Temporal SegmentatioN:perspectives from
statistics, machine learning, and signal processing. December 12th 2009, Whistler, British Columbia, CA Sponsored by Pascal II 
Organizing Committee

Workshop Overview 
Invited Speakers 
Call for papers

Timetable 
Bibliography 
Data with temporal (or sequential) structure arise in several applications, such as speaker diarization [FSJW08b, FDH08], human action segmentation [ZTH08], network intrusion detection [TRBK06], DNA copy number analysis [LXZ08], and neuron activity modelling [Y07], to name a few.
A particularly recurrent temporal structure in real applications is the socalled changepoint model [BH92], where the data may be temporally partitioned into a sequence of segments delimited by changepoints, such that a single model holds within each segment whereas different models hold accross segments. Changepoint problems may be tackled from two points of view, corresponding to the practical problem at hand: retrospective (or "a posteriori"), aka multiple changepoint estimation [F06], where the whole signal is taken at once and the goal is to estimate the changepoint locations [BKLMW09], and online (or sequential), aka quickest detection [PH09], where data are observed sequentially and the goal is to quickly detect changepoints. We refer to these classes of tasks as temporal segmentation.
An extensive literature has developed in these two viewpoints, in both the statistics (and probability) community [L01], and in the signal processing community [K98]. Many of the optimal algorithms proposed in this literature were developed under rather restrictive assumptions, however: parametric models for distributions, lowdimensional multivariate data, and, in the online case, perfect knowledge of the pre and postchange distributions.
In applications such as human action segmentation or speaker diarization, data are largescale, expensive to label, and highdimensional, therefore requiring approaches that can tackle more complex situations in temporal segmentation. Recent years have witnessed new approaches with broader applicability, essentially by proposing unsupervised [XWSS06, ZTH08], nonparametric [FSJW08b], and scalable temporal segmentation algorithms [FL07, FDH08].
The purpose of this workshop is to bring together experts from the statistics, machine learning, signal processing communities, to address a broad range of applications from robotics to neuroscience, to discuss and crossfertilize ideas, and to define the current challenges in temporal segmentation. We intend to encourage discussions on the following particular issues: How can traditional statistical approaches for temporal segmentation, essentially generative, be extended to discriminative approaches, allowing us to deal with highdimensional data? How well do unsupervised approaches for temporal segmentation perform with respect to supervised ones? What are the main statistical and computational issues that arise when addressing largescale (long) data signals?
Submissions are solicited for the workshop. Submissions are not constrained regarding the applications in which temporal segmentation is of interest: these can include speaker/audio processing, financial time series, video, motion capture, bioinformatics, network intrusion detection, etc. Presentations on closely related topics such as sequential decision making, temporal classification, structured prediction with temporal/spatial constraints, are also encouraged. Submissions may focus on theoretical, methodological, and computational aspects of temporal segmentation.
Accepted submissions will be presented either as short talks or
during the
workshop poster session, depending on the proposals. The deadline for
submission is October 23th 2009
(Midnight, Pacific Standard Time) and notifications will be sent out by
November
2nd 2009. The submission should be at most four pages
long in NIPS format, and should be sent to temposegment.nips09@gmail.com.
We
do
not
require
submissions
to be in blind format. Yet, submissions
may be in blind format if the authors wish to do so.
Any question regarding the workshop and the submission/reviewing
process may be sent to zaidh@andrew.cmu.edu.
Time 
Speaker 
Topic 
7:30am 
Haipeng Xing &Tze Leung Lai 
Retrospective and Sequential Changepoint Modelling Approaches 
8:15am 
Jens Kohlmorgen 
A Dynamic HMM for Online Segmentation 
8:30am 
Discussions and posters 

9:05am 
Kevin Murphy 
Product Partition Models for Modelling Changing Dependency Structure in Time Series 
9:35am 
Fernando de la Torre 
Segmentation of Human Activities in Video 
9:50am 
Erik Sudderth 
HierarchicalDirichletProcessbased Hidden Markov Models 
10:35am 
Posters and discussion 

3:30pm 
Olympia Hadjiliadis 
Sequential Changepoint Detection 
4:15pm 
Alexandre LungYutFong 
Distributed Detection and Localization of Network Anomalies
using Rank Tests 
4:30pm 
Brian Williams 
Mode estimation of Autonomous Systems 
5:15pm 
Discussion and posters 

5:35pm 
Ryan Turner 
Adaptive Sequential Bayesian Changepoint Detection 
5:50pm 
Francis Bach 
Temporal Segmentation with Kernel Changepoint
Detection 
6:35pm 
Discussion and wrapup 
[SVS08] Q. Shi, L. Wang, and A.J. Smola, Discriminative Human Action Segmentation and Recognition using SemiMarkov Model, CVPR'08
[XWSS06] L. Xu, D. Wilkinson, F. Southey, and D. Schuurmans, Discriminative Unsupervised Learning of Structured Predictors, ICML'06
[FSJW08a] E. Fox, E. Sudderth, M. I. Jordan, A. S. Willsky, Nonparametric Bayesian Learning of Switching Linear Dynamical Systems, NIPS'08
[FSJW08b] E. Fox, E. Sudderth, M. I. Jordan, A. S. Willsky, An HDPHMM For Systems with State Persistence, NIPS'08
[SS07] F. Sha, L. Saul, Large margin hidden Markov models for automatic speech recognition, NIPS'07
[Y07] A. Yu, Optimal ChangeDetection and Spiking Neurons, NIPS'07
[IT07] T. Ide and K. Tsuda, ChangePoint Detection using Krylov Subspace Learning, SIAM International Conference on Data Mining, 2007
[BH92] D. Barry, and J. A. Hartigan, Product Partition Models, Annals of Statistics, 1992
[F06] P. Fearnhead, Exact and Efficient Bayesian inference for Multiple Changepoint Problems, Statistics and Computing, 2006
[FL07] P. Fearnhead and Z. Liu, Online Inference for Multiple Changepoint Problems, Journal of the Royal Statistical Society Series B, 2007
[L01] T. L. Lai, Sequential Analysis: some classical problems and new challenges, Statistica Sinica, 2001
[L05] T. L. Lai, Sequential Changepoint Detection in Quality Control and Dynamical Systems, Journal of the Royal Statistical Society Series B, 2005
[LXZ08] T. L. Lai, H. Xing, and N. R. Zhang, Stochastic segmentation models for arraybased comparative genomic hybridization data analysis, Biostatistics, 2008
[BKLMW09] L. Boysen, A. Kempe, V. Liebscher, A. Munk, O. Wittich, Consistency and rates of convergences of jumppenalized leastsquare estimators, Annals of Statistics, 2009
[K98] S. M. Kay, Fundamentals of Signal Processing: Detection Theory, Prentice Hall, 1998
[PH09] H. V. Poor, O. Hadjiliadis, Quickest Change Detection, Cambridge University Press, 2009
[FDH08] B. Fergani, M. Davy, A. Houacine, Speaker Diarization Using One Class Support Vector Machines, Speech Communication, 2008.
[TRBK06] A. G. Tartakovsky, B. L. Rozovskii, R. B. Blazek, and H. Kim, Detection of intrusions in information systems by sequential changepoint methods, Statistical Methodology, 2006
[ZTH08] F. Zhou, F. de la Torre, J. K . Hodgins, Aligned Cluster Analysis for Temporal Segmentation of Human Motion, International Conference on Automatic Face and Gesture Recognition, 2008
[ZS05] Y. Zhai and M. Shah, A General Framework for Temporal Video Scene Segmentation, ICCV'05