Filters








10,291 Hits in 7.7 sec

Exploring inter-concept relationship with context space for semantic video indexing

Xiao-Yong Wei, Yu-Gang Jiang, Chong-Wah Ngo
2009 Proceeding of the ACM International Conference on Image and Video Retrieval - CIVR '09  
This paper proposes the construction of a context space and the exploration of the space for CBCF.  ...  The space is linear and can be built by modeling the inter-concept relationship through annotation provided by either manual labeling or machine tagging.  ...  In this paper, we propose to construct a context space which is able to offer global measurement of inter-concept relationship.  ... 
doi:10.1145/1646396.1646416 dblp:conf/civr/WeiJN09 fatcat:ykxm4gd2o5cgrddd2tvhjidcki

Semantic-Based Video Retrieval Survey

Shaimaa Toriah Mohamed Toriah, Atef Zaki Ghalwash, Aliaa A. A. Youssif
2018 Journal of Computer and Communications  
Moreover, the different methods that bridge the semantic gap in video retrieval are discussed in more details.  ...  Video retrieval is a vital process in multimedia applications such as video search engines, digital museums, and video-on-demand broadcasting.  ...  Semantic-based retrieval methods try to cover this gap by pooling a set of concepts and form their inter-relationships, which called context information.  ... 
doi:10.4236/jcc.2018.68003 fatcat:qfep2py7ufhwxea7vazpujltja

A generic framework for semantic video indexing based on visual concepts/contexts detection

Nizar Elleuch, Anis Ben Ammar, Adel M. Alimi
2014 Multimedia tools and applications  
The obtained experimental results are promising for a semantic concept/context detection process.  ...  The second level (level2) aims to build the semantic models for supervised learning of concepts/contexts.  ...  Also, the authors are grateful to NIST and the TRECVID coordinators for the benchmark organization's effort.  ... 
doi:10.1007/s11042-014-1955-9 fatcat:qd2rn5x7pzgstje32nffgigkru

Enrichment and Ranking of the YouTube Tag Space and Integration with the Linked Data Cloud [chapter]

Smitashree Choudhury, John G. Breslin, Alexandre Passant
2009 Lecture Notes in Computer Science  
We have explored social, temporal and spatial contexts to enrich and extend the existing tag space.  ...  The enhancement of tag spaces with semantics has been accomplished through two major tasks: (1) a tag space expansion and ranking step; and (2) through concept matching and integration with the Linked  ...  relationships between visual features and semantic concepts.  ... 
doi:10.1007/978-3-642-04930-9_47 fatcat:kieqduc4y5b35dtssmnhjwxkvq

VIREO at TRECVID 2010: Semantic Indexing, Known-Item Search, and Content-Based Copy Detection

Chong-Wah Ngo, Shiai Zhu, Hung-Khoon Tan, Wanlei Zhao, Xiao-Yong Wei
2010 TREC Video Retrieval Evaluation  
This paper presents our approaches and the comparative analysis of our results for the three TRECVID 2010 tasks that we participated in: semantic indexing, known-item search and content-based copy detection  ...  Summary This year, we explore integrating ontology context relationship for semantic indexing (SIN).  ...  The inter-concept relationships are two-fold: 1) semantic relationship, for example concept "car" is a kind of "vehicle"; 2) contextual relationship, which considers the co-occurrence between concepts,  ... 
dblp:conf/trecvid/NgoZTZW10 fatcat:x4yunq4r7bb2dfcbecni2y52zy

Incorporating Concept Ontology for Hierarchical Video Classification, Annotation, and Visualization

Jianping Fan, Hangzai Luo, Yuli Gao, R. Jain
2007 IEEE transactions on multimedia  
Index Terms-Concept ontology, hierarchical boosting, hyperbolic visualization, multimodal boosting, multitask learning, semantic gap, video classification and annotation.  ...  Automatic video concept detection via semantic classification is one promising solution to bridge the semantic gap.  ...  Worring for handling the review process of their paper.  ... 
doi:10.1109/tmm.2007.900143 fatcat:ts2cgdhakreanildysxdmcbncm

Landscaping the information space of large multi-database networks

Mike P. Papazoglou, Henderik A. Proper, Jian Yang
2001 Data & Knowledge Engineering  
This paper presents a conceptual architecture for the organisation information space across collections of component systems in multi-databases that provides serendipity, exploration and contextualisation  ...  support so that users can achieve logical connections between concepts they are familiar with and schema terms employed in multi-database systems.  ...  We call this former form of exploration index-driven.  ... 
doi:10.1016/s0169-023x(00)00050-1 fatcat:akgagzotjfhdtkpcii5s5kqkru

Multi-cue fusion for semantic video indexing

Ming-Fang Weng, Yung-Yu Chuang
2008 Proceeding of the 16th ACM international conference on Multimedia - MM '08  
First, a recursive algorithm is proposed to learn both inter-concept and inter-shot relationships from ground truth annotations of tens of thousands of shots for hundreds of concepts.  ...  This paper describes a multi-cue fusion approach toward improving the accuracy of semantic video indexing.  ...  In addition, the authors want to thank the Digital Video and Multimedia Laboratory of Columbia University and the Video Retrieval Group of City University of Hong Kong for providing the useful annotation  ... 
doi:10.1145/1459359.1459370 dblp:conf/mm/WengC08 fatcat:7xcrru23irbavnxhdb2afzdriy

Collaborative video reindexing via matrix factorization

Ming-Fang Weng, Yung-Yu Chuang
2012 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
Concept-based video indexing generates a matrix of scores predicting the possibilities of concepts occurring in video shots.  ...  Based on the idea of collaborative filtering, this paper presents unsupervised methods to refine the initial scores generated by concept classifiers by taking into account the concept-to-concept correlation  ...  We especially thank the Video Retrieval Group of City University of Hong Kong and Dr. Yu-Gang Jiang for providing us the useful detection scores.  ... 
doi:10.1145/2168996.2169003 fatcat:tl75radnbzhgllvw2pztbyvhim

Video semantics exploration for indexing and retrieval

2020 Al-Azhar Bulletin of Science  
To stand on the thoroughly situation, video semantic concepts exploration for indexing and retrieval purposes evolution from conventional methods to the state-ofthe-art ones will be reviewed.  ...  Video semantic concepts exploration is a fundamental problem in a video indexing and retrieval. It has a long history of investigation since early days till recent achievements.  ...  The different tasks involved in semantic concepts exploration for video indexing were linked and consolidated from its origin till recently achieved works.  ... 
doi:10.21608/absb.2020.210373 fatcat:h2olivohlrglpp5jtfvpnqbijy

Semantic context transfer across heterogeneous sources for domain adaptive video search

Yu-Gang Jiang, Chong-Wah Ngo, Shih-Fu Chang
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
Automatic video search based on semantic concept detectors has recently received significant attention.  ...  The semantic context transfer process provides an effective means to cope with the domain shift between external knowledge source (e.g., Flickr context) and test data, which is a critical issue in video  ...  We are grateful to Jun Wang for his help in the formulation part and Xiao-Yong Wei for providing baseline results using WordNet.  ... 
doi:10.1145/1631272.1631296 dblp:conf/mm/JiangNC09 fatcat:au3kklsoarb77mnfomme4zjbjy

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

H. Luo, J. Fan, S. Satoh, J. Yang, W. Ribarsky
2008 Signal processing. Image communication  
Second, visual semantic items, such as human faces, text captions, video concepts, are extracted automatically by using our semantic video analysis techniques.  ...  With a better global overview of large-scale news video collections, users can specify their queries more precisely and explore large-scale news video collections interactively.  ...  analysis results from multiple information sources are synchronized and integrated for indexing and exploring large-scale news video collections.  ... 
doi:10.1016/j.image.2008.04.014 fatcat:uvfv6g76kzhfbhx7mosxks3yum

VIREO/DVMM at TRECVID 2009: High-Level Feature Extraction, Automatic Video Search, and Content-Based Copy Detection

Chong-Wah Ngo, Yu-Gang Jiang, Xiao-Yong Wei, Wanlei Zhao, Yang Liu, Shiai Zhu, Jun Wang, Shih-Fu Chang
2009 TREC Video Retrieval Evaluation  
High-Level Feature Extraction (HLFE): Our main focus for the HLFE task is on the study of a new method named domain adaptive semantic diffusion (DASD) [1] , which exploits semantic context (concept relationship  ...  We apply our TRECVID 2008 HLFE system [2] to construct baseline detectors for the 20 evaluated concepts, where both local and global features are explored.  ...  (inter-concept relationship).  ... 
dblp:conf/trecvid/NgoJWZLZWC09 fatcat:2xcs2usjszh6zjdkiilqronbm4

An empirical study of inter-concept similarities in multimedia ontologies

Markus Koskela, Alan F. Smeaton
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
inter-concept relations, has not received similar attention.  ...  In this paper, we present results from our empirical analysis of different types of similarity among semantic concepts in two multimedia ontologies, LSCOM-Lite and CDVP-206.  ...  INTRODUCTION & CONTEXT Associating semantic information with visual data has attracted a lot of research attention recently in order to facilitate semantic indexing and concept-based retrieval of visual  ... 
doi:10.1145/1282280.1282348 dblp:conf/civr/KoskelaS07 fatcat:qqm5kniwvbarrp7xjtq56jbvvy

Concept-Oriented Indexing of Video Databases: Toward Semantic Sensitive Retrieval and Browsing

J. Fan, H. Luo, A.K. Elmagarmid
2004 IEEE Transactions on Image Processing  
; (c) Semantic video classification; (d) Concept-oriented video database indexing and access.  ...  Specifically, the framework includes: (1) A semantic-sensitive video content representation framework by using principal video shots to enhance the quality of features; (2) Semantic video concept interpretation  ...  The parent-child relationships in the database indexing structure correspond to the underlying inter-level relationships in a certain domaindependent concept hierarchy.  ... 
doi:10.1109/tip.2004.827232 pmid:15648863 fatcat:pevnxl3cfzb63fxyqbz3nssgti
« Previous Showing results 1 — 15 out of 10,291 results