Filters








658 Hits in 7.4 sec

Automatic semantic video annotation in wide domain videos based on similarity and commonsense knowledgebases

Amjad Altadmri, Amr Ahmed
2009 2009 IEEE International Conference on Signal and Image Processing Applications  
ACKNOWLEDGMENT The authors would like to thank Prof. Andrew Hunter for his efforts. This project is fully funded by Damascus University, Syria.  ...  These tags indicate which part is the object, which is the subject in linguistic terminology, and which is the event, i.e. the verb and its related prepositions, and the location, if exists.  ...  repeated parts (or whole sentence) resulted from many similar videos, like two videos, one annotated as "car speed up" and the other "car slow down".  ... 
doi:10.1109/icsipa.2009.5478723 fatcat:vter3pe2jjg5njcnkvfeyvvqei

VisualNet: Commonsense knowledgebase for video and image indexing and retrieval application

Amjad Altadmri, Amr Ahmed
2009 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems  
VisualNet is obtained by our fully automated engine that constructs a new unified structure concluding the knowledge from two commonsense knowledgebases, namely WordNet and ConceptNet.  ...  In this paper, we propose a novel commonsense knowledgebase that forms the link between the visual world and its semantic textual representation. We refer to it as "VisualNet".  ...  The non-useful parts in this area vary from some prepositions and stop words to some adjectives and adverbs.  ... 
doi:10.1109/icicisys.2009.5358084 fatcat:gfgfiy4qbjfcpjfmj3t6w6ctni

Using Commonsense Knowledge and Text Mining for Implicit Requirements Localization

Emebo Onyeka, Aparna S. Varde, Vaibhav Anu, Niket Tandon, Olawande Daramola
2020 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI)  
In this paper, we demonstrate a software tool called COTIR developed by us as a system that integrates Commonsense knowledge, Ontology and Text mining for early identification of Implicit Requirements.  ...  It would interest AI scientists as it entails multi-disciplinary work encompassing text mining, ontology and commonsense knowledge.  ...  Text Mining using CSKB and Ontology: The text mining functionality of COTIR, part of its NL Processor is illustrated in Fig. 3 . Raw text from SRS documents forms the input to this module.  ... 
doi:10.1109/ictai50040.2020.00146 fatcat:fkgr33zt4fbt7cppk4eremm5gq

Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches [article]

Shane Storks, Qiaozi Gao, Joyce Y. Chai
2020 arXiv   pre-print
relying on reasoning and knowledge of the world.  ...  learning and inference approaches in order to support a better understanding of this growing field.  ...  Acknowledgements We would like to thank the anonymous reviewers for their greatly helpful comments and suggestions.  ... 
arXiv:1904.01172v3 fatcat:minzpxrrwfebdipu55udwe5dxq

Sensor-Based Activity Recognition

Liming Chen, J. Hoey, C. D. Nugent, D. J. Cook, Zhiwen Yu
2012 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
However, there is a lack of high-level overview on this topic that can inform related communities of the research state of the art.  ...  Then we review the major approaches and methods associated with sensor-based activity monitoring, modeling and recognition from which strengths and weaknesses of those approaches are highlighted.  ...  They used the QTag tagger to tag each word in a sentence with its part of speech (POS) and a customized regular expression extractor to extract objects used in an activity.  ... 
doi:10.1109/tsmcc.2012.2198883 fatcat:6s6uew7xhjglva2wikyulmduiy

Open Mind Common Sense: Knowledge Acquisition from the General Public [chapter]

Push Singh, Thomas Lin, Erik T. Mueller, Grace Lim, Travell Perkins, Wan Li Zhu
2002 Lecture Notes in Computer Science  
Open Mind Common Sense is a knowledge acquisition system designed to acquire commonsense knowledge from the general public over the web.  ...  The new system acquires facts, descriptions, and stories by allowing participants to construct and fill in natural language templates.  ...  Acknowledgements We extend our thanks to David Stork for organizing the larger Open Mind effort, and the many thousands of members of the general public who contributed their knowledge to our database.  ... 
doi:10.1007/3-540-36124-3_77 fatcat:2sykukhuzbayzizpaacnhj2prq

Stereotypical gender actions can be extracted from web text

Amaç Herdağdelen, Marco Baroni
2011 Journal of the American Society for Information Science and Technology  
We conclude that it is feasible to use natural text (and a Twitter-derived corpus in particular) in order to augment commonsense repositories with the stereotypical gender expectations of actions.  ...  We extracted gender-specic actions from text corpora and Twitter, and compared them to stereotypical expectations of people.  ...  Commonsense knowledge has already been exploited in very practical application areas like assisting users of an image retrieval application, by employing knowledge about commonsense activities that relate  ... 
doi:10.1002/asi.21579 fatcat:uyquopfhobfghdneyweylzly5q

Commonsense Properties from Query Logs and Question Answering Forums [article]

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
2021 arXiv   pre-print
We devise novel ways of tapping into search-engine query logs and QA forums, and combining the resulting candidate assertions with statistical cues from encyclopedias, books and image tags in a corroboration  ...  This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources.  ...  We thank the anonymous reviewers and Niket Tandon for helpful comments.  ... 
arXiv:1905.10989v4 fatcat:h2iuxuc7nvfudkycgvbqx5kxqy

Commonsense Properties from Query Logs and Question Answering Forums

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
We devise novel ways of tapping into search-engine query logs and QA forums, and combining the resulting candidate assertions with statistical cues from encyclopedias, books and image tags in a corroboration  ...  This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources.  ...  We thank the anonymous reviewers and Niket Tandon for helpful comments.  ... 
doi:10.1145/3357384.3357955 dblp:conf/cikm/RomeroRPPSW19 fatcat:idb3jc75gjc7tjpvog5zj3qoqm

A framework for automatic semantic video annotation

Amjad Altadmri, Amr Ahmed
2013 Multimedia tools and applications  
Textual semantic representations, such as tagging, labelling and annotation, are often important factors in the process of indexing any video, because of their user-friendly way of representing the semantics  ...  Tackling this gap is even harder in the case of unconstrained videos, mainly due to the lack of any previous information about the analyzed video on the one hand, and the huge amount of generic knowledge  ...  These tags indicate which part is the object (the subject in linguistic terminology), which is the action (the verb and its related prepositions), and which is the scene (the location), if it exists.  ... 
doi:10.1007/s11042-013-1363-6 fatcat:r7l52voc7rdpto4doezf42dgcy

Combining bibliometrics, information retrieval, and relevance theory, Part 1: First examples of a synthesis

Howard D. White
2007 Journal of the American Society for Information Science and Technology  
The tf weight of the item predicts its effect on the user in the context of the seed term, and its idf weight predicts the user's processing effort in relating the item to the seed term.  ...  The tf*idf formula from information retrieval is used to operationalize this ratio for any item co-occurring with a user-supplied seed term in bibliometric distributions.  ...  from the Web.  ... 
doi:10.1002/asi.20543 fatcat:nhs7grtbkbe3hb6kfjzbxfuoqm

The @neurIST ontology of intracranial aneurysms: providing terminological services for an integrated IT infrastructure

Martin Boeker, Holger Stenzhorn, Kai Kumpf, Philippe Bijlenga, Stefan Schulz, Susanne Hanser
2007 AMIA Annual Symposium Proceedings  
The usage of the ontology in the project comprises terminological control, text mining, annotation, and data mediation.  ...  Due to the integrative structure of the project the ontology needs to represent entities from various disciplines on a large spatial and temporal scale.  ...  Acknowledgement This work was generated in the framework of the @neurIST Integrated Project, which is co-financed by the European Commission through the contract no.  ... 
pmid:18693797 pmcid:PMC2655878 fatcat:m2g6kx55lnac7fyc5aspmzdbry

A goal-oriented web browser

Alexander Faaborg, Henry Lieberman
2006 Proceedings of the SIGCHI conference on Human Factors in computing systems - CHI '06  
In this chapter we significantly expand the breadth and functionality of this type of user interface through the use of large-scale knowledge bases of semantic information.  ...  p0220 Many users are familiar with the interesting but limited functionality of data detector interfaces like Microsoft's Smart Tags and Google's AutoLink.  ...  The authors would also like to thank Alan Dix.  ... 
doi:10.1145/1124772.1124883 dblp:conf/chi/FaaborgL06 fatcat:kq42daddfzfvbptzbjyhozkpha

A goal-oriented Web browser [chapter]

Alexander Faaborg, Henry Lieberman
2010 No Code Required  
In this chapter we significantly expand the breadth and functionality of this type of user interface through the use of large-scale knowledge bases of semantic information.  ...  p0220 Many users are familiar with the interesting but limited functionality of data detector interfaces like Microsoft's Smart Tags and Google's AutoLink.  ...  The authors would also like to thank Alan Dix.  ... 
doi:10.1016/b978-0-12-381541-5.00004-3 fatcat:i5bybb5ehnhbrjeil2bmuu6qc4

Web-Scale Multimedia Information Networks

Guo-Jun Qi, Min-Hsuan Tsai, Shen-Fu Tsai, Liangliang Cao, Thomas S. Huang
2012 Proceedings of the IEEE  
| The abundance of multimedia data on the Web presents both challenges (how to annotate, search, and mine) and opportunities (crawling the Web to create large structured multimedia data bases which can  ...  Ontology and cross-media structures are constructed and expanded by automatically constructing MINets from web-scale data by state-of-the-art information extraction and knowledge-based population techniques  ...  The data set has 13 leaf concepts and 13 540 images obtained from the Web. The four-level vehicle hierarchy is shown in Fig. 3 .  ... 
doi:10.1109/jproc.2012.2201909 fatcat:4hcia4agvbaija2kx5ynj2esse
« Previous Showing results 1 — 15 out of 658 results