pubs.bib
@article{yang10:_detec_commun_their_evolut_dynam_social_networ,
author = {Tianbao Yang and Yun Chi and Shenghuo Zhu and Yihong
Gong and Rong Jin},
title = {Detecting Communities and Their Evolutions in
Dynamic Social Networks -- A {Bayesian} Approach},
journal = {Machine Learning},
year = 2010,
note = {to appear}
}
@article{wang10:_integ_docum_clust_multi_docum_summar,
author = {Dingding Wang and Shenghuo Zhu and Tao Li and Yun Chi and
Yihong Gong},
title = {Integrating Document Clustering and Multi-Document
Summarization},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = 2010,
note = {to appear}
}
@inproceedings{chi10:_facet,
author = {Yun Chi and Shenghuo Zhu},
title = {{FacetCube}: A Framework of Incorporating Prior
Knowledge into Non-negative Tensor Factorization},
booktitle = {CIKM '10: Proceeding of the 19th ACM conference on
Information and knowledge management},
year = 2010,
note = {to appear}
}
@inproceedings{guo10:_laten_topic_model_linked_docum,
author = {Zhen Guo and Shenghuo Zhu and Yun Chi and Zhongfei
Zhang and Yihong Gong},
title = {A Latent Topic Model for Linked Documents },
booktitle = {ICPR '10: 20th International Conference on Pattern
Recognition},
year = 2010,
note = {to appear}
}
@inproceedings{guo10:_topic_model_linked_docum_updat_rules_estim,
author = {Zhen Guo and Shenghuo Zhu and Zhongfei Zhang and Yun
Chi and Yihong Gong},
title = {A Topic Model for Linked Documents and Update Rules
for its Estimation},
booktitle = {AAAI '10: the Twenty-Fourth AAAI Conference on
Artificial Intelligence},
year = 2010,
url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI10/paper/view/1872/2020}
}
@article{wang10,
author = {Dingding Wang and Tao Li and Shenghuo Zhu and Yihong
Gong},
title = {{iHelp}: An Intelligent Online Helpdesk System},
journal = {IEEE Transactions on Systems, Man, and
Cybernetics—Part B: Cybernetics},
year = {2010},
doi = {10.1109/TSMCB.2010.2049352},
issn = {1083-4419}
}
@article{zhu08:_featur_selec_for_gene_expres,
author = {Shenghuo Zhu and Dingding Wang and Kai Yu and Tao Li
and Yihong Gong},
title = { Feature Selection for Gene Expression using
Model-based Entropy},
journal = {IEEE/ACM Transactions on Computational Biology and
Bioinformatics},
year = 2010,
volume = 7,
number = 1,
doi = {10.1109/TCBB.2008.35},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
code = {http://www.nec-labs.com/~zsh/files/FS-1.19.zip},
data = {http://www.nec-labs.com/~zsh/genexp.html}
}
@inproceedings{yang10:_direc_networ_commun_detec,
author = {Tianbao Yang and Yun Chi and Shenghuo Zhu and Rong
Jin},
title = {Directed Network Community Detection: A Popularity
and Productivity Link Model },
booktitle = {SDM'10: Proceedings of the 2010 SIAM International
Conference On Data Mining},
year = 2010,
url = {http://www.siam.org/proceedings/datamining/2010/dm10_065_yangt.pdf}
}
@inproceedings{5360314,
title = {Knowledge Discovery from Citation Networks},
author = {Zhen Guo and Zhongfei Zhang and Shenghuo Zhu and Yun
Chi and Yihong Gong},
booktitle = {ICDM '09: Ninth IEEE International Conference on
Data Mining},
year = 2009,
doi = {10.1109/ICDM.2009.137},
pages = {800-805},
issn = {1550-4786}
}
@incollection{NIPS2009_lcc,
title = { Nonlinear Learning using Local Coordinate Coding },
author = {Kai Yu and Tong Zhang and Yihong Gong},
booktitle = {NIPS '09: Advances in Neural Information Processing Systems
22},
year = {2010},
preprint = {http://www.dbs.informatik.uni-muenchen.de/~yu_k/nips09_lcc.pdf}
}
@inproceedings{Yang:ICCV09,
author = {Ming Yang and Fengjun Lv and Wei Xu and Yihong Gong},
title = {Detection driven adaptive multi-cue integration for
multiple human tracking},
booktitle = {ICCV '09: IEEE Int'l Conf. on Computer Vision},
year = {2009},
pages = {1554--1561},
address = {Kyoto, Japan},
month = {Sept.29 - Oct.2,}
}
@inproceedings{Yang:VOEC09,
author = {Ming Yang and Fengjun Lv and Wei Xu and Kai Yu and
Yihong Gong},
title = {Human action detection by boosting efficient motion
features},
booktitle = {VOEC '09: IEEE Workshop on Video-oriented Object and
Event Classification in Conjunction with ICCV},
year = {2009},
address = {Kyoto, Japan},
month = {Sept 28}
}
@inproceedings{Zhu:ACMMM09,
author = {Guangyu Zhu and Ming Yang and Kai Yu and Wei Xu and
Yihong Gong},
title = {Detecting video events based on action recognition
in complex scenes using spatio-temporal descriptor},
booktitle = {MM '09: ACM. Int'l Conf. on Multimedia},
year = {2009},
pages = {165--174},
address = {Beijing, China},
month = {Oct 19 - 24,}
}
@article{wang09:_resol_enhan_learn_spars_assoc_image_patch,
title = {Resolution enhancement based on learning the sparse
association of image patches},
journal = {Pattern Recognition Letters},
volume = 31,
number = 1,
pages = {1 - 10},
year = 2010,
issn = {0167-8655},
doi = {10.1016/j.patrec.2009.09.004},
author = {Jinjun Wang and Shenghuo Zhu and Yihong Gong},
keywords = {Image super-resolution, Image representation,
Sparse-coding}
}
@inproceedings{1646276,
author = {Dingding Wang and Shenghuo Zhu and Tao Li and Yihong
Gong},
title = {Comparative document summarization via
discriminative sentence selection},
booktitle = {CIKM '09: Proceeding of the 18th ACM conference on
Information and knowledge management},
year = {2009},
isbn = {978-1-60558-512-3},
pages = {1963--1966},
location = {Hong Kong, China},
doi = {10.1145/1645953.1646276},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1639721,
author = {Sarah K. Taylor and Shenghuo Zhu and Yun Chi and Yi
Zhang},
title = {Ordering innovators and laggards for product
categorization and recommendation},
booktitle = {RecSys '09: Proceedings of the third ACM conference
on Recommender systems},
year = {2009},
isbn = {978-1-60558-435-5},
pages = {29--36},
location = {New York, New York, USA},
doi = {10.1145/1639714.1639721},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{wang09:_multi_docum_summar_using_senten,
author = {Dingding Wang and Shenghuo Zhu and Tao Li and Yihong
Gong },
title = {Multi-Document Summarization using Sentence-based
Topic Models},
booktitle = {ACL-IJCNLP '09: Joint conference of the 47th Annual
Meeting of the Association for Computational
Linguistics and the 4th International Joint
Conference on Natural Language Processing of the
Asian Federation of Natural Language Processing},
year = 2009,
url = {http://www.aclweb.org/anthology/P/P09/P09-2075.pdf}
}
@inproceedings{1571979,
author = {Kai Yu and Shenghuo Zhu and John Lafferty and Yihong
Gong},
title = {Fast Nonparametric Matrix Factorization for
Large-sale Collaborative Filtering },
booktitle = {SIGIR '09: Proceedings of the 32nd annual
international ACM SIGIR conference on Research and
development in information retrieval},
isbn = {978-1-60558-483-6},
pages = {211--218},
location = {Boston, MA, USA},
doi = {10.1145/1571941.1571979},
publisher = {ACM},
address = {New York, NY, USA},
year = 2009,
code = {mailto:kyu@sv.nec-labs.com}
}
@inproceedings{1572095,
author = {Zhen Guo and Shenghuo Zhu and Yun Chi and Zhongfei
Zhang and Yihong Gong},
title = {A Latent Topic Model for Linked Documents},
booktitle = {SIGIR '09: Proceedings of the 32nd annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = 2009,
isbn = {978-1-60558-483-6},
pages = {720--721},
location = {Boston, MA, USA},
doi = {10.1145/1571941.1572095},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{yang09:_bayes_framew_for_commun_detec,
author = {Tianbao Yang and Rong Jin and Yun Chi and Shenghuo
Zhu},
title = {A {Bayesian} Framework for Community Detection
Integrating Content and Link },
booktitle = {UAI '09: Proceedings of the 25th Conference on
Uncertainty in Artificial Intelligence},
year = 2009,
url = {http://www.cs.mcgill.ca/~uai2009/papers/UAI2009_0069_bbacda16c2951fd1d73e591f45141a67.pdf}
}
@inproceedings{1553525,
author = {Yu, Kai and Lafferty, John and Zhu, Shenghuo and
Gong, Yihong},
title = {Large-scale collaborative prediction using a
nonparametric random effects model},
booktitle = {ICML '09: Proceedings of the 26th Annual
International Conference on Machine Learning},
year = {2009},
isbn = {978-1-60558-516-1},
pages = {1185--1192},
location = {Montreal, Quebec, Canada},
doi = {10.1145/1553374.1553525},
publisher = {ACM},
address = {New York, NY, USA},
code = {mailto:kyu@sv.nec-labs.com}
}
@inproceedings{1557120,
author = {Yang, Tianbao and Jin, Rong and Chi, Yun and Zhu,
Shenghuo},
title = {Combining link and content for community detection:
a discriminative approach},
booktitle = {KDD '09: Proceedings of the 15th ACM SIGKDD
international conference on Knowledge discovery and
data mining},
year = {2009},
isbn = {978-1-60558-495-9},
pages = {927--936},
location = {Paris, France},
publisher = {ACM},
address = {New York, NY, USA},
doi = {10.1145/1557019.1557120},
slides = {http://www.nec-labs.com/~zsh/kdd09-slides.pdf}
}
@inproceedings{5202645,
author = {Jinjun Wang and Shenghuo Zhu and Yihong Gong},
title = {Resolution-Invariant Image Representation for
Content-based Zooming},
booktitle = {ICME '09: IEEE International Conference on
Multimedia and Expo},
year = 2009,
month = {28 2009-July 3},
volume = {},
number = {},
pages = {918-921},
keywords = {image representation, image resolution2D image
interpolation algorithm, content-based zooming,
example-based resolution enhancement, image quality,
image upscaling task, multiresolution bases set,
resolution-invariant image representation},
doi = {10.1109/ICME.2009.5202645},
issn = {1945-7871}
}
@inproceedings{5206679,
author = {Jinjun Wang and Shenghuo Zhu and Yihong Gong},
title = {Resolution-Invariant Image Representation and Its
Applications},
booktitle = {CVPR'09: IEEE Conference on Computer Vision and
Pattern Recognition},
year = {2009},
month = {June},
volume = {},
number = {},
pages = {2512-2519},
abstract = {We present a resolution-invariant image
representation (RIIR) framework in this paper. The
RIIR framework includes the methods of building a
set of multi-resolution bases from training images,
estimating the optimal sparse resolution-invariant
representation of any image, and reconstructing the
missing patches of any resolution level. As the
proposed RIIR framework has many potential
resolution enhancement applications, we discuss
three novel image magnification applications in this
paper. In the first application, we apply the RIIR
framework to perform Multi-Scale Image Magnification
where we also introduced a training strategy to
built a compact RIIR set. In the second application,
the RIIR framework is extended to conduct Continuous
Image Scaling where a new base at any resolution
level can be generated using existing RIIR set on
the fly. In the third application, we further apply
the RIIR framework onto Content-Base Automatic
Zooming applications. The experimental results show
that in all these applications, our RIIR based
method outperforms existing methods in various
aspects.},
keywords = {image enhancement, image reconstruction, image
representation, image resolutioncontent-base
automatic zooming application, continuous image
scaling, image magnification application,
multiresolution base, multiscale image
magnification, patch reconstruction, resolution
enhancement application, resolution-invariant image
representation, training strategy},
doi = {10.1109/CVPRW.2009.5206679},
issn = {1063-6919}
}
@article{yun09:_iolap,
author = {Yun Chi and Shenghuo Zhu and Koji Hino and Yihong
Gong and Yi Zhang},
title = {{iOLAP}: A Framework for Analyzing the Internet,
Social Networks, and Other Networked Data},
journal = {IEEE Transactions on Multimedia},
year = 2009,
month = {Apr},
volume = {11},
number = {3},
pages = {372--382},
doi = {10.1109/TMM.2009.2012912}
}
@inproceedings{4761237,
title = {Temporal difference learning to detect unsafe system
states},
author = {Huazhong Ning and Wei Xu and Yue Zhou and Yihong
Gong and Huang, Thomas},
booktitle = {ICPR'08: The 19th International Conference on
Pattern Recognition},
year = {2008},
month = {Dec.},
abstract = {This paper proposes a general framework to detect
unsafe states of a system whose basic realtime
parameters are captured by multi-sensors. Our
approach is to learn a danger level function which
can be used to alert the users in advance of
dangerous situations. The main challenge to this
learning problem is the labelling issue, i.e., it is
difficult to assign an objective danger level at
each time step to the training data, except at the
collapse points where a penalty can be assigned and
at the successful ends where a certain reward can be
assigned. In this paper, we treat the danger level
as expected future reward (penalty is regarded as
negative reward) and use temporal difference (TD)
learning [2] to learn a function to approximate the
expected future reward. The TD learning obtains the
approximation by propagating the penalty/reward
observable at collapse points or successful ends to
the entire feature space following some
constraints. Our approach is applied to, but not
limited to, the application of monitoring of driving
safety and the experimental results demonstrate the
effectiveness of the approach.},
doi = {10.1109/ICPR.2008.4761237},
issn = {1051-4651}
}
@inproceedings{4587534,
title = {Discriminative learning of visual words for 3D human
pose estimation},
author = {Huazhong Ning and Wei Xu and Yihong Gong and Huang,
T.},
booktitle = {CVPR'08: IEEE Conference on Computer Vision and Pattern Recognition},
year = {2008},
month = {June},
abstract = {This paper addresses the problem of recovering 3D
human pose from a single monocular image, using a
discriminative bag-of-words approach. In previous
work, the visual words are learned by unsupervised
clustering algorithms. They capture the most common
patterns and are good features for coarse-grain
recognition tasks like object classification. But
for those tasks which deal with subtle differences
such as pose estimation, such representation may
lack the needed discriminative power. In this paper,
we propose to jointly learn the visual words and the
pose regressors in a supervised manner. More
specifically, we learn an individual distance metric
for each visual word to optimize the pose estimation
performance. The learned metrics rescale the visual
words to suppress unimportant dimensions such as
those corresponding to background. Another
contribution is that we design an appearance and
position context (APC) local descriptor that
achieves both selectivity and invariance while
requiring no background subtraction. We test our
approach on both a quasi-synthetic dataset and a
real dataset (HumanEva) to verify its
effectiveness. Our approach also achieves fast
computational speed thanks to the integral
histograms used in APC descriptor extraction and
fast inference of pose regressors.},
keywords = {image classification, pose estimation, unsupervised
learning3D human pose estimation, APC local
descriptor, coarse-grain recognition, discriminative
learning, integral histograms, object
classification, quasisynthetic dataset, single
monocular image, unsupervised clustering algorithms,
visual words},
doi = {10.1109/CVPR.2008.4587534},
issn = {1063-6919}
}
@inproceedings{4761904,
title = {Recognition of multiple drivers' emotional state},
author = {Jinjun Wang and Yihong Gong},
booktitle = {ICPR'08: The 19th International Conference on
Pattern Recognition},
year = {2008},
month = {Dec.},
abstract = {The paper attempted the recognition of multiple
drivers’ emotional state from physiological
signals. The major challenge of the research is due
to the severe inter-driver variation such that the
features of different emotional state are high
correlated, and it is found that simple
decorrelation method cannot normalize the features
well to achieve acceptable classification
accuracy. Hence, in this paper, we propose to apply
a latent variable to represent the hidden attribute
of individual driver and use statistical
training. In addition, we applied temporal
constraints for the inference process to improve the
recognition accuracy. Experimental results show that
the proposed method outperform existing algorithms
used for emotional state recognition.},
doi = {10.1109/ICPR.2008.4761904},
issn = {1051-4651}
}
@article{liu08:_visual_qualit_optim_super_resol,
author = {Feng Liu and Jinjun Wang and Shenghuo Zhu and
Michael Gleicher and Yihong Gong},
title = {Visual-Quality Optimizing Super Resolution},
journal = {Computer Graphics Forum},
year = 2009,
month = {Feb},
volume = 28,
number = 1,
pages = {127--140},
publisher = {The Eurographics Association and Blackwell
Publishing Ltd.},
doi = {10.1111/j.1467-8659.2008.01305.x}
}
@inproceedings{lin09:_learn_spars_markov_networ_struc,
author = {Yuanqing Lin and Shenghuo Zhu and Daniel Lee and Ben
Taskar},
title = {Learning Sparse Markov Network Structure via
Ensemble-of-Trees Models},
booktitle = {AISTAT'09: The Proceedings of the Twelfth
International Conference on Artificial Intelligence
and Statistics},
year = 2009,
volume = {5},
pages = {360--367},
url = {http://jmlr.csail.mit.edu/proceedings/papers/v5/lin09a/lin09a.pdf}
}
@article{1514891,
author = {Yu-Ru Lin and Yun Chi and Shenghuo Zhu and Hari
Sundaram and Belle L. Tseng},
title = {Analyzing communities and their evolutions in
dynamic social networks},
journal = {ACM Trans. Knowl. Discov. Data},
volume = {3},
number = {2},
year = {2009},
issn = {1556-4681},
pages = {1--31},
doi = {10.1145/1514888.1514891},
publisher = {ACM},
address = {New York, NY, USA}
}
@incollection{NIPS2008_0790,
title = {Deep Learning with Kernel Regularization for Visual
Recognition},
author = {Kai Yu and Wei Xu and Yihong Gong},
booktitle = {NIPS '08: Advances in Neural Information Processing Systems
21},
pages = {1889--1896},
year = {2009},
url = {http://books.nips.cc/papers/files/nips21/NIPS2008_0790.pdf}
}
@inproceedings{zhu08:_stoch_relat_model_for_large,
author = {Shenghuo Zhu and Kai Yu and Yihong Gong},
title = {Stochastic Relational Models for Large-scale Dyadic
Data using {MCMC}},
booktitle = {NIPS '08: Advances in Neural Information Processing
Systems 21},
publisher = {MIT Press},
address = {Cambridge, MA},
year = 2009,
url = {http://books.nips.cc/papers/files/nips21/NIPS2008_0664.pdf}
}
@inproceedings{1459467,
author = {Liu,, Feng and Wang,, Jinjun and Zhu,, Shenghuo and
Gleicher,, Michael and Gong,, Yihong},
title = {Noisy video super-resolution},
booktitle = {MM '08: Proceeding of the 16th ACM international
conference on Multimedia},
year = {2008},
isbn = {978-1-60558-303-7},
pages = {713--716},
location = {Vancouver, British Columbia, Canada},
doi = {10.1145/1459359.1459467},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1458206,
author = {Yun Chi and Shenghuo Zhu and Yihong Gong and Yi
Zhang},
title = {Probabilistic Polyadic Factorization and Its
Application to Personalized Recommendation},
booktitle = {CIKM '08: Proceedings of the 17th ACM Conference on
Information and Knowledge Management},
year = 2008,
pages = {941--950},
isbn = {978-1-59593-991-3},
location = {Napa Valley, California, USA},
doi = {10.1145/1458082.1458206},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1458319,
author = {Dingding Wang and Shenghuo Zhu and Yun Chi and Tao
Li},
title = {Integrating Clustering and Multi-Document
Summarization to Improve Document Understanding},
booktitle = {CIKM '08: Proceedings of the 17th ACM Conference on
Information and Knowledge Management},
isbn = {978-1-59593-991-3},
pages = {1435--1436},
location = {Napa Valley, California, USA},
year = 2008,
doi = {10.1145/1458082.1458319},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1453937,
author = {Shenghuo Zhu and Tao Li and Zhiyuan Chen and
Dingding Wang and Yihong Gong},
title = {Dynamic active probing of helpdesk databases},
booktitle = {VLDB '08: Proceedings of the 34th International
Conference on Very Large Data Bases},
year = {2008},
pages = {748--760},
doi = {10.1145/1453856.1453937},
publisher = {VLDB Endowment}
}
@inproceedings{1401967,
author = {Ka Cheung Sia and Junghoo Cho and Yun Chi and Belle
L. Tseng},
title = {Efficient computation of personal aggregate queries
on blogs},
booktitle = {KDD '08: Proceeding of the 14th ACM SIGKDD
international conference on Knowledge discovery and
data mining},
year = {2008},
isbn = {978-1-60558-193-4},
pages = {632--640},
location = {Las Vegas, Nevada, USA},
doi = {10.1145/1401890.1401967},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1390442,
author = {Kai Yu and Shenghuo Zhu and Wei Xu and Yihong Gong},
title = {Non-greedy active learning for text categorization
using convex ansductive experimental design},
booktitle = {SIGIR '08: Proceedings of the 31st annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = {2008},
isbn = {978-1-60558-164-4},
pages = {635--642},
location = {Singapore, Singapore},
doi = {10.1145/1390334.1390442},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1390387,
author = {Dingding Wang and Tao Li and Shenghuo Zhu and Chris
Ding},
title = {Multi-document summarization via sentence-level
semantic analysis and symmetric matrix
factorization},
booktitle = {SIGIR '08: Proceedings of the 31st annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = {2008},
isbn = {978-1-60558-164-4},
pages = {307--314},
location = {Singapore, Singapore},
doi = {10.1145/1390334.1390387},
publisher = {ACM},
address = {New York, NY, USA}
}
@article{1041083,
author = {Yihong Gong and Mei Han and Wei Hua and Wei Xu},
title = {Maximum entropy model-based baseball highlight
detection and classification},
journal = {Comput. Vis. Image Underst.},
volume = {96},
number = {2},
year = {2004},
issn = {1077-3142},
pages = {181--199},
doi = {10.1016/j.cviu.2004.02.002},
publisher = {Elsevier Science Inc.},
address = {New York, NY, USA}
}
@inproceedings{1043984,
author = {Yue Zhou and Wei Xu and Hai Tao and Yihong Gong},
title = {Background Segmentation Using Spatial-Temporal
Multi-Resolution MRF},
booktitle = {WACV-MOTION '05: Proceedings of the IEEE Workshop on
Motion and Video Computing (WACV/MOTION'05) - Volume
2},
year = {2005},
isbn = {0-7695-2271-8-2},
pages = {8--13},
doi = {10.1109/ACVMOT.2005.32},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA}
}
@inproceedings{1076082,
author = {Shenghuo Zhu and Xiang Ji and Wei Xu and Yihong
Gong},
title = {Multi-labelled classification using maximum entropy
method},
booktitle = {SIGIR '05: Proceedings of the 28th annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = {2005},
isbn = {1-59593-034-5},
pages = {274--281},
location = {Salvador, Brazil},
doi = {10.1145/1076034.1076082},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1081925,
author = {Xiaodan Song and Ching-Yung Lin and Belle L. Tseng
and Ming-Ting Sun},
title = {Modeling and predicting personal information
dissemination behavior},
booktitle = {KDD '05: Proceedings of the eleventh ACM SIGKDD
international conference on Knowledge discovery in
data mining},
year = {2005},
isbn = {1-59593-135-X},
pages = {479--488},
location = {Chicago, Illinois, USA},
doi = {10.1145/1081870.1081925},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1101338,
author = {Yi Wu and Edward Y. Chang and Belle L. Tseng},
title = {Multimodal metadata fusion using causal strength},
booktitle = {MULTIMEDIA '05: Proceedings of the 13th annual ACM
international conference on Multimedia},
year = {2005},
isbn = {1-59593-044-2},
pages = {872--881},
location = {Hilton, Singapore},
doi = {10.1145/1101149.1101338},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1148241,
author = {Xiang Ji and Wei Xu and Shenghuo Zhu},
title = {Document clustering with prior knowledge},
booktitle = {SIGIR '06: Proceedings of the 29th annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = {2006},
isbn = {1-59593-369-7},
pages = {405--412},
location = {Seattle, Washington, USA},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1148258,
author = {Xiaodan Song and Belle L. Tseng and Ching-Yung Lin
and Ming-Ting Sun},
title = {Personalized recommendation driven by information
flow},
booktitle = {SIGIR '06: Proceedings of the 29th annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = {2006},
isbn = {1-59593-369-7},
pages = {509--516},
location = {Seattle, Washington, USA},
doi = {10.1145/1148170.1148258},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1171839,
author = {Mei Han and Wei Xu and Yihong Gong},
title = {Video Foreground Segmentation Based on Sequential
Feature Clustering},
booktitle = {ICPR '06: Proceedings of the 18th International
Conference on Pattern Recognition},
year = {2006},
isbn = {0-7695-2521-0},
pages = {492--496},
doi = {10.1109/ICPR.2006.1170},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA}
}
@inproceedings{1172460,
author = {Dan Kong and Mei Han and Wei Xu and Hai Tao and
Yihong Gong},
title = {A Conditional Random Field Model for Video
Super-resolution},
booktitle = {ICPR '06: Proceedings of the 18th International
Conference on Pattern Recognition},
year = {2006},
isbn = {0-7695-2521-0},
pages = {619--622},
doi = {10.1109/ICPR.2006.56},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA}
}
@inproceedings{1180805,
author = {Mei Han and Wei Xu and Yihong Gong},
title = {Video object segmentation by motion-based sequential
feature clustering},
booktitle = {MULTIMEDIA '06: Proceedings of the 14th annual ACM
international conference on Multimedia},
year = {2006},
isbn = {1-59593-447-2},
pages = {773--782},
location = {Santa Barbara, CA, USA},
doi = {10.1145/1180639.1180805},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1183627,
author = {Arun Qamra and Belle Tseng and Edward Y. Chang},
title = {Mining blog stories using community-based and
temporal clustering},
booktitle = {CIKM '06: Proceedings of the 15th ACM international
conference on Information and knowledge management},
year = {2006},
isbn = {1-59593-433-2},
pages = {58--67},
location = {Arlington, Virginia, USA},
doi = {10.1145/1183614.1183627},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1183628,
author = {Yun Chi and Belle L. Tseng and Junichi Tatemura},
title = {Eigen-trend: trend analysis in the blogosphere based
on singular value decompositions},
booktitle = {CIKM '06: Proceedings of the 15th ACM international
conference on Information and knowledge management},
year = {2006},
isbn = {1-59593-433-2},
pages = {68--77},
location = {Arlington, Virginia, USA},
doi = {10.1145/1183614.1183628},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1191120,
author = {Tao Li and Chengliang Zhang and Shenghuo Zhu},
title = {Empirical Studies on Multi-label Classification},
booktitle = {ICTAI '06: Proceedings of the 18th IEEE
International Conference on Tools with Artificial
Intelligence},
year = {2006},
isbn = {0-7695-2728-0},
pages = {86--92},
doi = {10.1109/ICTAI.2006.55},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA}
}
@inproceedings{1242599,
author = {Xiaodan Song and Yun Chi and Koji Hino and Belle
L. Tseng},
title = {Information flow modeling based on diffusion rate
for prediction and ranking},
booktitle = {WWW '07: Proceedings of the 16th international
conference on World Wide Web},
year = {2007},
isbn = {978-1-59593-654-7},
pages = {191--200},
location = {Banff, Alberta, Canada},
doi = {10.1145/1242572.1242599},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1244410,
author = {Yu-Ru Lin and Hari Sundaram and Yun Chi and Junichi
Tatemura and Belle L. Tseng},
title = {Splog detection using self-similarity analysis on
blog temporal dynamics},
booktitle = {AIRWeb '07: Proceedings of the 3rd international
workshop on Adversarial information retrieval on the
web},
year = {2007},
isbn = {978-1-59593-732-2},
pages = {1--8},
location = {Banff, Alberta, Canada},
doi = {10.1145/1244408.1244410},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1281212,
author = {Yun Chi and Xiaodan Song and Dengyong Zhou and Koji
Hino and Belle L. Tseng},
title = {Evolutionary spectral clustering by incorporating
temporal smoothness},
booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD
international conference on Knowledge discovery and
data mining},
year = {2007},
isbn = {978-1-59593-609-7},
pages = {153--162},
location = {San Jose, California, USA},
doi = {10.1145/1281192.1281212},
publisher = {ACM},
address = {New York, NY, USA},
note = {{\bf Runner-up for the Best Research Paper Award}}
}
@inproceedings{1281213,
author = {Yun Chi and Shenghuo Zhu and Xiaodan Song and
Junichi Tatemura and Belle L. Tseng},
title = {Structural and temporal analysis of the blogosphere
through community factorization},
booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD
international conference on Knowledge discovery and
data mining},
year = {2007},
isbn = {978-1-59593-609-7},
pages = {163--172},
location = {San Jose, California, USA},
doi = {10.1145/1281192.1281213},
publisher = {ACM},
address = {New York, NY, USA}
}
@article{1283276,
author = {Yihong Gong},
title = {Summarizing audiovisual contents of a video program},
journal = {EURASIP J. Appl. Signal Process.},
volume = {2003},
number = {1},
year = {2003},
issn = {1110-8657},
pages = {160--169},
publisher = {Hindawi Publishing Corp.},
address = {New York, NY, United States}
}
@inproceedings{1321588,
author = {Xiaodan Song and Yun Chi and Koji Hino and Belle
Tseng},
title = {Identifying opinion leaders in the blogosphere},
booktitle = {CIKM '07: Proceedings of the sixteenth ACM
conference on Conference on information and
knowledge management},
year = {2007},
isbn = {978-1-59593-803-9},
pages = {971--974},
location = {Lisbon, Portugal},
doi = {10.1145/1321440.1321588},
publisher = {ACM},
address = {New York, NY, USA}
}
@article{1326565,
author = {Yu-Ru Lin and Hari Sundaram and Yun Chi and Junichi
Tatemura and Belle L. Tseng},
title = {Detecting splogs via temporal dynamics using
self-similarity analysis},
journal = {ACM Trans. Web},
volume = {2},
number = {1},
year = {2008},
issn = {1559-1131},
pages = {1--35},
doi = {10.1145/1326561.1326565},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1331787,
author = {Yu-Ru Lin and Hari Sundaram and Yun Chi and Junichi
Tatemura and Belle L. Tseng},
title = {Blog Community Discovery and Evolution Based on
Mutual Awareness Expansion},
booktitle = {WI '07: Proceedings of the IEEE/WIC/ACM
International Conference on Web Intelligence},
year = {2007},
isbn = {0-7695-3026-5},
pages = {48--56},
doi = {10.1109/WI.2007.30},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA}
}
@inproceedings{1341923,
author = {Belle L. Tseng},
title = {Blog analysis and mining technologies to summarize
the wisdom of crowds},
booktitle = {MDM '07: Proceedings of the 8th international
workshop on Multimedia data mining},
year = {2007},
isbn = {978-1-59593-837-4},
pages = {1--1},
location = {San Jose, California},
doi = {10.1145/1341920.1341923},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1348556,
author = {Akshay Java and Xiaodan Song and Tim Finin and Belle
Tseng},
title = {Why we twitter: understanding microblogging usage
and communities},
booktitle = {WebKDD/SNA-KDD '07: Proceedings of the 9th WebKDD
and 1st SNA-KDD 2007 workshop on Web mining and
social network analysis},
year = {2007},
isbn = {978-1-59593-848-0},
pages = {56--65},
location = {San Jose, California},
doi = {10.1145/1348549.1348556},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1367517,
author = {Ding Zhou and Shenghuo Zhu and Kai Yu and Xiaodan
Song and Belle L. Tseng and Hongyuan Zha and C. Lee
Giles},
title = {Learning multiple graphs for document
recommendations},
booktitle = {WWW '08: Proceeding of the 17th international
conference on World Wide Web},
year = {2008},
isbn = {978-1-60558-085-2},
pages = {141--150},
location = {Beijing, China},
doi = {10.1145/1367497.1367517},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{1367590,
author = {Yu-Ru Lin and Yun Chi and Shenghuo Zhu and Hari
Sundaram and Belle L. Tseng},
title = {Facetnet: a framework for analyzing communities and
their evolutions in dynamic networks},
booktitle = {WWW '08: Proceeding of the 17th international
conference on World Wide Web},
year = {2008},
isbn = {978-1-60558-085-2},
pages = {685--694},
location = {Beijing, China},
doi = {10.1145/1367497.1367590},
publisher = {ACM},
address = {New York, NY, USA}
}
@article{323500,
author = {Yihong Gong},
title = {Advancing content-based image retrieval by
exploiting image color and region features},
journal = {Multimedia Syst.},
volume = {7},
number = {6},
year = {1999},
issn = {0942-4962},
pages = {449--457},
doi = {10.1007/s005300050145},
publisher = {Springer-Verlag New York, Inc.},
address = {Secaucus, NJ, USA}
}
@inproceedings{564411,
author = {Xin Liu and Yihong Gong and Wei Xu and Shenghuo Zhu},
title = {Document clustering with cluster refinement and
model selection capabilities},
booktitle = {SIGIR '02: Proceedings of the 25th annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = {2002},
isbn = {1-58113-561-0},
pages = {191--198},
location = {Tampere, Finland},
doi = {10.1145/564376.564411},
publisher = {ACM},
address = {New York, NY, USA}
}
@inproceedings{641081,
author = {Mei Han and Wei Hua and Wei Xu and Yihong Gong},
title = {An integrated baseball digest system using maximum
entropy method},
booktitle = {MULTIMEDIA '02: Proceedings of the tenth ACM
international conference on Multimedia},
year = {2002},
isbn = {1-58113-620-X},
pages = {347--350},
location = {Juan-les-Pins, France},
doi = {10.1145/641007.641081},
publisher = {ACM},
address = {New York, NY, USA}
}
@article{959280,
author = {Yihong Gong and Xin Liu},
title = {Video summarization and retrieval using singular
value decomposition},
journal = {Multimedia Syst.},
volume = {9},
number = {2},
year = {2003},
issn = {0942-4962},
pages = {157--168},
doi = {10.1007/s00530-003-0086-3},
publisher = {Springer-Verlag New York, Inc.},
address = {Secaucus, NJ, USA}
}
@incollection{EM_287,
title = {Image and Video Super Resolution Techniques},
author = {Jinjun Wang and Yihong Gong},
booktitle = {Encyclopedia of Multimedia, 2nd Edition},
editor = {Dr. Borko Furht},
publisher = {Springer},
year = {2008}
}
@inproceedings{4284695,
title = {Efficient Video Object Segmentation by Graph-Cut},
author = {Jinjun Wang and Wei Xu and Shenghuo Zhu and Yihong
Gong},
booktitle = {ICME '07: IEEE International Conference on
Multimedia and Expo},
year = {2007},
month = {July},
volume = {},
number = {},
pages = {496-499},
abstract = {Segmentation of video objects from background is a
popular computer vision topic and has many important
applications. Most existing methods are either
computationally expensive or requiring manual
initialization, static cameras, and/or rigid
scenes. In a previous work, we proposed a joint
spatio-temporal linear regression algorithm to
automatically cluster the sparse edge/corner pixels
in each video frame and obtain two motion models for
the object and background respectively. To label the
rest pixels for object segmentation, in this paper,
we propose to model the Optical-Flow residual error,
color intensity residual error and temporal label
consistency features, as well as color/edge
orientation consistency constrains, in a graph, and
apply the Graph-Cut algorithm to minimize the energy
of the graph to obtain an optimal segmentation of
the two motion layers boundaries. Finally the object
layer is identified from the two using simple
heuristics. Experimental segmentation result with
videos taken by webcams is promising.},
keywords = {image colour analysis, image motion analysis, image
segmentation, regression analysis, video signal
processingcolor intensity residual error, computer
vision, graph-cut, motion layers boundaries,
spatio-temporal linear regression algorithm,
temporal label consistency features, video frame,
video object segmentation},
doi = {10.1109/ICME.2007.4284695}
}
@inproceedings{4607395,
title = {Fast image super-resolution using Connected
Component enhancement},
author = {Jinjun Wang and Yihong Gong},
booktitle = {ICME '08: IEEE International Conference on
Multimedia and Expo},
year = {2008},
month = {23 2008-April 26},
volume = {},
number = {},
pages = {157-160},
abstract = {The paper focuses on reconstructing the
discontinuity between homogenous color regions in an
interpolated image to improve its perceptual
quality. A low-resolution input image is firstly
interpolated and then decomposed into several
patches. Each patch is then segmented into multiple
homogenous regions using Connected Component
Analysis technique. Then a spatial-filter is applied
to enhance the color/intensity transition between
neighboring components. The designed spatial-filter
combines the advantages of both bilateral-filtering
and unsharp masking methods, with high computational
efficiency. The proposed method can be used for
image/video super-resolution
applications. Experimental results are promising.},
doi = {10.1109/ICME.2008.4607395}
}
@incollection{NIPS2007_896,
title = {Predictive Matrix-Variate t Models},
author = {Shenghuo Zhu and Kai Yu and Yihong Gong},
booktitle = {Advances in Neural Information Processing Systems
20},
editor = {J.C. Platt and D. Koller and Y. Singer and
S. Roweis},
publisher = {MIT Press},
address = {Cambridge, MA},
pages = {1721--1728},
year = {2008},
url = {http://books.nips.cc/papers/files/nips20/NIPS2007_0896.pdf}
}
@incollection{NIPS2007_928,
title = {Gaussian Process Models for Link Analysis and
Transfer Learning},
author = {Kai Yu and Wei Chu},
booktitle = {Advances in Neural Information Processing Systems
20},
editor = {J.C. Platt and D. Koller and Y. Singer and
S. Roweis},
publisher = {MIT Press},
address = {Cambridge, MA},
pages = {1657--1664},
year = {2008},
url = {http://books.nips.cc/papers/files/nips20/NIPS2007_0928.pdf}
}
@inproceedings{appan06:_summar_and_visual_of_commun,
author = { P. Appan and H. Sundaram and B. L. Tseng},
title = {Summarization and Visualization of Communication
Patterns in a Large Social network},
booktitle = { Proceedings of 10th. Pacific-Asia Conference, PAKDD
2006, Advances in Knowledge Discovery and Data
Mining},
pages = {371-379},
year = 2006,
editor = { Ng, W.K. },
number = 3918,
series = {Lecture Notes in Computer Science (LNCS)},
address = {New York},
publisher = {Springer-Verlag}
}
@inproceedings{gong01:_gener_text_summar_using_relev,
author = {Yihong Gong and Xin Liu},
title = {Generic text summarization using relevance measure
and latent semantic analysis},
booktitle = {SIGIR '01: Proceedings of the 24th annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = 2001,
isbn = {1-58113-331-6},
pages = {19--25},
location = {New Orleans, Louisiana, United States},
doi = {10.1145/383952.383955},
publisher = {ACM},
address = {New York, NY, USA}
}
@book{gong07:_machin_learn_for_multim_conten,
author = {Yihong Gong and Wei Xu},
title = {Machine Learning for Multimedia Content Analysis
(Multimedia Systems and Applications)},
year = 2007,
isbn = 0387699384,
publisher = {Springer-Verlag New York, Inc.},
address = {Secaucus, NJ, USA}
}
@article{han07:_multi_objec_trajec_track,
author = {Mei Han and Wei Xu and Hai Tao and Yihong Gong},
title = {Multi-object trajectory tracking},
journal = {Mach. Vision Appl.},
volume = 18,
number = 3,
year = 2007,
issn = {0932-8092},
pages = {221--232},
doi = {10.1007/s00138-007-0071-5},
publisher = {Springer-Verlag New York, Inc.},
address = {Secaucus, NJ, USA}
}
@inproceedings{kong06:_video_super_resol_with_scene_specif_prior,
author = {D. Kong and M. Han and W. Xu and H. Tao and
Y. Gong},
title = {Video Super-resolution with Scene-specific Priors},
booktitle = {Proceedings of British Machine Vision Seventeenth
Conference },
pages = {549-558},
year = 2006
}
@inproceedings{lin06:_splog_detec_task_and_solut,
author = { Y.R. Lin and W.Y. Chen and X. Shi and R. Sia and
X. Song and Y. Chi and K. Hino and H. Sundaram and
J. Tatemura and B. L. Tseng},
title = {The Splog Detection Task and A Solution Based on
Temporal and Link Properties},
booktitle = {Proceedings of NIST Text Retrieval Conference -
TREC},
year = 2006
}
@inproceedings{sia07:_captur_user_inter_by_both,
author = {Ka Cheung Sia and Shenghuo Zhu Yun Chi and Koji Hino and Belle L. Tseng},
title = {Capturing User Interests by Both Exploitation and
Exploration},
booktitle = {UM '07: Proceedings of User Modeling},
pages = {334-339},
year = 2007,
doi = {10.1007/978-3-540-73078-1_40}
}
@inproceedings{sia07:_monit_rss_feeds_based_user_brows_patter,
author = {Ka Cheung Sia and Junghoo Cho and Koji Hino and Yun
Chi and Shenghuo Zhu and Belle L. Tseng},
title = { Monitoring RSS Feeds Based on User Browsing
Pattern},
booktitle = {ICWSM '07: International Conference on Weblogs and
Social Media},
year = 2007,
url = {http://www.icwsm.org/papers/2--Sia-Cho-Hino-Chi-Zhu-Tseng.pdf}
}
@inproceedings{song05:_exper,
author = { X. Song and B.L. Tseng and C.Y. Lin and M.T. Sun},
title = {{ExpertiseNET} : Relational and Evolutionary Expert
Modeling},
booktitle = {10th. International Conference on User modeling},
pages = {99-108},
year = 2005,
editor = { Ardissono, Liliana },
number = 3538,
series = {Lecture Notes in Computer Science},
address = { Berlin},
publisher = {Springer-Verlag}
}
@inproceedings{song06:_model_evolut_behav_for_commun,
author = { X. Song and C.Y. Lin and B.L. Tseng and M.T. Sun},
title = {Modeling Evolutionary Behaviors for Community-based
Dynamic Recommendation},
booktitle = {SIAM SDM'06: Proceedings of the SIAM Conference on
Data Mining},
year = 2006
}
@inproceedings{song07:_summar_system_by_ident_influen_blogs,
author = {X. Song and Y. Chi and K. Hino and B. L. Tseng},
title = {Summarization System by Identifying Influential
Blogs},
booktitle = {Proceedings of the ICWSM},
pages = {325-326},
year = 2007
}
@inproceedings{tseng05:_tomog_clust_to_visual_blog,
author = {B.L. Tseng and J. Tatemura and Y. Wu},
title = {Tomographic Clustering To Visualize Blog Communities
as Mountain Views},
booktitle = {Proceedings of the WWW 2005 2nd. Annual Workshop on
the Weblogging Ecosystem: Aggregation, Analysis and
Dynamics},
year = 2005
}
@inproceedings{wu06:_impor_weblog_ident_and_hot_story_summar,
author = {Y. Wu and B.L. Tseng},
title = {Important Weblog Identification and Hot Story
Summarization},
booktitle = {Proceedings of AAAI Computational Approaches to
Analyzing Weblogs},
pages = {221-227},
year = 2006
}
@inproceedings{xu03:_docum_clust_based_non_negat_matrix_factor,
author = {Wei Xu and Xin Liu and Yihong Gong},
title = {Document clustering based on non-negative matrix
factorization},
booktitle = {SIGIR '03: Proceedings of the 26th annual
international ACM SIGIR conference on Research and
development in informaion retrieval},
pages = {267--273},
publisher = {ACM Press},
doi = {10.1145/860435.860485},
isbn = {1-58113-646-3},
location = {Toronto, Canada},
year = 2003
}
@inproceedings{xu04:_docum_clust_by_concep_factor,
author = {Wei Xu and Yihong Gong},
title = {Document clustering by concept factorization},
booktitle = {SIGIR '04: Proceedings of the 27th annual
international conference on Research and development in
information retrieval},
pages = {202--209},
publisher = {ACM Press},
doi = {10.1145/1008992.1009029},
isbn = {1-58113-881-4},
location = {Sheffield, United Kingdom},
year = 2004
}
@inproceedings{zhang06:_trend_analy_for_large_docum_stream,
author = {Chengliang Zhang and Shenghuo Zhu and Yihong Gong},
title = {Trend Analysis for Large Document Streams},
booktitle = {ICMLA '06: Proceedings of the 5th International
Conference on Machine Learning and Applications},
year = 2006,
isbn = {0-7695-2735-3},
pages = {285--295},
doi = {10.1109/ICMLA.2006.51},
publisher = {IEEE Computer Society},
address = {Washington, DC, USA}
}
@inproceedings{zhu07:_combin_conten_and_link_for,
author = {Shenghuo Zhu and Kai Yu and Yun Chi and Yihong Gong},
title = {Combining content and link for classification using
matrix factorization},
booktitle = {SIGIR '07: Proceedings of the 30th annual
international ACM SIGIR conference on Research and
development in information retrieval},
year = 2007,
isbn = {978-1-59593-597-7},
pages = {487--494},
location = {Amsterdam, The Netherlands},
doi = {10.1145/1277741.1277825},
publisher = {ACM Press},
address = {New York, NY, USA}
}
@inproceedings{4284929,
title = {Detecting Unsafe Driving Patterns using
Discriminative Learning},
author = {Yue Zhou and Wei Xu and Huazhong Ning and Yihong
Gong and Huang, T.S.},
booktitle = {Multimedia and Expo, 2007 IEEE International
Conference on},
year = {2007},
month = {July},
volume = {},
number = {},
pages = {1431-1434},
abstract = {We propose a discriminative learning approach for
fusing multichannel sequential data with application
to detect unsafe driving patterns from multi-channel
driving recording data. The fusion is performed
using a discriminatively trained graphical model
-conditional random field (CRF). The proposed
approach offers several advantage over existing
information fusing approaches. First, it derives its
classification power by directly modelling and
maximizing the conditional probability. Second, it
represents the variable dependency in an undirected
graph, which is very efficient in inference. Third,
it does not require to label all the training data
and utilizes both labelled and unlabelled data
efficiently by semi-supervised learning
algorithms. The proposed approach is evaluated on
driving recording data collected from driving
simulator -STISIM. Experiments show it outperforms
the simple discriminative classifier (SVM) and
generative model (HMM).},
keywords = {driver information systems, hidden Markov models,
learning (artificial intelligence), support vector
machinesHMM, STISIM, SVM, conditional random field,
discriminative learning, driving simulator,
multichannel driving recording data, multichannel
sequential data, semisupervised learning, unsafe
driving patterns},
doi = {10.1109/ICME.2007.4284929},
issn = {}
}
@inproceedings{4284831,
title = {Bilateral Back-Projection for Single Image Super
Resolution},
author = {Shengyang Dai and Mei Han and Ying Wu and Yihong
Gong},
booktitle = {Multimedia and Expo, 2007 IEEE International
Conference on},
year = {2007},
month = {July},
volume = {},
number = {},
pages = {1039-1042},
abstract = {In this paper, a novel algorithm for single image
super resolution is proposed. Back-projection [1]
can minimize the reconstruction error with an
efficient iterative procedure. Although it can
produce visually appealing result, this method
suffers from the chessboard effect and ringing
effect, especially along strong edges. The
underlining reason is that there is no edge guidance
in the error correction process. Bilateral filtering
can achieve edge-preserving image smoothing by
adding the extra information from the feature
domain. The basic idea is to do the smoothing on the
pixels which are nearby both in space domain and in
feature domain. The proposed bilateral
back-projection algorithm strives to integrate the
bilateral filtering into the back-projection
method. In our approach, the back-projection process
can be guided by the edge information to avoid
across-edge smoothing, thus the chessboard effect
and ringing effect along image edges are
removed. Promising results can be obtained by the
proposed bilateral back-projection method
efficiently.},
keywords = {feature extraction, filtering theory, image
reconstruction, image resolutionbilateral back
projection, bilateral filtering, chessboard effect,
edge preserving image smoothing, feature domain,
iterative procedure, reconstruction error, ringing
effect, single image super resolution, space domain},
doi = {10.1109/ICME.2007.4284831},
issn = {}
}
@inproceedings{4270053,
title = {Soft Edge Smoothness Prior for Alpha Channel Super
Resolution},
author = {Shengyang Dai and Mei Han and Wei Xu and Ying Wu and
Yihong Gong},
booktitle = {Computer Vision and Pattern Recognition, 2007. CVPR
'07. IEEE Conference on},
year = {2007},
month = {June},
volume = {},
number = {},
pages = {1-8},
abstract = {Effective image prior is necessary for image super
resolution, due to its severely under-determined
nature. Although the edge smoothness prior can be
effective, it is generally difficult to have
analytical forms to evaluate the edge smoothness,
especially for soft edges that exhibit gradual
intensity transitions. This paper finds the
connection between the soft edge smoothness and a
soft cut metric on an image grid by generalizing the
Geocuts method (Y. Boykov and V. Kolmogorov, 2003),
and proves that the soft edge smoothness measure
approximates the average length of all level lines
in an intensity image. This new finding not only
leads to an analytical characterization of the soft
edge smoothness prior, but also gives an intuitive
geometric explanation. Regularizing the super
resolution problem by this new form of prior can
simultaneously minimize the length of all level
lines, and thus resulting in visually appealing
results. In addition, this paper presents a novel
combination of this soft edge smoothness prior and
the alpha matting technique for color image super
resolution, by normalizing edge segments with their
alpha channel description, to achieve a unified
treatment of edges with different contrast and
scale.},
keywords = {edge detection, geometry, image colour analysis,
image resolution, image segmentation, smoothing
methodsGeocuts method, alpha channel super
resolution, alpha matting technique, color image
super resolution, edge segments normalization, image
grid, intensity transitions, intuitive geometric
explanation, soft cut metric, soft edge smoothness},
doi = {10.1109/CVPR.2007.383028},
issn = {}
}
@inproceedings{4036996,
title = {Improving Speaker Diarization by Cross EM
Refinement},
author = {Huazhong Ning and Wei Xu and Yihong Gong and Huang,
T.},
booktitle = {Multimedia and Expo, 2006 IEEE International
Conference on},
year = {2006},
month = {July},
volume = {},
number = {},
pages = {1901-1904},
abstract = {In this paper, we present a new speaker diarization
system that improves the accuracy of traditional
hierarchical clustering-based methods with little
increase in computational cost. Our contributions
are mainly two fold. First, we include a
preprocessing called "local clustering" before the
hierarchical clustering algorithm to merge very
similar adjacent speech segments. This local
clustering aims to reduce the number of segments to
be clustered by the hierarchical clustering, so as
to dramatically increase the processing
speed. Second, we perform a postprocessing called
"cross EM refinement" to purify the clusters
generated by the hierarchical clustering. This
algorithm is based on the idea of cross validation
and EM algorithm. Our experimental evaluations show
that the proposed cross EM refinement approach
reduces the speaker diarization error by up to 56%,
with an average reduction of 22% compared to the
traditional hierarchical clustering method},
keywords = {expectation-maximisation algorithm, speaker
recognitioncross EM refinement approach,
hierarchical clustering, local clustering algorithm,
speaker diarization system},
doi = {10.1109/ICME.2006.262927},
issn = {}
}
@inproceedings{1421760,
title = {A detection-based multiple object tracking method},
author = {Mei Han and Sethi, A. and Wei Hua and Yihong Gong},
booktitle = {Image Processing, 2004. ICIP '04. 2004 International
Conference on},
year = {2004},
month = {Oct.},
volume = {5},
number = {},
pages = { 3065-3068 Vol. 5},
abstract = { In this paper we describe a method for tracking
multiple objects whose number is unknown and varies
during tracking. Based on preliminary results of
object detection in each image which may have
missing and/or false detection, the multiple object
tracking method keeps a graph structure where it
maintains multiple hypotheses about the number and
the trajectories of the objects in the video. The
image information drives the process of extending
and pruning the graph, and determines the best
hypothesis to explain the video. While the
image-based object detection makes a local decision,
the tracking process confirms and validates the
detection through time, therefore, it can be
regarded as temporal detection which makes a global
decision across time. The multiple object tracking
method gives feedbacks which are predictions of
object locations to the object detection
module. Therefore, the method integrates object
detection and tracking tightly. The most possible
hypothesis provides the multiple object tracking
result. The experimental results are presented.},
keywords = { image sequences, object detection, tracking, video
signal processing detection-based multiple object
tracking method, graph structure, image sequence,
image-based object detection, temporal detection},
doi = {10.1109/ICIP.2004.1421760},
issn = {1522-4880 }
}
@inproceedings{1315122,
title = {An algorithm for multiple object trajectory
tracking},
author = {Mei Han and Wei Xu and Hai Tao and Yihong Gong},
booktitle = {Computer Vision and Pattern Recognition, 2004. CVPR
2004. Proceedings of the 2004 IEEE Computer Society
Conference on},
year = {2004},
month = {June-2 July},
volume = {1},
number = {},
pages = { I-864-I-871 Vol.1},
abstract = { Most tracking algorithms are based on the maximum a
posteriori (MAP) solution of a probabilistic
framework called Hidden Markov Model, where the
distribution of the object state at current time
instance is estimated based on current and previous
observations. However this approach is prone to
errors caused by temporal distractions such as
occlusion, background clutter and multi-object
confusion. In this paper we propose a multiple
object tracking algorithm that seeks the optimal
state sequence which maximizes the joint
state-observation probability. We name this
algorithm trajectory tracking since it estimates the
state sequence or "trajectory" instead of the
current state. The algorithm is capable of tracking
multiple objects whose number is unknown and varies
during tracking. We introduce an observation model
which is composed of the original image, the
foreground mask given by background subtraction and
the object detection map generated by an object
detector The image provides the object appearance
information. The foreground mask enables the
likelihood computation to consider the multi-object
configuration in its entirety. The detection map
consists of pixel-wise object detection scores,
which drives the tracking algorithm to perform joint
inference on both the number of objects and their
configurations efficiently.},
keywords = { hidden Markov models, maximum likelihood sequence
estimation, object detection, probability, state
estimation, tracking Hidden Markov model, MAP
solution, joint state observation probability,
likelihood computation, maximum a posteriori
solution, multiobject configuration, multiple object
trajectory tracking, object detection map, object
state estimation, observation model, optimal state
sequence estimation, pixel wise object detection
scores, probabilistic framework, temporal
distractions},
doi = {10.1109/CVPR.2004.1315122},
issn = {1063-6919 }
}
@inproceedings{1038097,
title = {Extract highlights from baseball game video with
hidden Markov models},
author = {Peng Chang and Mei Han and Yihong Gong},
booktitle = {Image Processing. 2002. Proceedings. 2002
International Conference on},
year = {2002},
month = {},
volume = {1},
number = {},
pages = { I-609-I-612 vol.1},
abstract = { We describe a statistical method to detect
highlights in a baseball game video. The input video
is first segmented into scene shots, within which
the camera motion is continuous. Our approach is
based on the observations that (1) most highlights
in baseball games are composed of certain types of
scene shots and (2) those scene shots exhibit
special transition context in time. To exploit those
two observations, we first build statistical models
for each type of scene shots with products of
histograms, and then for each type of highlight a
hidden Markov model is learned to represent the
context of transition in the time domain. A
probabilistic model can be obtained by combining the
two, which is used for highlight detection and
classification. Satisfactory results have been
achieved on initial experimental results.},
keywords = { feature extraction, games of skill, hidden Markov
models, image classification, image motion analysis,
probability, statistical analysis, video signal
processing HMM, baseball game video, camera motion,
hidden Markov models, highlight classification,
highlight detection, highlights extraction,
histograms, input video segmentation, probabilistic
model, scene shots, statistical method, statistical
models, time domain},
doi = {10.1109/ICIP.2002.1038097},
issn = {1522-4880 }
}
@inproceedings{1035908,
title = {Baseball scene classification using multimedia
features},
author = {Wei Hua and Mei Han and Yihong Gong},
booktitle = {ICME '02: IEEE International Conference on
Multimedia and Expo},
year = {2002},
month = {},
volume = {1},
number = {},
pages = { 821-824 vol.1},
abstract = { In this paper, we address the issue of classifying
video scenes which is essential in video indexing,
archiving and summarization. Compared with previous
methods, we emphasize the integration of multimedia
features, including image, audio and speech
cues. With current state-of-the-art image and audio
analysis techniques, most image and audio features
we can extract from videos are very low level,
therefore, classifying scenes based on features from
a single medium yields poor performance. We propose
a maximum entropy based method for baseball scene
classification in TV broadcast videos. The maximum
entropy scheme is chosen because it can
automatically select and fuse multimedia features
from temporal contexts.},
keywords = { content-based retrieval, database indexing, feature
extraction, maximum entropy methods, multimedia
databases, pattern classification, sport, television
broadcasting, video databases TV broadcast videos,
archiving, audio analysis, audio cues, automatic
selection, baseball scene classification, feature
extraction, image analysis, image cues, maximum
entropy based method, multimedia feature fusion,
multimedia feature integration, multimedia features,
speech cues, summarization, temporal context, video
indexing, video scene classification},
doi = {10.1109/ICME.2002.1035908}
}
@inproceedings{1035774,
title = {Creating motion video summaries with partial
audio-visual alignment},
author = {Yihong Gong and Xin Liu and Wei Hua},
booktitle = {Multimedia and Expo, 2002. ICME
'02. Proceedings. 2002 IEEE International Conference
on},
year = {2002},
month = {},
volume = {1},
number = {},
pages = { 285-288 vol.1},
abstract = { In this paper, we propose an audio-visual
summarization system which creates an audio and a
visual summary of a given video program separately,
and then integrates the two summaries with a partial
alignment. A bipartite graph-based audio-visual
alignment algorithm is developed to efficiently find
the best alignment solution that satisfies the
predefined alignment requirements. With the proposed
system, we strive to produce a motion video summary
for the original video that: (1) provides a natural
visual and audio content overview; and (2) maximizes
the coverage for both audio and visual contents of
the original video without having to sacrifice
either of them. Such audio-visual summaries
dramatically increase the information intensity and
depth, and lead to a more effective video content
overview.},
keywords = { content-based retrieval, database indexing, graph
theory, image sequences, television applications,
video databases, video on demand bipartite graph,
motion video summaries, partial audio-visual
alignment, summarization system, video content
overview, video program},
doi = {10.1109/ICME.2002.1035774},
issn = { }
}
@inproceedings{953917,
title = {Creating generic text summaries},
author = {Yihong Gong and Xin Liu},
booktitle = {Document Analysis and Recognition,
2001. Proceedings. Sixth International Conference
on},
year = {2001},
month = {},
volume = {},
number = {},
pages = {903-907},
abstract = {We propose two generic text summarization methods
that create text summaries by ranking and extracting
sentences from the original documents. The first
method uses standard information retrieval methods
to rank sentence relevances, while the second method
uses the latent semantic analysis technique to
identify semantically important sentences, for
summary creations. Both methods strive to select
sentences that are highly ranked and different from
each other. This is an attempt to create a summary
with a wider coverage of the document's main content
and less redundancy. Performance evaluations on the
two summarization methods are conducted by comparing
their summarization outputs with the manual
summaries generated by three independent human
evaluators},
keywords = {relevance feedback, text analysisgeneric text
summaries, latent semantic analysis technique,
sentence relevances, standard information retrieval
methods, summary creations},
doi = {10.1109/ICDAR.2001.953917},
issn = {}
}
@inproceedings{1237793,
title = {Summarizing video by minimizing visual content redundancies},
author = { Yihong Gong and Xin Liu},
booktitle = {Multimedia and Expo, 2001. ICME 2001. IEEE International Conference on},
year = {2001},
month = {Aug.},
volume = {},
number = {},
pages = { 607-610},
abstract = {},
issn = { }
}