Search For:

Displaying 1-10 out of 10 total
Forward Basis Selection for Pursuing Sparse Representations over a Dictionary
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xiao-Tong Yuan, Shuicheng Yan
Issue Date:December 2013
pp. 3025-3036
The forward greedy selection algorithm of Frank and Wolfe has recently been applied with success to coordinate-wise sparse learning problems, characterized by a tradeoff between sparsity and accuracy. In this paper, we generalize this method to the setup o...
 
Multi-label visual classification with label exclusive context
Found in: Computer Vision, IEEE International Conference on
By Xiangyu Chen,Xiao-Tong Yuan,Qiang Chen,Shuicheng Yan,Tat-Seng Chua
Issue Date:November 2011
pp. 834-841
We introduce in this paper a novel approach to multi-label image classification which incorporates a new type of context -- label exclusive context -- with linear representation and classification. Given a set of exclusive label groups that describe the ne...
 
Agglomerative Mean-Shift Clustering
Found in: IEEE Transactions on Knowledge and Data Engineering
By Xiao-Tong Yuan,Bao-Gang Hu,Ran He
Issue Date:February 2012
pp. 209-219
Mean-Shift (MS) is a powerful nonparametric clustering method. Although good accuracy can be achieved, its computational cost is particularly expensive even on moderate data sets. In this paper, for the purpose of algorithmic speedup, we develop an agglome...
 
Visual classification with multi-task joint sparse representation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiao-Tong Yuan, Shuicheng Yan
Issue Date:June 2010
pp. 3493-3500
We address the problem of computing joint sparse representation of visual signal across multiple kernel-based representations. Such a problem arises naturally in supervised visual recognition applications where one aims to reconstruct a test sample with mu...
 
Stochastic gradient kernel density mode-seeking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiao-Tong Yuan, S.Z. Li
Issue Date:June 2009
pp. 1926-1931
As a well known fixed-point iteration algorithm for kernel density mode-seeking, mean-shift has attracted wide attention in pattern recognition field. To date, mean-shift algorithm is typically implemented in a batch way with the entire data set known at o...
 
Video accessibility enhancement for hearing-impaired users
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Jianguo Jiang, Meng Wang, Meng Wang, Mengdi Xu, Mengdi Xu, Richang Hong, Richang Hong, Shuicheng Yan, Shuicheng Yan, Tat-Seng Chua, Tat-Seng Chua, Xiao-Tong Yuan, Xiao-Tong Yuan
Issue Date:October 2011
pp. 1-19
There are more than 66 million people suffering from hearing impairment and this disability brings them difficulty in video content understanding due to the loss of audio information. If the scripts are available, captioning technology can help them in a c...
     
iComics: automatic conversion of movie into comics
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Guangda Li, Meng Wang, Richang Hong, Shuicheng Yan, Tat-Seng Chua, Xiao-Tong Yuan
Issue Date:October 2010
pp. 1599-1602
This demonstration presents a system, named iComics, for automatic conversion of movie into comics. We design three components to realize the system: script-face mapping, key-scene extraction, and cartoonization. Script-face mapping utilizes face recogniti...
     
Movie2Comics: a feast of multimedia artwork
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Meng Wang, Mengdi Xu, Richang Hong, Shuicheng Yan, Tat-Seng Chua, Xiao-Tong Yuan
Issue Date:October 2010
pp. 611-614
As a type of artwork, comics are prevalent and popular around the world. However, although there are several assistive software and tools available, the creation of comics is still a tedious and labor intensive process. This paper proposes a scheme that is...
     
Robust feature extraction via information theoretic learning
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By Bao-Gang Hu, Xiao-Tong Yuan
Issue Date:June 2009
pp. 1-8
In this paper, we present a robust feature extraction framework based on information-theoretic learning. Its formulated objective aims at simultaneously maximizing the Renyi's quadratic information potential of features and the Renyi's cross information po...
     
A set theoretical method for video synopsis
Found in: Proceeding of the 1st ACM international conference on Multimedia information retrieval (MIR '08)
By Bin Li, Min Xu, Shi-Ming Xiang, Stan Z. Li, Xiao-Tong Yuan
Issue Date:October 2008
pp. 1-1
A synopsis video presents a condensed video activities occurring during different periods, based on moving objects extracted in the spatial-temporal domain. How to place different object tubes with least collision in limited video length is crucial to syno...
     
 1