Multimedia Technologies for Landmark-Based Vehicle Navigation
Wen Wu
Ph.D. thesis, CMU-LTI-09-014, Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Nov 2009.
[Abstract][PDF]

A Maximal Figure-of-Merit Learning Approach to Text Categorization
Wen Wu
Master's degree thesis, School of Computing, National University of Singapore, Dec 2002.

Dissolve Detection in a MPEG Compressed Video Sequence
Wen Wu
Bachelor degree thesis, Department of Computer Science and Technology, Tsinghua University, Jun 2001.

Intelligent Multimedia Vision Systems for Vehicle Navigation
Wen Wu, Jie Yang and Xilin Chen.
Book chapter, submitted, 2009. [PDF]

Semi-Automatically Labeling Objects in Images
Wen Wu and Jie Yang.
In IEEE Transactions on Image Processing, Volume 18, Issue 6, Pages 1340-1349, Jun 2009. [PDF][data][[results]

A Maximal Figure-of-Merit (MFoM) Learning Approach to Robust Classifier Design for Text Categorization
Sheng Gao, Wen Wu, Chin-Hui Lee and Tat-Seng Chua.
In ACM Transactions on Information Systems (TOIS), Volume 24, Issue 2, Pages 1150-218, Apr 2006. [PDF]

Detection of Text on Road Signs from Video
Wen Wu, Xilin Chen and Jie Yang.
In IEEE Transactions on Intelligent Transportation Systems (ITS), Volume 6, Issue 4, Pages 378-3150, Dec 2005. [PDF] [results]

A Prototype of Landmark-Based Car Navigation Using a Full-Windshield Head-Up Display System
Wen Wu, Fabian Blaicher, Jie Yang, Thomas Seder and Dehua Cui.
To appear in ACM Intl. Conference on Multimedia - Workshop on Ambient Media Computing, 2009. [PDF][results] [results(short clip)]

PFID: Pittsburgh Fast-Food Image Dataset
Mei Chen, Kapil Dev Dhingra, Wen Wu, Lei Yang, Rahul Sukthankar and Jie Yang.
To appear in IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, November 7-11, 2009. [PDF] [dataset] [one video]

Fast Food Recognition from Videos of Eating for Calorie Estimation
Wen Wu and Jie Yang.
To appear in IEEE International Conference on Multimedia & Expo (ICME), New York City, USA, June 28 - July 3, 2009. Oral presentation. [PDF] [results]

Object Fingerprints for Content Analysis with Applications to Street Landmark Localization
Wen Wu and Jie Yang
In ACM International Conference on Multimedia (ACM MM), Vancouver, Canada, Oct 2008. Oral presentation. [PDF][data] [results]

Semi-Supervised Learning of Object Categories from Paired Local Features
Wen Wu and Jie Yang
In ACM International Conference on Image and Video Retrieval (CIVR), Niagara Falls, Canada, Jul 2008. [PDF]

Discovering Leadership Roles in Email Workgroups
Vitor R. Carvalho, Wen Wu and William W. Cohen
In 4th Conference on Email and Anti-Spam (CEAS), Mountain View, USA, Aug 2007. Oral presentation. [PDF]

SmartLabel: An Object Labeling Tool Using Iterated Harmonic Energy Minimization
Wen Wu and Jie Yang
In ACM International Conference on Multimedia (ACM MM), Santa Barbara, USA, Oct 2006. Oral presentation. [PDF][data][Harmonic function code, from Xiaojin Zhu]

A Multimedia System for Route Sharing and Video-based Navigation
Wen Wu, Jie Yang and Jing Zhang
In IEEE International Conference on Multimedia & Expo (ICME), Toronto, Canada, Jul 2006. Oral presentation. [PDF] [results]

Integrating Co-training and Recognition for Text Detection
Wen Wu, Datong Chen and Jie Yang.
In IEEE International Conference on Multimedia & Expo (ICME), Amsterdam, The Netherlands, Jul 2005. [PDF]

Incremental Detection of Text on Road Signs from Video with Application to a Driving Assistant System
Wen Wu, Xilin Chen and Jie Yang.
In ACM International Conference on Multimedia (ACM MM), New York City, USA, Oct 2004. Oral presentation. [PDF]

An MFoM Learning Approach to Robust Multiclass Multi-Label Text Categorization
Sheng Gao, Wen Wu, Chin-Hui Lee and Tat-Seng Chua.
In 21st International Conference on Machine Learning (ICML), Banff, Canada, Jul 2004. Oral presentation. [PDF]

A Maximal-Figure-of-Merit Learning Approach to Text Categorization
Sheng Gao, Wen Wu, Chin-Hui Lee and Tat-Seng Chua.
In 26th Annual International ACM SIGIR Conference, Toronto, Canada, Jul 2003. Oral presentation. [PDF]