Search For:

Displaying 1-4 out of 4 total
Silicon Photonic Interconnects for Large-Scale Computer Systems
Found in: IEEE Micro
By Ron Ho,Philip Amberg,Eric Chang,Pranay Koka,Jon Lexau,Guoliang Li,Frankie Y. Liu,Herb Schwetman,Ivan Shubin,Hiren D. Thacker,Xuezhe Zheng,John E. Cunningham,Ashok V. Krishnamoorthy
Issue Date:January 2013
pp. 68-78
Optical interconnects play an integral role in large-scale digital computing, switching, and routing systems. The authors describe a path toward future many-chip modules based on silicon photonic interposers that stitch together tens of chips in a dense an...
Unsupervised object class discovery via saliency-guided multiple class learning
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jun-Yan Zhu, Jiajun Wu, Yichen Wei,Eric Chang, Zhuowen Tu
Issue Date:June 2012
pp. 3218-3225
Discovering object classes from images in a fully unsupervised way is an intrinsically ambiguous task; saliency detection approaches however ease the burden on unsupervised learning. We develop an algorithm for simultaneously localizing objects and discove...
Red Opal: product-feature scoring from reviews
Found in: Proceedings of the 8th ACM conference on Electronic commerce (EC '07)
By Christopher Scaffidi, Chun Jin, Eric Chang, Herman Ng, Kevin Bierhoff, Mikhael Felker
Issue Date:June 2007
pp. 182-191
Online shoppers are generally highly task-driven: they have a certain goal in mind, and they are looking for a product with features that are consistent with that goal. Unfortunately, finding a product with specific features is extremely time-consuming usi...
Speech-driven cartoon animation with emotions
Found in: Proceedings of the ninth ACM international conference on Multimedia (MULTIMEDIA '01)
By Eric Chang, Feng Yu, Heung-Yeung Shum, Yan Li, Ying-Qing Xu
Issue Date:September 2001
pp. 365-371
In this paper, we present a cartoon face animation system for multimedia HCI applications. We animate face cartoons not only from input speech, but also based on emotions derived from speech signal. Using a corpus of over 700 utterances from different spea...