Filters








39,358 Hits in 3.5 sec

Probabilistic visual concept trees

Lexing Xie, Rong Yan, Jelena Tešić, Apostol Natsev, John R. Smith
2010 Proceedings of the international conference on Multimedia - MM '10  
This paper presents probabilistic visual concept trees, a model for large visual semantic taxonomy structures and its use in visual concept detection.  ...  We propose probabilistic visual concept trees for modeling a taxonomy forest with observation uncertainty.  ...  CONCLUSION We presented probabilistic concept trees, a novel representation and inference model for large semantic visual taxonomy.  ... 
doi:10.1145/1873951.1874099 dblp:conf/mm/XieYTNS10 fatcat:xq4qag77r5d2ti4nfhytk6tttq

A System for Probabilistic Linking of Thesauri and Classification Systems

Lisa Posch, Philipp Schaer, Arnim Bleier, Markus Strohmaier
2015 Künstliche Intelligenz  
This paper presents a system which creates and visualizes probabilistic semantic links between concepts in a thesaurus and classes in a classification system.  ...  The links are then presented to users of the system in an interactive visualization, providing them with an automatically generated overview of the relations between the thesaurus and the classification  ...  The probabilistic links are then visualized in an interactive way.  ... 
doi:10.1007/s13218-015-0413-9 fatcat:qbiyua4shjgvxk7pk7o3mhcdmq

IPL at ImageCLEF 2017 Concept Detection Task

Leonidas Valavanis, Spyridon Stathopoulos
2017 Conference and Labs of the Evaluation Forum  
A probabilistic k-nearest neighbor approach was used for automatically detecting multiple concepts in medical images.  ...  The visual representation of images was based on the well known, bag of visual words and bag-of-colors models.  ...  Our approach to concept detection is based on a Probabilistic k-nearest neighbor (PKNN) merging two well known models for image representation, that of the Bag of Visual Words (BoVW), [6] and an improved  ... 
dblp:conf/clef/ValavanisS17 fatcat:w2zflzdi5vfkbjwjqs5zqdh7uu

Image Interpretation by Combining Ontologies and Bayesian Networks [chapter]

Spiros Nikolopoulos, Georgios Th. Papadopoulos, Ioannis Kompatsiaris, Ioannis Patras
2012 Lecture Notes in Computer Science  
A bayesian network (BN) is used for integrating statistical and explicit knowledge and perform hypothesis testing using evidence-driven probabilistic inference.  ...  In this work we propose a framework that performs knowledge-assisted analysis of visual content using ontologies to model domain knowledge and conditional probabilities to model the application context  ...  The low level processing of visual stimulus consists of visual features extraction, segmentation and learning the concept detection models.  ... 
doi:10.1007/978-3-642-30448-4_39 fatcat:yrbi3oyxvncj7hpyeoeszvegne

LEGO-MM: LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiMedia

Jinhui Tang, Shiyu Chang, Guo-Jun Qi, Qi Tian, Yong Rui, Thomas S. Huang
2017 IEEE Transactions on Image Processing  
Index Terms-LEGO-MM, Concept recycling, Model warehouse, Probabilistic logic ontology tree, Logical operations.  ...  Specifically, we first formulate the logic operations to be the lego connectors to combine existing concept models hierarchically in probabilistic logic ontology trees.  ...  PROBABILISTIC LOGICAL ONTOLOGY TREE To present how we can apply LEGO-MM to construct complex concepts, in this section we define concrete data learning structure -Probabilistic Logical Ontology Tree (PLOT  ... 
doi:10.1109/tip.2016.2612825 pmid:28113970 fatcat:sqfkjdpcgzeu3eyza74zt2o3se

Using Color to Help in the Interactive Concept Formation [chapter]

Vasco Furtado, Alexandre Cavalcante
2004 Lecture Notes in Computer Science  
This article describe s a technique that aims at qualifying a concept hierarchy with colors, in such a way that it can be feasible to promote the interactivity between the user and an incremental probabilistic  ...  concept formation algorithm.  ...  Incremental Probabilistic Concept Formation Incremental probabilistic concept formation systems accomplish a process of concept hierarchy formation that generalizes obs ervations contained in the node  ... 
doi:10.1007/978-3-540-28645-5_16 fatcat:5nzpxalhzzdmvnpuhm4aujn66m

Probabilistic, Multi-staged Interpretation of Spoken Utterances

Ingrid Zukerman, Michael Niemann, Sarah George
2006 2006 International Conference on Computational Inteligence for Modelling Control and Automation and International Conference on Intelligent Agents Web Technologies and International Commerce (CIMCA'06)  
s interpretation process maps spoken utterances to conceptual graphs, and the nodes in these graphs to concepts in the world.  ...  The authors thank Eugene Charniak for his modifications to his probabilistic parser, and Charles Prosser for his assistance in extracting multiple texts from ViaVoice.  ...  The word sequences are then parsed using Charniak's probabilistic parser, which generates a set of Parse Trees. The last stage uses Concept Graphs (CGs) to perform semantic interpretation.  ... 
doi:10.1109/cimca.2006.165 dblp:conf/cimca/ZukermanNG06 fatcat:sgh3shq64vdu7hoynui26zzeai

Image Retrieval of Semantic Similarity Measure based on Probability-weighted

Qian Wang, Chunli Zhang, Lixin Song
2014 International Journal of Multimedia and Ubiquitous Engineering  
This method combines the image feature mapping the visual characteristics of the underlying semantic with the domain ontology description to build a tree-like hierarchical semantic model.  ...  proposed a novel similarity calculation method of image semantic based on the probabilistic weighting.  ...  In this study, the image low level visual features are mapped to the visual semantic associated with domain ontology concept semantic to constitute a tree-like hierarchical semantic.  ... 
doi:10.14257/ijmue.2014.9.10.12 fatcat:7bgb6vs33nhm5h2ohbnxcs54bm

Probabilistic, Multi-staged Interpretation of Spoken Utterances [chapter]

Ingrid Zukerman, Michael Niemann, Sarah George, Yuval Marom
2006 Lecture Notes in Computer Science  
s interpretation process maps spoken utterances to conceptual graphs, and the nodes in these graphs to concepts in the world.  ...  The authors thank Eugene Charniak for his modifications to his probabilistic parser, and Charles Prosser for his assistance in extracting multiple texts from ViaVoice.  ...  The word sequences are then parsed using Charniak's probabilistic parser, which generates a set of Parse Trees. The last stage uses Concept Graphs (CGs) to perform semantic interpretation.  ... 
doi:10.1007/11941439_150 fatcat:ungur5sbpzbizgub5izyotgmyy

FrIDA -A Free Intelligent Data Analysis Toolbox

C. Borgelt, G.G. Rodriguez
2007 2007 IEEE International Fuzzy Systems Conference  
In addition, this toolbox is equipped with basic visualization capabilities, like scatter plots and bar charts, but also with specialized visualization modules for decision and regression trees as well  ...  Fig. 14 . 14 Fuzzy and probabilistic cluster visualization. Fig. 15 . 15 Decision/Regression Tree parameters. Fig. 16 . 16 Decision/Regression Tree induction.  ...  Fig. 17 . 17 Decision/Regression Tree pruning.Fig. 18. Decision/Regression Tree execution. Fig. 19 . 19 Decision Tree visualization. Fig. 20. Regression Tree visualization.  ... 
doi:10.1109/fuzzy.2007.4295654 dblp:conf/fuzzIEEE/BorgeltR07 fatcat:bzmzppkiirezzosodnwvmsjdw4

A Probabilistic Approach to the Interpretation of Spoken Utterances [chapter]

Ingrid Zukerman, Enes Makalic, Michael Niemann, Sarah George
2008 Lecture Notes in Computer Science  
postulates and maintains multiple interpretations of the spoken discourse, and employs a probabilistic formalism to assess and rank hypotheses regarding the meaning of spoken utterances.  ...  The second stage applies Charniak's probabilistic parser (ftp: //ftp.cs.brown.edu/pub/nlparser/) to generate parse trees from the texts.  ...  ., all instantiated concepts have the same prior, hence it does not affect the performance of the system. However, visual and dialogue context will come into play when Scusi?  ... 
doi:10.1007/978-3-540-89197-0_53 fatcat:x6i3rnwhrndttlpat4x5sf5umm

Using Probabilistic Feature Matching to Understand Spoken Descriptions [chapter]

Ingrid Zukerman, Enes Makalic, Michael Niemann
2008 Lecture Notes in Computer Science  
We describe a probabilistic reference disambiguation mechanism developed for a spoken dialogue system mounted on an autonomous robotic agent.  ...  Our mechanism performs probabilistic comparisons between features specified in referring expressions (e.g., size and colour) and features of objects in the domain.  ...  Conclusion We have offered a probabilistic reference disambiguation mechanism that considers intrinsic features.  ... 
doi:10.1007/978-3-540-89378-3_16 fatcat:7iyqzjz4dnakdcmy6gbivkd6tq

Probabilistic combination of spatial context with visual and co-occurrence information for semantic image analysis

Georgios Th. Papadopoulos, Vasileios Mezaris, Ioannis Kompatsiaris, Michael G. Strintzis
2010 2010 IEEE International Conference on Image Processing  
In this paper, a probabilistic approach to combining spatial context with visual and co-occurrence information for semantic image analysis is presented.  ...  Overall, the examined image is segmented and subsequently an initial classification of the resulting image regions to semantic concepts is performed based solely on visual information.  ...  In particular, it is shown that concepts exhibiting more well-defined spatial configuration are substantially favored, such as concepts Building, Person in D 1 and Tree, Road in D2.  ... 
doi:10.1109/icip.2010.5652615 dblp:conf/icip/PapadopoulosMKS10 fatcat:ttzvwtpg2bgovdmwigy7bbf3jm

Guest Editorial on Decision Making in Human and Machine Vision

Alfredo Petrosino, Sankar K. Pal
2014 IEEE Transactions on Systems, Man & Cybernetics. Systems  
Modeling top-down visual attention in complex interactive environments," by Borji et al., the authors model top-down overt visual attention based on graphical models for probabilistic inference and reasoning  ...  The proposed model is shown to be more effective in employing and reasoning over spatiotemporal visual data compared with the state-of-the-art.  ... 
doi:10.1109/tsmc.2014.2313155 fatcat:435wqhhvi5eopegnfbhx57zc4e

A Bayesian generative model for learning semantic hierarchies

Roni Mittelman, Min Sun, Benjamin Kuipers, Silvio Savarese
2014 Frontiers in Psychology  
Using a weak form of supervision, provided by the category labels, semantic concepts such as "furry" and "snout" have been discovered using a RBM with a bag-of-visual-words based representation (Mittelman  ...  system, as well as improve the performance of computerized visual recognition systems.  ... 
doi:10.3389/fpsyg.2014.00417 pmid:24904452 pmcid:PMC4033064 fatcat:34d22oromrdbtndu5wgrpuvqjq
« Previous Showing results 1 — 15 out of 39,358 results