检索结果-内蒙古大学图书馆

Hierarchical attention fusion for geo-localization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yan, Liqi Cui, Yiming Chen, Yingjie Liu, Dongfang Department of Computer Science and Technology Fudan University China Department of Electrical and Computer Engineering University of Florida United States Department of Computer Graphics Technology Purdue University United States

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. © 2021, CC BY.

关键词： Semantics

An IoT Course Program to Foster the Adoption of IoT Driven Food and Agriculture in Sub-Saharan Africa (SSA)

学校读者我要写书评

暂无评论

An IoT Course Program to Foster the Adoption of IoT Driven F...

2022 IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2022

作者： Kuaban, Godlove Suila Nowak, Mateusz Czekalski, Piotr Tokarz, Krzysztof Tangka, Julius Kewir Siggursson, Kjartan Nikitenko, Agris Berkolds, Karlis Sell, Raivo Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice 44-100 Poland Department of Computer Graphics Vision and Digital Systems Silesian University of Technology Akademicka 16 Gliwice44-100 Poland Renewable Energy Laboratory University of Dschang Dschang Cameroon University of Twente Netherlands Riga Technical University Latvia TalTech Estonia

ISBN: (数字)9781665470872

ISBN: (纸本)9781665470872

The Internet of Things (IoT) technologies, together with other technological advances such as big data analytics, Artificial Intelligence (AI), automation, and unmanned electrical vehicles (e.g., self-driving vehicles and drones), are currently being used to transform the food and agriculture industry to increase yields significantly with minimal damage to the environment. These recent advances in Information and Communication Technologies and advances in biotechnology are driving the transition into the fourth agricultural revolution or agriculture 4.0. Some research studies on the adoption of IoT in the agriculture sector in Sub-Saharan Africa concluded that some of the reasons the rate of adoption of IoT in Africa is still very low are gaps in knowledge, skills, finance, and infrastructure. The knowledge and skills gaps are partly a result of an educational curriculum that is not up to date with current advances in the food and agricultural industry. To foster IoT adoption in the food and agriculture sectors and other sectors or industries in Sub-saharan Africa, we propose an IoT course program consisting of lectures and laboratory modules. The course is accompanied by textbooks, video lectures that are freely available on Edx, and remote online laboratories with the hardware resources hosted in some European countries but accessible through the Internet. These courses can also be adapted by vocational training schools, Higher Institutes, and universities in Sub-Saharan Africa or could be used by professionals and enthusiasts to improve their skills. © 2022 IEEE.

关键词： Agriculture

Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze

学校读者我要写书评

暂无评论

Visual Localization for Autonomous Driving: Mapping the Accu...

International Conference on Pattern Recognition

作者： Dongfang Liu Yiming Cui Xiaolei Guo Wei Ding Baijian Yang Yingjie Chen Computer Graphics Technology Purdue University Electrical & Computer Engineering University of Florida Computer Information Technology Purdue University Ray W. Herrick Laboratories Mechanical Engineering Purdue University

Accurate localization is a foundational capacity, required for autonomous vehicles to accomplish other tasks such as navigation or path planning. It is a common practice for vehicles to use GPS to acquire location information. However, the application of GPS can result in severe challenges when vehicles run within the inner city where different kinds of structures may shadow the GPS signal and lead to inaccurate location results. To address the localization challenges of urban settings, we propose a novel feature voting technique for visual localization. Different from the conventional front-view-based method, our approach employs views from three directions (front, left, and right) and thus significantly improves the robustness of location prediction. In our work, we craft the proposed feature voting method into three state-of-the-art visual localization networks and modify their architectures properly so that they can be applied for vehicular operation. Extensive field test results indicate that our approach can predict location robustly even in challenging inner-city settings. Our research sheds light on using the visual localization approach to help autonomous vehicles to find accurate location information in a city maze, within a desirable time constraint. The source code is available at ***/HappyDonkey13/Visual- Localization-for- Autonomous-Driving.

关键词： Location awareness Visualization Urban areas Pipelines Robustness Pattern recognition Time factors

CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lin, Wei Kukleva, Anna Sun, Kunyang Possegger, Horst Kuehne, Hilde Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Max-Planck-Institute for Informatics Germany Southeast University China Goethe University Frankfurt Germany Christian Doppler Laboratory for Semantic 3D Computer Vision

Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Therefore, image-to-video adaptation has been proposed to exploit labeling-free web image source for adapting on unlabeled target videos. This poses two major challenges: (1) spatial domain shift between web images and video frames;(2) modality gap between image and video data. To address these challenges, we propose Cycle Domain Adaptation (CycDA), a cycle-based approach for unsupervised image-to-video domain adaptation. We leverage the joint spatial information in images and videos on the one hand and, on the other hand, train an independent spatio-temporal model to bridge the modality gap. We alternate between the spatial and spatio-temporal learning with knowledge transfer between the two in each cycle. We evaluate our approach on benchmark datasets for image-to-video as well as for mixed-source domain adaptation achieving state-of-the-art results and demonstrating the benefits of our cyclic adaptation. Code is available at https://***/wlin-at/CycDA. Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge management

Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lau, Tim Tsz-Kit Liu, Han Pock, Thomas Department of Statistics and Data Science Northwestern University EvanstonIL60208 United States The University of Chicago Booth School of Business ChicagoIL60637 United States Department of Computer Science Northwestern University EvanstonIL60208 United States Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria

We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality. We focus on performing this task via Markov chain Monte Carlo (MCMC) methods derived from discretizations of the overdamped Langevin diffusions, which are commonly known as Langevin Monte Carlo algorithms. Furthermore, we are also interested in two nonsmooth cases for which a large class of proximal MCMC methods have been developed: (i) a nonsmooth prior is considered with a Gaussian mixture likelihood;(ii) a Laplacian mixture distribution. Such nonsmooth and non-log-concave sampling tasks arise from a wide range of applications to Bayesian inference and imaging inverse problems such as image deconvolution. We perform numerical simulations to compare the performance of most commonly used Langevin Monte Carlo algorithms. © 2023, CC BY.

关键词： Inverse problems

Decoupling Contact for Fine-Grained Motion Style Transfer

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Xiangjun Wu, Linjun Wang, He Wu, Yiqian Hu, Bo Li, Songnan Gong, Xu Liao, Yuchen Kou, Qilong Jin, Xiaogang State Key Lab of CAD&CG Zhejiang University China Department of Computer Science UCL Centre for Artificial Intelligence University College London United Kingdom Tencent Technology Co. Ltd. China State Key Lab of CAD&CG Zhejiang University ZJU-Tencent Game and Intelligent Graphics Innovation Technology Joint Lab China

Motion style transfer changes the style of a motion while retaining its content and is useful in computer animations and games. Contact is an essential component of motion style transfer that should be controlled explicitly in order to express the style vividly while enhancing motion naturalness and quality. However, it is unknown how to decouple and control contact to achieve fine-grained control in motion style transfer. In this paper, we present a novel style transfer method for fine-grained control over contacts while achieving both motion naturalness and spatial-temporal variations of style. Based on our empirical evidence, we propose controlling contact indirectly through the hip velocity, which can be further decomposed into the trajectory and contact timing, respectively. To this end, we propose a new model that explicitly models the correlations between motions and trajectory/contact timing/style, allowing us to decouple and control each separately. Our approach is built around a motion manifold, where hip controls can be easily integrated into a Transformer-based decoder. It is versatile in that it can generate motions directly as well as be used as post-processing for existing methods to improve quality and contact controllability. In addition, we propose a new metric that measures a correlation pattern of motions based on our empirical evidence, aligning well with human perception in terms of motion naturalness. Based on extensive evaluation, our method outperforms existing methods in terms of style expressivity and motion quality. Copyright © 2024, The Authors. All rights reserved.

关键词： computer games

Stating Comparison Score Uncertainty and Verification Decision Confidence Towards Transparent Face Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huber, Marco Terhörst, Philipp Kirchbuchner, Florian Damer, Naser Kuijper, Arjan Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Technical University of Darmstadt Darmstadt Germany Norwegian University of Science and Technology Gjøvik Norway Paderborn University Paderborn Germany

Face Recognition (FR) is increasingly used in critical verification decisions and thus, there is a need for assessing the trustworthiness of such decisions. The confidence of a decision is often based on the overall performance of the model or on the image quality. We propose to propagate model uncertainties to scores and decisions in an effort to increase the transparency of verification decisions. This work presents two contributions. First, we propose an approach to estimate the uncertainty of face comparison scores. Second, we introduce a confidence measure of the system's decision to provide insights into the verification decision. The suitability of the comparison scores uncertainties and the verification decision confidences have been experimentally proven on three face recognition models on two datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Face recognition

ReGenMorph: Visibly realistic GAN generated face morphing attacks by attack re-generation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Damer, Naser Raja, Kiran Süßmilch, Marius Venkatesh, Sushma Boutros, Fadi Fang, Meiling Kirchbuchner, Florian Ramachandra, Raghavendra Kuijper, Arjan Fraunhofer Institute for Computer Graphics Research IGD Germany Department of Computer Science TU Darmstadt Germany Norwegian University of Science and Technology Norway

Face morphing attacks aim at creating face images that are verifiable to be the face of multiple identities, which can lead to building faulty identity links in operations like border checks. While creating a morphed face detector (MFD), training on all possible attack types is essential to achieve good detection performance. Therefore, investigating new methods of creating morphing attacks drives the generalizability of MADs. Creating morphing attacks was performed on the image level, by landmark interpolation, or on the latent-space level, by manipulating latent vectors in a generative adversarial network. The earlier results in varying blending artifacts and the latter results in synthetic-like striping artifacts. This work presents the novel morphing pipeline, ReGenMorph, to eliminate the LMA blending artifacts by using a GAN-based generation, as well as, eliminate the manipulation in the latent space, resulting in visibly realistic morphed images compared to previous works. The generated ReGenMorph appearance is compared to recent morphing approaches and evaluated for face recognition vulnerability and attack detectability, whether as known or unknown attacks. Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

Significance of Single Interval Discrete Attributes: Case Study on 2-Level Discretisation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Stańczyk, Urszula Zielosko, Beata Baron, Grzegorz Department of Computer Graphics Vision and Digital Systems Silesian University of Technology Akademicka 2A Gliwice44-100 Poland Institute of Computer Science University of Silesia in Katowice Bȩdzińska 39 Sosnowiec41-200 Poland

Supervised discretisation is widely considered as far more advantageous form of transformation than unsupervised processing of attributes. When evaluating candidate cut-points for splitting the ranges of values of discretised features, the supervised methods help to preserve informative content of a variable, which is useful for classification. After a discretisation process, based on employed criteria, some attributes can be found as irrelevant, with all their values represented in discrete domain by a single interval. In consequence, such variables are removed from considerations, and no knowledge is mined from them. The paper presents research works focused on extended 2-level transformations of attributes values, with combining supervised with unsupervised discretisation strategies. For all variables with single intervals returned from supervised algorithms, the ranges of values were divided by unsupervised methods with varying numbers of bins. Resulting variants of data were subjected to selected data mining techniques and performance of chosen classifiers evaluated and compared. The experiments were performed on stylometric task of authorship attribution. © 2022, The Authors. All rights reserved.

关键词： Pattern recognition