Filters








18 Hits in 6.0 sec

MediaMill

Ork de Rooij, Cees G. M. Snoek, Marcel Worring
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
To handle such a large thesaurus in retrieval, an engine is developed which automatically selects a set of relevant concepts based on a textual query, and an novel user interface which uses multi dimensional  ...  In this technical demonstration we showcase the current version of the MediaMill system[1], a search engine that facilitates access to news video archives at a semantic level.  ...  CIVR'07, July 9-11, 2007, Amsterdam, The Netherlands. ACM 978-1-59593-733-9/07/0007. Figure 1 : 1 Left: multi thread dimensions for the Ro-torBrower.  ... 
doi:10.1145/1282280.1282376 dblp:conf/civr/RooijSW07 fatcat:3aa3xuuxuzeavacctmwskzweqm

RETIN

Julien Gony, Matthieu Cord, Sylvie Philipp-Foliguet, Philippe H. Gosselin, Frederic Precioso, Michel Jordan
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
RETIN applies also an active learning strategy for proposing documents to the user for labeling. The system can deal with images, 3D objects and videos and other media can be added to.  ...  The core of our system is an interactive online classification based on user labeling.  ...  Aknowledgement The authors are grateful to MUSCLE Network of Excellence for the financial support of this work.  ... 
doi:10.1145/1282280.1282294 dblp:conf/civr/GonyCPGPJ07 fatcat:j2tfatwkgjdspkvdqu5lybvnaq

Shaping 3D multimedia environments

Michael Dittenbach, Helmut Berger, Ronald Genswaider, Andreas Pesenhofer, Andreas Rauber, Thomas Lidy, Dieter Merkl
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. CIVR'07, July 9-11, 2007, Amsterdam, The Netherlands.  ...  Copyright 2007 ACM 978-1-59593-733-9/07/0007 ...$5.00.  ...  THE MEDIASQUARE The 3D Music Showroom The Scientific Library  ... 
doi:10.1145/1282280.1282292 dblp:conf/civr/DittenbachBGPRLM07 fatcat:ogdwu3qdwbg67g42t24kluzcwa

Video parsing based on head tracking and face recognition

Pengxu Li, Haizhou Ai, Yuan Li, Chang Huang
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
In this paper, we describe a fully automatic video retrieval prototype system that uses an image or a video sequence of an interested identity as probe.  ...  The system is based on face vision techniques including face detection and tracking, face alignment and recognition.  ...  CONCLUSIONS We have proposed a fully automatic video retrieval system. It integrates the state-of-the-art head tracking, face alignment and face recognition algorithms.  ... 
doi:10.1145/1282280.1282288 dblp:conf/civr/LiALH07 fatcat:i36tzoradzd4rc2m7ulf46rab4

The value of stories for speech-based video search

Bouke Huurnink, Maarten de Rijke
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
We isolate speech from other retrieval features, and evaluate on the 2003-2006 TRECVID test sets with a set of 94 natural language queries.  ...  Anecdotal evidence suggests that story-level information is important for the speech component of video retrieval.  ...  To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. CIVR'07, July 9-11, 2007 , Amsterdam, The Netherlands.  ... 
doi:10.1145/1282280.1282322 dblp:conf/civr/HuurninkR07 fatcat:nqwnprzsv5fvjkqofnozawug7y

Inducing a perceptual relevance shape classifier

Victoria J. Hodge, John Eakins, James Austin
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
We previously investigated human visual perception of trademark images and established a body of ground truth data in the form of trademark images and their respective human segmentations.  ...  The work indicated that there is a core set of segmentations for each image that people perceive.  ...  CIVR'07, July 9-11, 2007 list of boundary points to calculate the attributes used here.  ... 
doi:10.1145/1282280.1282306 dblp:conf/civr/HodgeEA07 fatcat:lo7av235qzhuvj77y7t7g6vzkm

Enhancing HSV histograms with achromatic points detection for video retrieval

Costantino Grana, Roberto Vezzani, Rita Cucchiara
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
Color is one of the most meaningful features used in content based retrieval of visual data.  ...  HSV is a widely adopted space in image and video retrieval, but its quantization for histogram generation can create misleading errors in classification of achromatic and low saturated colors.  ...  ACKNOWLEDGMENTS This work is supported by the DELOS NoE on Digital Libraries, as part of the IST Program of the European Commission (Contract G038-507618).  ... 
doi:10.1145/1282280.1282327 dblp:conf/civr/GranaVC07 fatcat:fpzdbl2mybcjneterxmed6i26m

New local descriptors based on dissociated dipoles

Alexis Joly
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
This allows the complete retrieval to be both more efficient and faster.  ...  This paper describes new local photometric descriptors based on dissociated dipoles for transformed images or rigid objects retrieval.  ...  To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. CIVR'07, July 9-11, 2007 , Amsterdam, Netherlands.  ... 
doi:10.1145/1282280.1282362 dblp:conf/civr/Joly07 fatcat:jeclodb54vebvjo6acifrlltem

Shape based 3D model retrieval without query

Susumu Endo, Takayuki Baba, Shuichi Shiitani, Yusuke Uehara, Daiki Masumoto, Shigemi Nagata
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
In previous retrieval systems, users should provide a 3D model as a query to the system. Then, the system retrieves similar 3D models and returns them to the user.  ...  In addition, we present the results of experiments to evaluate the retrieval efficiency, which shows that our method is four times as fast as a retrieval method using a query model.  ...  To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. CIVR'07, July 9-11, 2007 , Amsterdam, The Netherlands.  ... 
doi:10.1145/1282280.1282316 dblp:conf/civr/EndoBSUMN07 fatcat:tk2dcf7rxrbprn6qsrj4nchmvq

Multi-level local descriptor quantization for bag-of-visterms image representation

Pedro Quelhas, Jean-Marc Odobez
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
The use of this new multi-level representation will allow for the description of fine and coarse local image detail in one framework.  ...  In this view they somehow restrict the image description to one level of visual detail.  ...  To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. CIVR'07, July 9-11, 2007 , Amsterdam, The Netherlands.  ... 
doi:10.1145/1282280.1282319 dblp:conf/civr/QuelhasO07 fatcat:dewhln7tfjdjxorw3wlxhhvci4

Semantic facets

Jonathon S. Hare, Paul H. Lewis, Peter G. B. Enser, Christine J. Sandom
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
The second half of the paper describes our semantic retrieval system, and demonstrates its use with the museum image collection.  ...  A number of factors related to the image dataset that affect the quality of retrieval are also discussed.  ...  We are also grateful to the Victoria and Albert museum for providing the image data used in this work, and to the EPSRC and the Motorola UK Research Laboratory for their support of the initial development  ... 
doi:10.1145/1282280.1282320 dblp:conf/civr/HareLES07 fatcat:o5xoyto5dbcdzkggoiroae5qiu

Using multiple segmentations for image auto-annotation

Jiayu Tang, Paul H. Lewis
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
In this paper, we explore the novel use of multiple segmentations in the context of image auto-annotation.  ...  Unfortunately, automatic segmentation is a difficult problem, and most of the current segmentation techniques do not guarantee good results.  ...  CIVR'07, July 9-11, 2007 , Amsterdam, The Netherlands Copyright 2007 ACM 978-1-59593-733-9/07/0007 ...$5.00. 6, 15] , while a few are able to attach words to specific image regions [5, 17, 14] .  ... 
doi:10.1145/1282280.1282363 dblp:conf/civr/TangL07 fatcat:uj5eo5bymzgatgn2c4bfy3tbqy

A framework for multimedia content abstraction and its application to rushes exploration

Werner Bailer, Georg Thallinger
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
Multimedia content abstraction methods such as summarisation, skimming and browsing are of growing importance for the exploration of multimedia collections, complementing search and retrieval approaches  ...  We demonstrate the practical usability of the framework by using it to build an application for browsing a collection of rushes.  ...  ACKNOWLEDGMENTS The authors would like to thank their colleagues at the Institute of Information Systems of JOANNEUM RESEARCH for their support and feedback, especially Werner Haas and Christian Schober  ... 
doi:10.1145/1282280.1282307 dblp:conf/civr/BailerT07 fatcat:j33zqthr7ja7jdoqoucunctfay

Searching for logo and trademark images on the web

Euripides G. M. Petrakis, Epimenides Voutsakis, Evangelos E. Milios
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
This work shows that it is possible to exploit text and image content characteristics of logo and trademark images in Web pages for enhancing the performance of retrievals on the Web.  ...  PicASHOW exploits this idea in retrieval of important images on the Web using link information alone.  ...  Acknowledgements This work was supported by project PYTHAGORAS of the Greek Secretariat for Research and Technology.  ... 
doi:10.1145/1282280.1282358 dblp:conf/civr/PetrakisVM07 fatcat:c3lcpbzvdzcjrhxcqcc4z6d22m

Practice and challenges in trademark image retrieval

Jan Schietse, John P. Eakins, Remco C. Veltkamp
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
In this paper, we outline some of the main challenges facing trademark searchers today, and discuss the extent to which current automated systems are meeting those challenges.  ...  CIVR'07, July 9-11, 2007 Trademark Image Retrieval One of the major issues in the Intellectual Property field is trademark infringement.  ...  Example of four figurative images judged by professional trademark examiners to be perceptually similar. , Amsterdam, The Netherlands. Copyright 2007 ACM 978-1-59593-733-9/07/0007 ...$5.00.  ... 
doi:10.1145/1282280.1282355 dblp:conf/civr/SchietseEV07 fatcat:62ngiemq55gv7igb3xrgktve2e
« Previous Showing results 1 — 15 out of 18 results