Author image not provided
 Wen Wu

Authors:
Add personal information
  Affiliation history
Bibliometrics: publication history
Average citations per article8.77
Citation Count114
Publication count13
Publication years2003-2012
Available for download8
Average downloads per article631.50
Downloads (cumulative)5,052
Downloads (12 Months)173
Downloads (6 Weeks)22
SEARCH
ROLE
Arrow RightAuthor only


AUTHOR'S COLLEAGUES
See all colleagues of this author

SUBJECT AREAS
See all subject areas




BOOKMARK & SHARE


13 results found Export Results: bibtexendnoteacmrefcsv

Result 1 – 13 of 13
Sort by:

1
January 2012
Bibliometrics:
Citation Count: 0

Most existing Global Positioning System (GPS)-based vehicle navigation systems (also termed route guidance systems) utilize distance within their turn-by-turn navigation directions. For example, a system might give a voice instruction like "turn left in 0.2 mile". However, human drivers usually use landmarks to help their navigation. Some previous research has ...

2
November 2009 ICIP'09: Proceedings of the 16th IEEE international conference on Image processing
Publisher: IEEE Press
Bibliometrics:
Citation Count: 18

We introduce the first visual dataset of fast foods with a total of 4,545 still images, 606 stereo pairs, 303 360° videos for structure from motion, and 27 privacy-preserving videos of eating events of volunteers. This work was motivated by research on fast food recognition for dietary assessment. The data ...
Keywords: food image dataset, object recognition

3 published by ACM
October 2009 AMC '09: Proceedings of the 2009 workshop on Ambient media computing
Publisher: ACM
Bibliometrics:
Citation Count: 5
Downloads (6 Weeks): 6,   Downloads (12 Months): 64,   Downloads (Overall): 629

Full text available: PdfPdf
In driving applications, a full windshield head-up display (FWD) system provides a flexible way for delivering driving related information. The projected information (text, image and graphics) is distorted on the car windshield because of its non-planar surface, the FWD projector's position and the viewing angle of the driver. In this ...
Keywords: full-windshield head-up display, landmark-based car navigation, automatic windshield distortion correction, street landmark detection

4
June 2009 ICME'09: Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Publisher: IEEE Press
Bibliometrics:
Citation Count: 10

Accurate and passive acquisition of dietary data from patients is essential for a better understanding of the etiology of obesity and development of effective weight management programs. Self-reporting is currently the main method for such data acquisition. However, studies have shown that data obtained by self-reporting seriously underestimate food intake ...
Keywords: calorie estimation, fast food recognition

5
June 2009 IEEE Transactions on Image Processing: Volume 18 Issue 6, June 2009
Publisher: IEEE Press
Bibliometrics:
Citation Count: 0

Labeling objects in images plays a crucial role in many visual learning and recognition applications that need training data, such as image retrieval, object detection and recognition. Manually creating object labels in images is time consuming and, thus, becomes impossible for labeling a large image dataset. In this paper, we ...
Keywords: Gaussian fields, labeling objects, superpixels, quadtree, SmartLabel, harmonic functions

6 published by ACM
October 2008 MM '08: Proceedings of the 16th ACM international conference on Multimedia
Publisher: ACM
Bibliometrics:
Citation Count: 4
Downloads (6 Weeks): 0,   Downloads (12 Months): 4,   Downloads (Overall): 308

Full text available: PDFPDF
An object can be a basic unit for multimedia content analysis. Besides similarity among common objects, each object has its own unique characteristics which we cannot find in other surrounding objects in multimedia data. We call such unique characteristics object fingerprints. In this paper, we propose a novel approach to ...
Keywords: object fingerprint, street landmark localization

7 published by ACM
July 2008 CIVR '08: Proceedings of the 2008 international conference on Content-based image and video retrieval
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 2,   Downloads (12 Months): 9,   Downloads (Overall): 282

Full text available: PDFPDF
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a large amount of unlabeled data as well as a small amount of labeled data to boost classification performance. Our approach proposes to formulate the ...
Keywords: object classification, semi-supervised learning

8 published by ACM
October 2006 MM '06: Proceedings of the 14th ACM international conference on Multimedia
Publisher: ACM
Bibliometrics:
Citation Count: 5
Downloads (6 Weeks): 1,   Downloads (12 Months): 11,   Downloads (Overall): 323

Full text available: PDFPDF
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detection and recognition. Manually creating labels in images is not only time-consuming but also subject to human labeling errors, and eventually, becomes impossible for a ...
Keywords: gaussian random field, harmonic energy minimization, object labeling, semi-supervised learning

9 published by ACM
April 2006 ACM Transactions on Information Systems (TOIS): Volume 24 Issue 2, April 2006
Publisher: ACM
Bibliometrics:
Citation Count: 9
Downloads (6 Weeks): 2,   Downloads (12 Months): 18,   Downloads (Overall): 841

Full text available: PDFPDF
We propose a maximal figure-of-merit (MFoM)-learning approach for robust classifier design, which directly optimizes performance metrics of interest for different target classifiers. The proposed approach, embedding the decision functions of classifiers and performance metrics into an overall training objective, learns the parameters of classifiers in a decision-feedback manner to effectively ...
Keywords: Text categorization, generalized probabilistic descent method, information retrieval, decision tree, latent semantic indexing, maximal figure-of-merit

10
December 2005 IEEE Transactions on Intelligent Transportation Systems: Volume 6 Issue 4, December 2005
Publisher: IEEE Press
Bibliometrics:
Citation Count: 13

A fast and robust framework for incrementally detecting text on road signs from video is presented in this paper. This new framework makes two main contributions. 1) The framework applies a divide-and-conquer strategy to decompose the original task into two subtasks, that is, the localization of road signs and the ...
Keywords: Object detection from video, road sign detection, text detection, vehicle navigation

11 published by ACM
October 2004 MULTIMEDIA '04: Proceedings of the 12th annual ACM international conference on Multimedia
Publisher: ACM
Bibliometrics:
Citation Count: 8
Downloads (6 Weeks): 6,   Downloads (12 Months): 18,   Downloads (Overall): 674

Full text available: PDFPDF
This paper proposes a fast and robust framework for incrementally detecting text on road signs from natural scene video. The new framework makes two main contributions. First, the framework applies a Divide-and-Conquer strategy to decompose the original task into two sub-tasks, that is, localization of road signs and detection of ...
Keywords: driving assistant system, incremental text detection, natural scene video, road sign

12 published by ACM
July 2004 ICML '04: Proceedings of the twenty-first international conference on Machine learning
Publisher: ACM
Bibliometrics:
Citation Count: 23
Downloads (6 Weeks): 4,   Downloads (12 Months): 29,   Downloads (Overall): 788

Full text available: PDFPDF
We propose a multiclass (MC) classification approach to text categorization (TC). To fully take advantage of both positive and negative training examples, a maximal figure-of-merit (MFoM) learning algorithm is introduced to train high performance MC classifiers. In contrast to conventional binary classification, the proposed MC scheme assigns a uniform score ...

13 published by ACM
July 2003 SIGIR '03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Publisher: ACM
Bibliometrics:
Citation Count: 15
Downloads (6 Weeks): 1,   Downloads (12 Months): 20,   Downloads (Overall): 1,207

Full text available: PDFPDF
A novel maximal figure-of-merit (MFoM) learning approach to text categorization is proposed. Different from the conventional techniques, the proposed MFoM method attempts to integrate any performance metric of interest (e.g. accuracy, recall, precision, or F1 measure) into the design of any classifier. The corresponding classifier parameters are learned by optimizing ...
Keywords: decision tree, latent semantic indexing, support vector machines, maximal figure-of-merit, text categorization, generalized probabilistic descent method



The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2018 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us