9 Hits in 9.7 sec

Visualizing High-Dimensional Data: Advances in the Past Decade

Shusen Liu, Dan Maljovec, Bei Wang, Peer-Timo Bremer, Valerio Pascucci
2017 IEEE Transactions on Visualization and Computer Graphics  
pipeline and identifying future opportunities for visualization research.  ...  Massive simulations and arrays of sensing devices, in combination with increasing computing resources, have generated large, complex, high-dimensional datasets used to study phenomena across numerous fields  ...  Take the distance function learning work [BLBC12] , for example. The initial embedding is created using a default distance measure.  ... 
doi:10.1109/tvcg.2016.2640960 pmid:28113321 fatcat:3xb2npz44fgxzpfueum5hhso5u

Deep Learning for 3D Point Clouds: A Survey [article]

Yulan Guo, Hanyun Wang, Qingyong Hu, Hao Liu, Li Liu, Mohammed Bennamoun
2020 arXiv   pre-print
To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.  ...  Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area.  ...  The initial segmentation result is refined by pooling the scores of neighboring points with learned attention weights.  ... 
arXiv:1912.12033v2 fatcat:qiiyvvuulfccxaiihf2mu23k34

Fusion of a Static and Dynamic Convolutional Neural Network for Multiview 3D Point Cloud Classification

Wenju Wang, Haoran Zhou, Gang Chen, Xiaolin Wang
2022 Remote Sensing  
Three-dimensional (3D) point cloud classification methods based on deep learning have good classification performance; however, they adapt poorly to diverse datasets and their classification accuracy must  ...  Therefore, FSDCNet, a neural network model based on the fusion of static and dynamic convolution, is proposed and applied for multiview 3D point cloud classification in this paper.  ...  Gumble subset sampling (GSS) was proposed for end-to-end learning and task-agnostic sampling.  ... 
doi:10.3390/rs14091996 fatcat:u6z55mruw5dxjgyej5uylkz36m

Spatial Clustering with SOM and GeoSOM: Case Study of Lisbon's Metropolitan Area

Roberto Henriques, Fernando Bacao, Victor Lobo
2010 2010 Second International Conference on Advanced Geographic Information Systems, Applications, and Services  
learning rate and initial neighbourhood radius.  ...  Learning rate and learning functions The learning rate assumes values in [0, 1], having an initial value given by the user.  ... 
doi:10.1109/geoprocessing.2010.30 fatcat:d6es6triyjgarp3smlmbibvsra

Conference Guide [Front matter]

2020 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)  
The proposed method is compared with SSD (Single Shot MultiBox Detector), YOLOv3 and YOLOv4 algorithms.  ...  In this study, we aim for automatic parameter optimization of feature matching-based object recognition algorithms.  ...  In this paper we investigate the resilient consensus problem for multi-agent systems under the specific attack scenarios where the attacker can eavesdrop on initial information of agents among the system  ... 
doi:10.1109/icarcv50220.2020.9305477 fatcat:4h7gpoj7ljgsrlkjoyw3qcfzxi

Learning probabilistic interaction models [article]

Advanced Video and Signal Based Surveillance (AVSS'17), Lecce, Italy (2017). -Hand pose recognition in First Person Vision through graph spec- tral analysis, M. Baydoun, A. Betancourt, P.  ...  With aforementioned abnormality thresholds, it is possible to find time shots in which peaks in db1 indicate the current experience is outside the learned model.  ...  As the ground truth of the simulated rules is available, the latter provides a visual comparison between theoretical velocity fields and C-DBN motion estimations for different attractor-follower configurations  ... 
doi:10.15167/baydoun-mohamad_phd2020-02-26 fatcat:dj2vtavwxvdbhojvoz3pqccloe

ADVCOMP 2010 Industry Liaison Chairs ADVCOMP 2010 Technical Program Committee

Wolfgang Gentzsch, Pascal Lorenz, Oana Dini, Flavio Oquendo, Jameleddine Hassine, Helmut Reiser, Supercomputing Centre, Lrz) -Garching, Germany Xu, Flavio Oquendo, Jameleddine Hassine, Helmut Reiser (+64 others)
Foreword The Fourth International Conference on Advanced Engineering Computing and Applications in Sciences (ADVCOMP 2010   unpublished
procedures, software and hardware solutions dealing with specific domains of science.  ...  With the current computing software, hardware and distributed platforms effective use of advanced computing techniques is more achievable.  ...  The authors wish to thank all their partners for providing the testcases and for many fruitful discussions (  ... 

iCORE Research Report: Volume 3 [article]

Caelli, Terry (Ed.), University Of Calgary, University Of Calgary
This report outlines activities and achievements of the iCORE research teams, which have been established in collaboration with Alberta universities and companies.  ...  ALBERTA INGENUITY CENTRE FOR MACHINE LEARNING (AICML) This research centre was formed two years ago, with Jonathan Schaeffer as one of the co-principal investigators.  ...  Centre) and multi-disciplinary initiative.  ... 
doi:10.11575/prism/10592 fatcat:byiphq4djfb3pomvcksjyfjb7q

Dynamic Social Networks in Agent-based Modelling Dynamic Social Networks in Agent-based Modelling Increasingly Detailed Approaches of Network Initialisation and Network Dynamics

Sascha Holzhauer, Sascha Holzhauer
This dissertation initially identifies important properties of social networks and their dynamics and reviews their representation in agent-based models of relevant domains.  ...  Agent-based modelling enables the explicit representation of entities and their interaction with each other and the environment, and so it became an important method to study complex systems.  ...  Initially, the motivation for the survey as means to inform agent-based models is addressed.  ...