Filters








417 Hits in 3.8 sec

Higra: Hierarchical Graph Analysis

B. Perret, G. Chierchia, J. Cousty, S.J. F. Guimarães, Y. Kenmochi, L. Najman
2019 SoftwareX  
The main aspects of hierarchical graph analysis addressed in Higra are the construction of hierarchical representations (agglomerative clustering, mathematical morphology hierarchies, etc.), the analysis  ...  Higra -Hierarchical Graph Analysis is a C++/Python library for efficient sparse graph analysis with a special focus on hierarchical methods capable of handling large amount of data.  ...  On the contrary, Scikit-Learn [5] has a module dedicated to agglomerative clustering which can handle sparse graph.  ... 
doi:10.1016/j.softx.2019.100335 fatcat:hmgnylzgenh25n5iry5q3kg7hm

A CLUSTERED SEMANTIC GRAPH APPROACH FOR MULTI-DOCUMENT ABSTRACTIVE SUMMARIZATION

Atif Khan, Naomie Salim, Waleed Reafee, Anupong Sukprasert, Yogan Jaya Kumar
2015 Jurnal Teknologi  
Agglomerative hierarchical clustering is performed to eliminate redundancy in such a way that representative PAS with the highest salience score from each cluster is chosen, and fed to language generation  ...  Content selection for summary is made by ranking the important graph vertices (PASs) based on modified graph based ranking algorithm.  ...  The graph nodes are ranked based on salience score.  ... 
doi:10.11113/jt.v77.6491 fatcat:zhuxgbmfavfkvjhsbuu4qhjsem

Path-based clustering for grouping of smooth curves and texture segmentation

B. Fischer, J.M. Buhmann
2003 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Perceptual Grouping organizes image parts in clusters based on psychophysically plausible similarity measures.  ...  In addition to extracting connected structures, objects are singled out as outliers when they are too far away from any cluster structure.  ...  Therefore, we will present a fast agglomerative optimization heuristic which is based on the Path-Based Clustering costs function.  ... 
doi:10.1109/tpami.2003.1190577 fatcat:xr4hmgfnufbtvktwzvpz3xej44

Clustering Ontology-enriched Graph Representation for Biomedical Documents based on Scale-Free Network Theory

Illhoi Yoo, Xiaohua Hu
2006 2006 3rd International IEEE Conference Intelligent Systems  
Based on scale-free network theory, our approach generates a model for each document cluster from the ontology-enriched graph representation by identifying k high density subgraphs capturing the core semantic  ...  Instead of depending on traditional vector space model, this approach represents documents as graphs using domain knowledge in ontology because graphs can represent the semantic relationships among the  ...  documents to clusters based on the graph model.  ... 
doi:10.1109/is.2006.348532 fatcat:jfe3vidtknhdzbvkyntr3smbme

Multi-document summarization using cluster-based link analysis

Xiaojun Wan, Jianwu Yang
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
This paper proposes the Cluster-based Conditional Markov Random Walk Model (ClusterCMRW) and the Cluster-based HITS Model (ClusterHITS) to fully leverage the cluster-level information.  ...  Experimental results on the DUC2001 and DUC2002 datasets demonstrate the good effectiveness of our proposed summarization models.  ...  In addition, Marcu [19] selects important sentences based on the discourse structure of the text.  ... 
doi:10.1145/1390334.1390386 dblp:conf/sigir/WanY08 fatcat:djxvs7yrbbcoxglefqdbv7ukui

Hierarchical Salient Object Detection for Assisted Grasping [article]

Dominik Alexander Klein, Boris Illing, Bastian Gaspers, Dirk Schulz, Armin Bernd Cremers
2017 arXiv   pre-print
Based on this, an easy-to-use pick and place manipulation system was developed and tested exemplarily.  ...  In comprehensive experiments we demonstrate its ability to detect salient objects in a scene.  ...  Since our approach is working purely on the graph structure created from hierarchical grouping, we call it Partition Tree Saliency (PaTS).  ... 
arXiv:1701.04284v2 fatcat:kwakraxkznazrorlzarr5oib6a

Grouping business news stories based on salience of named entities

Llorenc Escoter, Lidia Pivovarova, Mian Du, Anisia Katinskaia, Roman Yangarber
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers  
We present a grouping algorithm, and explore several vector-based representations of input documents: from a baseline using keywords, to a method using salience-a measure of importance of named entities  ...  In news aggregation systems focused on broad news domains, certain stories may appear in multiple articles.  ...  We compare salience to two other weighting strategies: namely, frequency alone, and TF-IDF. Clustering algorithm The experiments follow the same structure.  ... 
doi:10.18653/v1/e17-1103 dblp:conf/eacl/YangarberEPDK17 fatcat:woddqtxpajgethvaxkp2zoj2za

Contextual Hypergraph Modelling for Salient Object Detection [article]

Xi Li, Yao Li, Chunhua Shen, Anthony Dick, Anton van den Hengel
2013 arXiv   pre-print
Furthermore, we propose an alternative approach based on center-versus-surround contextual contrast analysis, which performs salient object detection by optimizing a cost-sensitive support vector machine  ...  As a result, the problem of salient object detection becomes one of finding salient vertices and hyperedges in the hypergraph.  ...  To accelerate the optimization process (8), we adopt a fast agglomerative mean-shift clustering method based on iterative query set compression [27] .  ... 
arXiv:1310.5767v1 fatcat:aqrgy5gfnzamzfakefq7pgglm4

Contextual Hypergraph Modeling for Salient Object Detection

Xi Li, Yao Li, Chunhua Shen, Anthony Dick, Anton Van Den Hengel
2013 2013 IEEE International Conference on Computer Vision  
Furthermore, we propose an alternative approach based on centerversus-surround contextual contrast analysis, which performs salient object detection by optimizing a cost-sensitive support vector machine  ...  As a result, the problem of salient object detection becomes one of finding salient vertices and hyperedges in the hypergraph.  ...  To accelerate the optimization process (8), we adopt a fast agglomerative mean-shift clustering method based on iterative query set compression [27] .  ... 
doi:10.1109/iccv.2013.413 dblp:conf/iccv/LiLSDH13 fatcat:zh7egfzuzfawbjvsehzseyniri

Comparative Analysis Of Superpixel Segmentation Methods

SumitKaur, Dr. R.K Bansal
2018 Zenodo  
K mean based SLIC method shows better performance as compare to other while evaluating on the bases of under segmentation error and boundary recall, etc parameters.  ...  It performs an agglomerative clustering of pixels as nodes on a graph, such that each superpixel is the minimum spanning tree of the constituent pixels.  ...  Saliency Detection The goal of saliency detection is to tell whether a pixel belongs to the most salient object.  ... 
doi:10.5281/zenodo.1205971 fatcat:ileqplaumzbpfak3egu4jobepq

Multiregion Segmentation Based on Compact Shape Prior

Ran Fan, Xiaogang Jin, Charlie C. L. Wang
2015 IEEE Transactions on Automation Science and Engineering  
Secondly, we extract components with compact shape by using agglomerative clustering to optimize the normalized cut metric, in which the affinities of boundary compatibility, 2D shape compactness and 3D  ...  To solve the problem of generating segmentations of meaningful parts from scanned models with freeform surfaces, we explore a compact shape prior based segmentation approach in this paper.  ...  Agglomerative clustering The methodology of other mesh segmentation algorithm based on graph partition (e.g., [14] , [35] ) cannot be applied here as the metrics used in our approach cannot be accurately  ... 
doi:10.1109/tase.2014.2317497 fatcat:xtaopz2jrbbxxnj7xa3shujy44

Temporally stable feature clusters for maritime object tracking in visible and thermal imagery

Christopher Osborne, Tom Cane, Tahir Nawaz, James Ferryman
2015 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)  
Object detection is based on agglomerative clustering of temporally stable features.  ...  Object extents are first determined based on persistence of detected features and their relative separation and motion attributes.  ...  Graph-based agglomerative clustering We propose a cluster analysis technique which belongs to the class of hierarchical clustering methods known as agglomerative clustering in which a cluster is initially  ... 
doi:10.1109/avss.2015.7301769 dblp:conf/avss/OsborneCNF15 fatcat:msc2sxtbtrebzobpspeown4qiu

Unsupervised 3D Object Discovery and Categorization for Mobile Robots [chapter]

Jiwon Shin, Rudolph Triebel, Roland Siegwart
2016 Springer Tracts in Advanced Robotics  
Our algorithm finds the mapping from local class labels to global category labels by inferring on this graph and uses this mapping to assign the final category label to the discovered objects.  ...  We demonstrate on real data our alogrithm's ability to discover and categorize objects without supervision.  ...  This classifications determines saliency based on difference in entropy of a region to its nearby regions.  ... 
doi:10.1007/978-3-319-29363-9_4 fatcat:hf3gombhzvb2jnvcusckc3mlxu

COMPARATIVE ANALYSIS OF SUPERPIXEL SEGMENTATION METHODS

Sumit Kaur, R.K Bansal
2020 International Journal of Engineering Technologies and Management Research  
K mean based SLIC method shows better performance as compare to other while evaluating on the bases of under segmentation error and boundary recall, etc parameters.  ...  It performs an agglomerative clustering of pixels as nodes on a graph, such that each superpixel is the minimum spanning tree of the constituent pixels.  ...  Saliency Detection The goal of saliency detection is to tell whether a pixel belongs to the most salient object.  ... 
doi:10.29121/ijetmr.v5.i3.2018.172 fatcat:fapg6o7jvjc3ne4i3hltf2ixre

Saliency maps on image hierarchies

Verónica Vilaplana
2015 Signal processing. Image communication  
In this paper we propose two saliency models for salient object segmentation based on a hierarchical image segmentation, a tree-like structure that represents regions at different scales from the details  ...  The first model is based on a hierarchy of image partitions. The saliency at each level is computed on a region basis, taking into account the contrast between regions.  ...  Next, a BPT is created using the saliency of the regions to define the merging criterion and merging order. Based on the analysis of the tree structure a final pixel-based saliency map is derived.  ... 
doi:10.1016/j.image.2015.07.012 fatcat:t4dytwnaxnairhxa45ppvs374u
« Previous Showing results 1 — 15 out of 417 results