scholarly journals Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

2019 ◽  
Author(s):  
Mans Larsson ◽  
Erik Stenborg ◽  
Carl Toft ◽  
Lars Hammarstrand ◽  
Torsten Sattler ◽  
...  
Keyword(s):  
Visual Localization ◽  
Fine Grained ◽  
Supervised Segmentation

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

scholarly journals Non-Local and Multi-Scale Mechanisms for Image Inpainting

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3281
Author(s):  
Xu He ◽  
Yong Yin
Keyword(s):  
Markov Random Fields ◽  
Receptive Fields ◽  
Image Inpainting ◽  
Long Distance ◽  
Visual Appearance ◽  
Fine Grained ◽  
Multi Scale ◽  
Non Local ◽  
Relationship Of

Recently, deep learning-based techniques have shown great power in image inpainting especially dealing with squared holes. However, they fail to generate plausible results inside the missing regions for irregular and large holes as there is a lack of understanding between missing regions and existing counterparts. To overcome this limitation, we combine two non-local mechanisms including a contextual attention module (CAM) and an implicit diversified Markov random fields (ID-MRF) loss with a multi-scale architecture which uses several dense fusion blocks (DFB) based on the dense combination of dilated convolution to guide the generative network to restore discontinuous and continuous large masked areas. To prevent color discrepancies and grid-like artifacts, we apply the ID-MRF loss to improve the visual appearance by comparing similarities of long-distance feature patches. To further capture the long-term relationship of different regions in large missing regions, we introduce the CAM. Although CAM has the ability to create plausible results via reconstructing refined features, it depends on initial predicted results. Hence, we employ the DFB to obtain larger and more effective receptive fields, which benefits to predict more precise and fine-grained information for CAM. Extensive experiments on two widely-used datasets demonstrate that our proposed framework significantly outperforms the state-of-the-art approaches both in quantity and quality.

scholarly journals Map Management for Efficient Long-Term Visual Localization in Outdoor Environments

2018 ◽  
Author(s):  
Mathias Burki ◽  
Marcin Dymczyk ◽  
Igor Gilitschenski ◽  
Cesar Cadena ◽  
Roland Siegwart ◽  
...  
Keyword(s):  
Visual Localization ◽  
Outdoor Environments ◽  
Map Management

scholarly journals Innovation Motives in Family Firms: A Transgenerational View

2018 ◽  
Vol 44 (2) ◽  
pp. 256-287 ◽  
Author(s):  
Vanessa Diaz-Moriana ◽  
Eric Clinton ◽  
Nadine Kammerlander ◽  
G. T. Lumpkin ◽  
Justin B. Craig
Keyword(s):  
Family Firms ◽  
Fine Grained ◽  
Study Approach ◽  
Data Collection Process ◽  
Semistructured Interviews ◽  
Multigenerational Family ◽  
Multiple Case ◽  
Innovation Patterns

Drawing on the transgenerational entrepreneurship perspective, we employ a multiple case study approach to investigate why multigenerational family firms innovate. The data collection process drew upon five in-depth cases comprising 42 semistructured interviews, 25 participant observations, and several thousand pages of historical data dating from 1916 to 2017. We find patterns on how the firms’ long-term view—embracing both the past and the future—influences the innovation motives of these firms. Specifically, we identify three innovation patterns: conserving, persisting and legacy-building. We introduce a set of propositions and a framework linking long-term orientation dimensions to innovation motives and innovation outcomes. Our research thus contributes to a more fine-grained understanding of innovation behavior in family firms.

Introduction

2020 ◽  
pp. 1-16
Author(s):  
T. K. Wilson
Keyword(s):  
Political Violence ◽  
Coercive Power ◽  
Social Changes ◽  
Pull Factors ◽  
Push Factors ◽  
Western State ◽  
Fine Grained ◽  
Violent Action ◽  
Push And Pull

How has political violence changed over the long term? This introduction makes the case for looking closely at specific acts—or ‘repertoires’—of violent action. Only through such a fine-grained approach can the distinctively modern quality to contemporary violence be isolated analytically: including its frequently impersonal nature—the killing of strangers referenced in the book’s title. The definitional and geographical parameters of the study are briskly sketched: and the overall structure delineated. An early emphasis is placed here on both ‘push’ and ‘pull’ factors in shaping modern political violence. Push factors concern chiefly the rise of the modern western state undergirded by bureaucracies of extraordinary coercive power and reach. ‘Pull’ factors refer to the technological and social changes that open up radically new opportunities and possibilities for violence.

scholarly journals Grey theory–based BP-NN co-training for dense sequence long-term tendency prediction

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yuling Hong ◽  
Yingjie Yang ◽  
Qishan Zhang
Keyword(s):  
State Transition ◽  
Transition Probability ◽  
Training Model ◽  
Transition Probability Matrix ◽  
Content Type ◽  
Fine Grained ◽  
State Transition Probability ◽  
Dense Sequence ◽  
Popularity Prediction

PurposeThe purpose of this paper is to solve the problems existing in topic popularity prediction in online social networks and advance a fine-grained and long-term prediction model for lack of sufficient data.Design/methodology/approachBased on GM(1,1) and neural networks, a co-training model for topic tendency prediction is proposed in this paper. The interpolation based on GM(1,1) is employed to generate fine-grained prediction values of topic popularity time series and two neural network models are considered to achieve convergence by transmitting training parameters via their loss functions.FindingsThe experiment results indicate that the integrated model can effectively predict dense sequence with higher performance than other algorithms, such as NN and RBF_LSSVM. Furthermore, the Markov chain state transition probability matrix model is used to improve the prediction results.Practical implicationsFine-grained and long-term topic popularity prediction, further improvement could be made by predicting any interpolation in the time interval of popularity data points.Originality/valueThe paper succeeds in constructing a co-training model with GM(1,1) and neural networks. Markov chain state transition probability matrix is deployed for further improvement of popularity tendency prediction.

Music and cremation rituals in The Netherlands: A fine-grained analysis of a crematorium’s playlist

2018 ◽  
Vol 34 (4) ◽  
pp. 806-817
Author(s):  
Doris van der Smissen ◽  
Margaret A Steenbakker ◽  
Martin J M Hoondert ◽  
Menno M van Zaanen
Keyword(s):  
The Netherlands ◽  
Computational Analysis ◽  
Qualitative Approach ◽  
Close Reading ◽  
Musical Analysis ◽  
Fine Grained ◽  
History Of ◽  
Multi Method Approach ◽  
Method Approach

Abstract Although music is an important part of cremation rituals, there is hardly any research regarding music and cremations. This lack of research has inspired the authors to conduct a long-term research project, focusing on musical and linguistic aspects of music played during cremations. This article presents the analysis of a playlist consisting of twenty-five sets of music, each consisting of three tracks, used in a crematorium in the south of The Netherlands from 1986 onward. The main objective is to identify the differences and similarities of the twenty-five sets of musical tracks regarding content and musical properties. Consequently, we aim to provide insight in the history of (music played during) cremation rituals in The Netherlands. To analyze the musical properties of the sets, the authors use both a qualitative approach (close reading and musical analysis) and a computational analysis approach. The article demonstrates that a combination of a close reading and musical analysis and a computational analysis is necessary to explain the differences in properties of the sets. The presented multi-method approach may allow for comparisons against musical preferences in the context of current cremations, which makes it possible to trace the development of music and cremation rituals.

scholarly journals Scaling property of ideal granitic sequences

2007 ◽  
Vol 14 (3) ◽  
pp. 237-246 ◽  
Author(s):  
D. Xu ◽  
Q. Cheng ◽  
F. Agterberg
Keyword(s):  
Lake Area ◽  
Fine Grained ◽  
Multi Scale ◽  
Invariance Properties ◽  
The Past ◽  
Ideal Granite ◽  
Markov Properties ◽  
The Ideal

Abstract. Quantification of granite textures and structures using a mathematical model for characterization of granites has been a long-term attempt of mathematical geologists over the past four decades. It is usually difficult to determine the influence of magma properties on mineral crystallization forming fined-grained granites due to its irregular and fine-grained textures. The ideal granite model was originally developed for modeling mineral sequences from first and second-order Markov properties. This paper proposes a new model for quantifying scale invariance properties of mineral clusters and voids observed within mineral sequences. Sequences of the minerals plagioclase, quartz and orthoclase observed under the microscope for 104 aplite samples collected from the Meech Lake area, Gatineau Park, Québec were used for validation of the model. The results show that the multi-scale approaches proposed in this paper may enable quantification of the nature of the randomness of mineral grain distributions. This, in turn, may be related to original properties of the magma.

Sign in / Sign up

Export Citation Format

Share Document