Filters








2,747 Hits in 10.9 sec

A Graph Layout Framework Combining t-distributed Neighbor Retrieval Visualizer and Energy Models

Guangluan Xu, Zhenzhou Song, Yang Wang, Daoyu Lin, Jing Chen, Tingyun Mao, Wenjia Xu
2019 IEEE Access  
framework called "tNEM" that layouts graphs by combining t-distributed neighbor retrieval visualizer (t-NeRV) and energy models.  ...  INDEX TERMS Graph layout, dimension reduction, energy model, t-NeRV.  ...  III. tNEM:t-DISTRIBUTED NEIGHBOR RETRIEVAL VISUALIZER AND ENERGY MODEL GRAPH LAYOUT ALGORITHM In this paper, we propose a graph layout algorithm called ''tNEM'' which based on t-NeRV and energy models.  ... 
doi:10.1109/access.2019.2900358 fatcat:acnwj5jsmngyng2welaph4mqii

Coherent Time-Varying Graph Drawing with Multifocus+Context Interaction

Kun-Chuan Feng, Chaoli Wang, Han-Wei Shen, Tong-Yee Lee
2012 IEEE Transactions on Visualization and Computer Graphics  
We present a new approach for time-varying graph drawing that achieves both spatiotemporal coherence and multi-focus+context visualization in a single framework.  ...  Our approach utilizes existing graph layout algorithms to produce the initial graph layout, and formulates the problem of generating coherent time-varying graph visualization with the focus+context capability  ...  Technological University startup fund and the U.S.  ... 
doi:10.1109/tvcg.2011.128 pmid:21788669 fatcat:cgyhrcq55refrb3jy2p7dpytni

Extracting foreground masks towards object recognition

Amir Rosenfeld, Daphna Weinshall
2011 2011 International Conference on Computer Vision  
The model includes a geometric prior and an appearance prior, whose parameters are learnt on the fly from images that are similar to the query image.  ...  The method is tested on the challenging VOC09 and VOC10 segmentation datasets, achieving excellent results in providing a foreground mask.  ...  Figure 3 . 3 It = (V It , E It ) ← the graph induced on I t using coarse superpixels from ([1])2. nei A (I t ) ← {I N 1 , . . . , I N K A }, the K A nearest BOW neighbors of A(I t ) in I train 3.  ... 
doi:10.1109/iccv.2011.6126391 dblp:conf/iccv/RosenfeldW11 fatcat:rvzpjh3chjasrlmnbwb42mc5z4

A General Framework for Visualization of Sound Collections in Musical Interfaces

Gerard Roma, Anna Xambó, Owen Green, Pierre Alexandre Tremblay
2021 Applied Sciences  
The proposed framework allows for a modular combination of different techniques for sound segmentation, analysis, and dimensionality reduction, using the reduced feature space for interactive applications  ...  This paper describes a general framework for devising interactive applications based on the content-based visualization of sound collections.  ...  Acknowledgments: We would like to thank the reviewers for their time and thoughtful comments. Also, thanks to Claudine Levasseur for proofreading.  ... 
doi:10.3390/app112411926 fatcat:rxeyqnk7ujg75nphsz62wvnobq

READ: Recursive Autoencoders for Document Layout Generation [article]

Akshay Gadi Patil, Omri Ben-Eliezer, Or Perel, Hadar Averbuch-Elor
2020 arXiv   pre-print
In this paper, we present a novel framework, coined READ, for REcursive Autoencoders for Document layout generation, to generate plausible 2D layouts of documents in large quantities and varieties.  ...  code, the space of which is approximated by a Gaussian distribution.  ...  [16] present an interactive energy-based model that allows novice designers to improve their page layout design. Swearngin et al.  ... 
arXiv:1909.00302v4 fatcat:4uzjy5ruhnfchpnilg7ibj2q3i

Deep Image Synthesis from Intuitive User Input: A Review and Perspectives [article]

Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang
2021 arXiv   pre-print
While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial  ...  In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically  ...  , visual attributes, graphs and layouts.  ... 
arXiv:2107.04240v2 fatcat:ticrsi27nzhozmw7dp7wwja2ni

Deep image synthesis from intuitive user input: A review and perspectives

Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang
2021 Computational Visual Media  
While classically, works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial  ...  AbstractIn many applications of computer graphics, art, and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph, or layout, and have a computer  ...  Zhang were supported by the National Natural Science Foundation of China (Project Nos. 61521002 and 61772298), a Research Grant of Beijing Higher Institution Engineering Research Center, and the Tsinghua-Tencent  ... 
doi:10.1007/s41095-021-0234-8 fatcat:ot6dyrrrsnakxob4jzw4zld7zu

DClusterE

Yi Zhang, Tao Li
2012 ACM Transactions on Intelligent Systems and Technology  
In this article, we present DClusterE, a comprehensive and effective framework for document clustering evaluation and understanding using information visualization.  ...  Combined with coarse seriation, MUA is able to provide better visualization of the cluster structures. (2) A Mallows-distance-based algorithm for establishing the relationship between the clustering results  ...  As for visualization techniques, WEKA uses stacked bars for presenting true label distributions and utilizes trees or net graphs for describing the model structures. (2) CLUSION.  ... 
doi:10.1145/2089094.2089100 fatcat:w2xnu56nszf3bkzaqpvepduqjq

READ: Recursive Autoencoders for Document Layout Generation

Akshay Gadi Patil, Omri Ben-Eliezer, Or Perel, Hadar Averbuch-Elor
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we present a novel framework, coined READ, for REcursive Autoencoders for Document layout generation, to generate plausible 2D layouts of documents in large quantities and varieties.  ...  code, the space of which is approximated by a Gaussian distribution.  ...  [17] present an interactive energy-based model that allows novice designers to improve their page layout design. Swearngin et al.  ... 
doi:10.1109/cvprw50498.2020.00280 dblp:conf/cvpr/PatilBPA20 fatcat:i4l7v2gabvdejbfgh4fwu3kksq

Scene Parsing With Integration of Parametric and Non-Parametric Models

Bing Shuai, Zhen Zuo, Gang Wang, Bing Wang
2016 IEEE Transactions on Image Processing  
The global scene constraint is mathematically achieved by adding a global energy term to the labeling energy function, and it is practically estimated in a non-parametric framework.  ...  Based on the occurrence frequency distribution of classes, an ensemble of CNNs (CNN-Ensemble) are learned, in which each CNN component focuses on learning different and complementary visual patterns.  ...  The research is also supported by Singapore Ministry of Education (MOE) Tier 2 ARC28/14, and Singapore A*STAR Science and Engineering Research Council PSF1321202099.  ... 
doi:10.1109/tip.2016.2533862 pmid:26929044 fatcat:po2g567m2jhspeyyzpz2kbbsmu

Learning a perceptual manifold with deep features for animation video resequencing [article]

Charles C.Morace, Thi-Ngoc-Hanh Le, Sheng-Yi Yao, Shang-Wei Zhang, Tong-Yee Lee
2021 arXiv   pre-print
We show that with this perceptual metric and graph-based manifold learning techniques, our framework can produce new smooth and visually appealing animation video results for a variety of animation video  ...  We propose a novel deep learning framework for animation video resequencing.  ...  [21] proposed a view-independent Energy-Based Model that simultaneously detects faces and estimates head pose.  ... 
arXiv:2111.01455v1 fatcat:bdnzaapkeff3rahm2dpspbhd64

Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection [article]

Lina Wei, Fangfang Wang, Xi Li, Fei Wu, Jun Xiao
2017 arXiv   pre-print
As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames.  ...  Motivated by this observation, we propose a graph-theoretic video saliency detection approach based on adaptive video structure discovery, which is carried out within a spatiotemporal atomic graph.  ...  of the graph model which defines the saliency distribution of the video by graph-based propagation.  ... 
arXiv:1707.07815v1 fatcat:yyqicwunufhkbmdfuhd547dzae

VizTract: Visualization of Complex Social Networks for Easy User Perception

Ramya Akula, Ivan Garibay
2019 Big Data and Cognitive Computing  
VizTract is a two-level graph abstraction visualization tool that is designed to visualize both hierarchical and adjacency information in a tree structure.  ...  The visualization techniques used in VizTract are the force-directed layout, circle packing, cluster dendrogram, and hierarchical edge bundling.  ...  Using two graph visualizations with four different layout combinations, VizTract tool is also user-friendly.  ... 
doi:10.3390/bdcc3010017 fatcat:rycy4o2psne7rifgdkufucgxwm

Scene Segmentation with Low-Dimensional Semantic Representations and Conditional Random Fields

Wen Yang, Bill Triggs, Dengxin Dai, Gui-Song Xia
2010 EURASIP Journal on Advances in Signal Processing  
In the first stage, codebook-based local appearance features are regularized and reduced in dimension using latent topic models, combined with spatial pyramid matching based spatial layout features, and  ...  Shotton et al. [7] described a model for discriminating object classes that efficiently incorporates texture, layout, and contextual information.  ...  The authors would like to thank Professor T. Joachims of Cornell University for his help with SVMStruct.  ... 
doi:10.1155/2010/196036 fatcat:6rq7rl4w7ng23nrl2ezgg3emnq

Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries [article]

Yuke Zhu, Ce Zhang, Christopher Ré, Li Fei-Fei
2015 arXiv   pre-print
Our system achieves competitive results compared to purpose-built models on standard recognition and retrieval tasks, while exhibiting greater flexibility in answering richer visual queries.  ...  We propose a knowledge base (KB) framework to handle an assortment of visual queries, without the need to train new classifiers for new tasks.  ...  A.4.1 Learning The factor graph model in Sec. 3.1 is an instance of standard energy-based probabilisitic models [22] where the energy function E(I) is defined through a linear combination of factors:  ... 
arXiv:1507.05670v2 fatcat:fjcydziz6zbknegnvwa6xy6cyu
« Previous Showing results 1 — 15 out of 2,747 results