, CC BY-NC-SA.

关键词： Virtual reality

Predicting surface reflectance properties of outdoor scenes under unknown natural illumination

学校读者我要写书评

暂无评论

arXiv 2021年

作者： RahmanWasee, Farhan Joy, Alen Poullis, Charalambos Immersive and Creative Technologies Lab Department of Computer Science Concordia University

Estimating and modelling the appearance of an object under outdoor illumination conditions is a complex process. Although there have been several studies on illumination estimation and relighting, very few of them focus on estimating the reflectance properties of outdoor objects and scenes. This paper addresses this problem and proposes a complete framework to predict surface reflectance properties of outdoor scenes under unknown natural illumination. Uniquely, we recast the problem into its two constituent components involving the BRDF incoming light and outgoing view directions: (i) surface points' radiance captured in the images, and outgoing view directions are aggregated and encoded into reflectance maps, and (ii) a neural network trained on reflectance maps of renders of a unit sphere under arbitrary light directions infers a low-parameter reflection model representing the reflectance properties at each surface in the scene. Our model is based on a combination of phenomenological and physics-based scattering models and can relight the scenes from novel viewpoints. We present experiments that show that rendering with the predicted reflectance properties results in a visually similar appearance to using textures that cannot otherwise be disentangled from the reflectance properties. © 2021, CC BY-NC-SA.

关键词： Textures

Exploring Local Governance and Sustainability Challenges in Community Reserves: A Data science Perspective with Global Insights

学校读者我要写书评

暂无评论

Exploring Local Governance and Sustainability Challenges in ...

Electrical Power Engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Sachin Pavithran A P Anurima Banerjee G S Pradeep Ghantasala Rajesh Sharma R U Ananthanagu Suresh Kumar Natarajan Pellakuri Vidyullatha Department of Humanities and Social Sciences Jain (Deemed-to-beUniversity) Ramanagara India Department of Humanities and Social Sciences (HCIMT Kozhikode) Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Center of Excellence in Immersive Technologies Alliance University Bengaluru India School of Computer Science and Engineering Jain (Deemed-to-beUniversity) Ramanagara India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Andhra Pradesh India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

As one of the furthermost noticeable industries, tourism strives for to magnify the situation in numerous forms, effectually addressing the dissimilar matters and concerns into the world nowadays. Frequently, these issues disturb the ecologically momentous areas and the local communities on a higher note. It's the need of the hour to check the forecasts of sustainable and community-based coastal tourism, whichever targets to promote the area's tourism potential over vigorous involvement by the local community although preservative the aboriginal ecological balance. Kerala, a classic tourism destination in India, provides significant opportunities for livelihood options to the local community who depend on natural resources. The contemporaneous research paper was centered on a case study of Kadalundi- Vallikkunnu Community Reserve in Kerala, the local authority and several influences it could need onto the local community then the recommendations whichever could be measured to discourse a interrelated issues. A vast portion of the respondents, having tourism activities as their primary source of income, have identified the problem of environmental degradation as prevalent in the area. In contrast, the rest are unaware of the harmful effects happening to the natural ecosystem, primarily because of waste disposal and water pollution. The paper is an endeavor to shed graceful on the local governance system of community reserve and socio-economic aspects of the local communities on the development of tourism initiatives in Kerala.

关键词： Ecosystems Sea measurements Livelihood Environmental degradation Water conservation Water pollution Time measurement Pollution measurement Waste disposal Sustainable development

IEEE T-BIOM Editorial Board Changes

学校读者我要写书评

暂无评论

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

IEEE Transactions on Biometrics, Behavior, and Identity science 2024年第1期7卷 1-2页

作者： Naser Damer Weihong Deng Jianjiang Feng Vishal M. Patel Ajita Rattani Mark Nixon Smart Living & Biometric Technologies Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA Department of Computer Science and Engineering College of Engineering University of North Texas Denton TX USA

Face Morphing Attacks and Face Image Quality: The Effect of Morphing and the Unsupervised Attack Detection by Quality

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fu, Biying Damer, Naser The Department of Smart Living & Biometric Technologies Fraunhofer Institute for Computer Graphics Research Darmstadt64283 Germany The Department of Computer Science TU Darmstadt Darmstadt64283 Germany

Morphing attacks are a form of presentation attacks that gathered increasing attention in recent years. A morphed image can be successfully verified to multiple identities. This operation, therefore, poses serious security issues related to the ability of a travel or identity document to be verified to belong to multiple persons. Previous works touched on the issue of the quality of morphing attack images, however, with the main goal of quantitatively proofing the realistic appearance of the produced morphing attacks. We theorize that the morphing processes might have an effect on both, the perceptual image quality and the image utility in face recognition (FR) when compared to bona fide samples. Towards investigating this theory, this work provides an extensive analysis of the effect of morphing on face image quality, including both general image quality measures and face image utility measures. This analysis is not limited to a single morphing technique, but rather looks at six different morphing techniques and five different data sources using ten different quality measures. This analysis reveals consistent separability between the quality scores of morphing attack and bona fide samples measured by certain quality measures. Our study goes further to build on this effect and investigate the possibility of performing unsupervised morphing attack detection (MAD) based on quality scores. Our study looks intointra and inter-dataset detectability to evaluate the generalizability of such a detection concept on different morphing techniques and bona fide sources. Our final results point out that a set of quality measures, such as MagFace and CNNNIQA, can be used to perform unsupervised and generalized MAD with a correct classification accuracy of over 70%. © 2022, CC BY.

关键词： Image quality

Reversing BLE Remote Control Protocols of Dual Channel LED Lamps with CCT and Illumination Control

学校读者我要写书评

暂无评论

Reversing BLE Remote Control Protocols of Dual Channel LED L...

Automatics and Informatics (ICAI), International Conference

作者： Rostislav Kandilarov Yordan Yordanov Department of Machine Science Machine Elements Engineering Graphics and Physics Faculty of Transport University of Ruse “Angel Kanchev” Ruse Bulgaria Computer Systems and Technologies Faculty of Electrical Engeneering Electronics and Automation University of Ruse “Angel Kanchev” Ruse Bulgaria

In this paper various BLE protocols for communication between remote or Android applications and intelligent dual channel (cool and warm white) LED lamps were reverse engineered. Three protocols were fully decoded and several partially. Replay attack is tested and confirmed working. Demo C++ library was developed and a proof-of-concept firmware for esp32 based development board was used to verify the decoding and the attacks applicability.

关键词：