Search For:

Displaying 1-20 out of 20 total
Faceted topic retrieval of news video using joint topic modeling of visual features and speech transcripts
Found in: Multimedia and Expo, IEEE International Conference on
By Kong-Wah Wan, Ah-Hwee Tan, Joo-Hwee Lim, Liang-Tien Chia
Issue Date:July 2010
pp. 843-848
Because of the inherent ambiguity in user queries, an important task of modern retrieval systems is faceted topic retrieval (FTR), which relates to the goal of returning diverse or novel information elucidating the wide range of topics or facets of the que...
A Collection-Oriented Metadata Framework for Digital Images
Found in: Multimedia and Expo, IEEE International Conference on
By William Ku, Mohan Kankanhalli, Joo-hwee Lim
Issue Date:July 2006
pp. 761-764
A digital photo can
Home Photo Content Modeling for Personalized Event-Based Retrieval
Found in: IEEE Multimedia
By Joo-Hwee Lim, Qi Tian, Philippe Mulhem
Issue Date:October 2003
pp. 28-37
<p>With rapid advances in sensor, storage, processor, and communication technologies, consumers can now store large digital photo collections. Consumers need effective and efficient tools to organize and access photos in a semantically meaningful way...
A Recursive and Model-Constrained Region Splitting Algorithm for Cell Clump Decomposition
Found in: Pattern Recognition, International Conference on
By Wei Xiong, Sim-Heng Ong, Joo-Hwee Lim
Issue Date:August 2010
pp. 4416-4419
Decomposition of cells in clumps is a difficult segmentation task requiring region splitting techniques. Techniques that do not employ prior shape constraints usually fail to achieve accurate segmentation. Those using shape constraints are unable to cope w...
Learning from an ensemble of Receptive Fields
Found in: Cognitive Informatics, IEEE International Conference on
By Hanlin Goh,Joo Hwee Lim,Chai Quek
Issue Date:June 2009
pp. 86-93
In this paper, we construct a neural-inspired computational model based on the representational capabilities of receptive fields. The proposed model, known as Shape Encoding Receptive Fields (SERF), is able to perform fast and accurate data classification ...
Similarity Learning for Nearest Neighbor Classification
Found in: Data Mining, IEEE International Conference on
By Ali Mustafa Qamar, Eric Gaussier, Jean-Pierre Chevallet, Joo Hwee Lim
Issue Date:December 2008
pp. 983-988
In this paper, we propose an algorithm for learning a general class of similarity measures for kNN classification. This class encompasses, among others, the standard cosine measure, as well as the Dice and Jaccard coefficients. The algorithm we propose is ...
Boosting descriptors condensed from video sequences for place recognition
Found in: Computer Vision and Pattern Recognition Workshop
By Tat-Jun Chin, Hanlin Goh, Joo-Hwee Lim
Issue Date:June 2008
pp. 1-8
We investigate the task of efficiently training classifiers to build a robust place recognition system. We advocate an approach which involves densely capturing the facades of buildings and landmarks with video recordings to greedily accumulate as much vis...
An ensemble classifier learning approach to ROC optimization
Found in: Pattern Recognition, International Conference on
By Sheng Gao, Chin-Hui Lee, Joo Hwee Lim
Issue Date:August 2006
pp. 679-682
An ensemble learning framework is proposed to optimize the receiver operating characteristic (ROC) curve corresponding to a given classifier. The proposed ensemble maximal figure-ofmerit (E-MFoM) learning framework meets four key requirements desirable for...
Scene Identification using Discriminative Patterns
Found in: Pattern Recognition, International Conference on
By Joo-Hwee Lim, Jean-Pierre Chevallet, Sheng Gao
Issue Date:August 2006
pp. 642-645
With the proliferation of camera phones, new information retrieval applications will emerge. The image of a scene captured by a camera phone can be a query to a remote server to identify the scene and return relevant information. But unconstrained scene id...
Towards Automatic Mobile Blogging
Found in: Multimedia and Expo, IEEE International Conference on
By Pujianto Cemerlang, Joo-hwee Lim, Yilun You, Jun Zhang, Jean-pierre Chevallet
Issue Date:July 2006
pp. 2033-2036
Weblog (usually shortened as blog) has gained its popularity lately. There are about 70,000 new blogs a day and about 29,100 blog updates an hour. As an emerging blogging phenomenon, with the proliferation of camera phones, mobile bloggers can write their ...
Cascading Classifiers for Consumer Image Indexing
Found in: Pattern Recognition, International Conference on
By Joo-Hwee Lim, Jesse S. Jin
Issue Date:August 2004
pp. 897-900
In this paper, we propose a cascading framework of binary classifiers to extract and combine intra-image and inter-class semantics for image indexing and retrieval. Support vector detectors are first trained on semantic support regions without image segmen...
Visual Keywords Labeling in Soccer Video
Found in: Pattern Recognition, International Conference on
By Yu-Lin Kang, Joo-Hwee Lim, Qi Tian, Mohan S. Kankanhalli, Chang-Sheng Xu
Issue Date:August 2004
pp. 850-853
In this paper, we propose a framework to label soccer video shots with pre-defined visual keywords to bridge the semantic gap between low-level features and semantic understanding. Based on these visual keywords, further structure analysis and event detect...
Event-based home photo retrieval
Found in: Multimedia and Expo, IEEE International Conference on
By Joo-Hwee Lim, P. Mulhem, Qi Tian
Issue Date:July 2003
pp. 33-36
With rapid advances in sensor, storage, processor, and communication technologies, consumers can now afford to create, store, process, and share large digital photo collections. With more and more digital photos accumulated, consumers need effective and ef...
Content-Based Summarization for Personal Image Library
Found in: Digital Libraries, Joint Conference on
By Joo-Hwee Lim, Jun Li, Philippe Mulhem, Qi Tian
Issue Date:May 2003
pp. 393
With the accumulation of consumer?s personal image library, the problem of managing, browsing, querying and presenting photos effectively and efficiently would become critical. We propose a framework for automatic organization of personal image libraries b...
Learning Similarity Matching in Multimedia Content-Based Retrieval
Found in: IEEE Transactions on Knowledge and Data Engineering
By Joo-Hwee Lim, Jian Kang Wu, Sumeet Singh, Desai Narasimhalu
Issue Date:September 2001
pp. 846-850
<p><b>Abstract</b>—Many multimedia content-based retrieval systems allow query formulation with user setting of relative importance of features (e.g., color, texture, shape, etc) to mimic the user's perception of similarity. However, the ...
Robust and Efficient Saliency Modeling from Image Co-Occurrence Histograms
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shijian Lu,Cheston Tan, Joo-Hwee Lim
Issue Date:January 2014
pp. 195-201
This paper presents a visual saliency modeling technique that is efficient and tolerant to the image scale variation. Different from existing approaches that rely on a large number of filters or complicated learning processes, the proposed technique comput...
Learning Visual Keywords for Content-Based Retrieval
Found in: Multimedia Computing and Systems, International Conference on
By Joo-Hwee Lim
Issue Date:June 1999
pp. 169
Today keyword-based text retrieval systems have enjoyed reasonable success in real usage. Despite the simplicity of the keyword metaphor, practical text search engines are able to handle huge volumes of free text documents. In image and video retrieval, se...
Symbolic photograph content-based retrieval
Found in: Proceedings of the eleventh international conference on Information and knowledge management (CIKM '02)
By Joo Hwee Lim, Philippe Mulhem
Issue Date:November 2002
pp. 94-101
Photograph retrieval systems face the difficulty to deal with the different ways to apprehend the content of images. We consider and demonstrate here the use of multiple index representations of photographs to achieve effective retrieval. The use of multip...
Explicit query formulation with visual keywords
Found in: Proceedings of the eighth ACM international conference on Multimedia (MULTIMEDIA '00)
By Joo-Hwee Lim
Issue Date:October 2000
pp. 407-412
This paper presents a novel framework called visual keywords for indexing and retrieving digital images. Visual keywords are flexible and intuitive visual prototypes with semantics. A new query method based on visual constraints allows direct and explicit ...
Learnable visual keywords for image classification
Found in: Proceedings of the fourth ACM conference on Digital libraries (DL '99)
By Joo-Hwee Lim
Issue Date:August 1999
pp. 139-145
This presentation focuses on the strategic design planning and vision creation process for the E-Quarium, the online complement to the Monterey Bay Aquarium. More than six months of informed investigation and analysis resulted in an ambitious redesign of t...