Search For:

Displaying 1-19 out of 19 total
A support vector hierarchical method for multi-class classification and rejection
Found in: Neural Networks, IEEE - INNS - ENNS International Joint Conference on
By Yu-Chiang Frank Wang, David Casasent
Issue Date:June 2009
pp. 3281-3288
We address both recognition of true classes and rejection of unseen false classes inputs, as occurs in many realistic pattern recognition problems. we advance a hierarchical binary-decision classifier and produce analog outputs at each node, with yields a ...
Cluster Computing and Grid 2005 Works in Progress
Found in: IEEE Distributed Systems Online
By Frank Wang, Na Helian, Sining Wu, Yuhui Deng, Ke Zhou, Yike Guo, Steve Thompson, Ian Johnson, Dave Milward, Robert Maddock, Benjamin Khoo
Issue Date:September 2005
pp. 2
The first in a two-part series of works-in-progress articles from the Cluster Computing and Grid 2005 conference held in Cardiff, UK.
An Efficient Lyapunov Equation-Based Approach for Generating Reduced-Order Models of Interconnect
Found in: Design Automation Conference
By Jing-Rebecca Li, Frank Wang, Jacob White
Issue Date:June 1999
pp. 1-6
In this paper we present a new algorithm for computing reduced-order models of interconnect which utilizes the dominant controllable subspace of the system. The dominant controllable modes are computed via a new iterative Lyapunov equation solver, Vector A...
Automatic annotation of Web videos
Found in: Multimedia and Expo, IEEE International Conference on
By Shih-Wei Sun, Yu-Chiang Frank Wang, Yao-Ling Hung, Chia-Ling Chang, Kuan-Chieh Chen,Shih-Sian Cheng,Hsin-Min Wang, Hong-Yuan Mark Liao
Issue Date:July 2011
pp. 1-6
Most Web videos are captured in uncontrolled environments (e.g. videos captured by freely-moving cameras with low resolution); this makes automatic video annotation very difficult. To address this problem, we present a robust moving foreground object detec...
Learning Dense Optical-Flow Trajectory Patterns for Video Object Extraction
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Wang-Chou Lu, Yu-Chiang Frank Wang, Chu-Song Chen
Issue Date:September 2010
pp. 315-322
We proposes an unsupervised method to address videoobject extraction (VOE) in uncontrolled videos, i.e. videoscaptured by low-resolution and freely moving cameras. Weadvocate the use of dense optical-flow trajectories (DOTs),which are obtained by propagati...
Simultaneous Object Recognition and Localization in Image Collections
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Shao-Chuan Wang, Yu-Chiang Frank Wang
Issue Date:September 2010
pp. 497-504
This papers presents a weakly supervised method to simultaneouslyaddress object localization and recognitionproblems. Unlike prior work using exhaustive search methodssuch as sliding windows, we propose to learn categoryand image-specific visual words in i...
Segmentation-free object localization in image collections
Found in: Multimedia and Expo, IEEE International Conference on
By Shao-Chuan Wang, Yu-Chiang Frank Wang
Issue Date:July 2010
pp. 1546-1551
We propose a novel method to address object localization in a weakly supervised framework. Unlike prior work using exhaustive search methods such as sliding windows, we advocate the use of visual attention maps which are constructed by class-specific visua...
Coupled Dictionary and Feature Space Learning with Applications to Cross-Domain Image Synthesis and Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By De-An Huang,Yu-Chiang Frank Wang
Issue Date:December 2013
pp. 2496-2503
Cross-domain image synthesis and recognition are typically considered as two distinct tasks in the areas of computer vision and pattern recognition. Therefore, it is not clear whether approaches addressing one task can be easily generalized or extended for...
Anomaly Detection via Online Oversampling Principal Component Analysis
Found in: IEEE Transactions on Knowledge and Data Engineering
By Yuh-Jye Lee,Yi-Ren Yeh,Yu-Chiang Frank Wang
Issue Date:July 2013
pp. 1460-1470
Anomaly detection has been an important research topic in data mining and machine learning. Many real-world applications such as intrusion or credit card fraud detection require an effective and efficient framework to identify deviated data instances. Howe...
Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Min-Chun Yang,De-An Huang,Chih-Yun Tsai,Yu-Chiang Frank Wang
Issue Date:July 2012
pp. 574-579
We present a self-learning approach for single image super-resolution (SR), with the ability to preserve high frequency components such as edges in resulting high resolution (HR) images. Given a low-resolution (LR) input image, we construct its image pyram...
Context-Aware Single Image Rain Removal
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By De-An Huang,Li-Wei Kang,Min-Chun Yang,Chia-Wen Lin,Yu-Chiang Frank Wang
Issue Date:July 2012
pp. 164-169
Rain removal from a single image is one of the challenging image denoising problems. In this paper, we present a learning-based framework for single image rain removal, which focuses on the learning of context information from an input image, and thus the ...
Automatic object extraction in single-concept videos
Found in: Multimedia and Expo, IEEE International Conference on
By Kuo-Chin Lien,Yu-Chiang Frank Wang
Issue Date:July 2011
pp. 1-6
We propose a motion-driven video object extraction (VOE) method, which is able to model and segment foreground objects in single-concept videos, i.e. videos which have only one object category of interest but may have multiple object instances with pose, s...
Monte Carlo-Based Approach for Simulating Nanostructured Catalytic and Electrocatalytic Systems
Found in: Computing in Science and Engineering
By Venkatasubramanian Viswanathan,Frank Wang,Heinz Pitsch
Issue Date:March 2012
pp. 60-69
This geometry-generation method within a Monte Carlo-based approach enables the simulation of kinetics on nanostructured catalytic and electrocatalytic systems relevant for industrial applications. The method is applicable to realistic catalyst geometries,...
Implementing and Evaluating Security Controls for an Object-Based Storage System
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Zhongying Niu, Ke Zhou, Dan Feng, Hong Jiang, Frank Wang, Hua Chai, Wei Xiao, Chunhua Li
Issue Date:September 2007
pp. 87-99
This paper presents the implementation and performance evaluation of a real, secure object-based storage system compliant to the T10 OSD standard. In contrast to previous work, our system implements the entire three security methods of the OSD security pro...
A Block-level Security based on Hierarchical Logical Volume of Fibre Channel RAID
Found in: Embedded Software and Systems, Second International Conference on
By Ke Zhou, Dan Feng, Frank Wang, Zhan Shi
Issue Date:December 2005
pp. 574-577
Block-level security provides the lowest level security for storage devices. In this paper, we propose a block-level security based on hierarchical logical volume of FC RAID. Using the hierarchical logical volume, a group of physical disks can be mapped to...
StegoTorus: a camouflage proxy for the Tor anonymity system
Found in: Proceedings of the 2012 ACM conference on Computer and communications security (CCS '12)
By Dan Boneh, Frank Wang, Jeffrey Wang, Linda Briesemeister, Steven Cheung, Vinod Yegneswaran, Zachary Weinberg
Issue Date:October 2012
pp. 109-120
Internet censorship by governments is an increasingly common practice worldwide. Internet users and censors are locked in an arms race: as users find ways to evade censorship schemes, the censors develop countermeasures for the evasion tactics. One of the ...
With one look: robust face recognition using single sample per person
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By De-An Huang, Yu-Chiang Frank Wang
Issue Date:October 2013
pp. 601-604
In this paper, we address the problem of robust face recognition using single sample per person. Given only one training image per subject of interest, our proposed method is able to recognize query images with illumination or expression changes, or even t...
Exploring self-similarities of bag-of-features for image classification
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Chih-Fan Chen, Yu-Chiang Frank Wang
Issue Date:November 2011
pp. 1421-1424
The use of bag-of-features (BOF) models has been a popular technique for image classification and retrieval. In order to better represent and discriminate images from different classes, we advance BOF and explore the self-similarities of visual words for i...
An efficient Lyapunov equation-based approach for generating reduced-order models of interconnect
Found in: Proceedings of the 36th ACM/IEEE conference on Design automation conference (DAC '99)
By Frank Wang, Jacob K. White, Jing-Rebecca Li
Issue Date:June 1999
pp. 1-6
We present the SpecSyn system-level design environment supp orting the sp ecify-explor e-refine (SER) designparadigm. This thr ee-step appr oach includes precise specification of system functionality, rapid explor ation of numerous system-level design opti...