---
_id: '3428'
abstract:
- lang: eng
text: In this issue of Molecular Cell, Davies et al. (2009) work out a sequence
of active cellular events that lead to the death of Escherichia coli in the presence
of the drug hydroxyurea.
article_processing_charge: No
author:
- first_name: Mark Tobias
full_name: Bollenbach, Mark Tobias
id: 3E6DB97A-F248-11E8-B48F-1D18A9856A87
last_name: Bollenbach
orcid: 0000-0003-4398-476X
- first_name: Roy
full_name: Kishony, Roy
last_name: Kishony
citation:
ama: Bollenbach MT, Kishony R. Hydroxyurea triggers cellular responses that actively
cause bacterial cell death. Molecular Cell. 2009;36(5):728-729. doi:10.1016/j.molcel.2009.11.027
apa: Bollenbach, M. T., & Kishony, R. (2009). Hydroxyurea triggers cellular
responses that actively cause bacterial cell death. Molecular Cell. Cell
Press. https://doi.org/10.1016/j.molcel.2009.11.027
chicago: Bollenbach, Mark Tobias, and Roy Kishony. “Hydroxyurea Triggers Cellular
Responses That Actively Cause Bacterial Cell Death.” Molecular Cell. Cell
Press, 2009. https://doi.org/10.1016/j.molcel.2009.11.027.
ieee: M. T. Bollenbach and R. Kishony, “Hydroxyurea triggers cellular responses
that actively cause bacterial cell death,” Molecular Cell, vol. 36, no.
5. Cell Press, pp. 728–729, 2009.
ista: Bollenbach MT, Kishony R. 2009. Hydroxyurea triggers cellular responses that
actively cause bacterial cell death. Molecular Cell. 36(5), 728–729.
mla: Bollenbach, Mark Tobias, and Roy Kishony. “Hydroxyurea Triggers Cellular Responses
That Actively Cause Bacterial Cell Death.” Molecular Cell, vol. 36, no.
5, Cell Press, 2009, pp. 728–29, doi:10.1016/j.molcel.2009.11.027.
short: M.T. Bollenbach, R. Kishony, Molecular Cell 36 (2009) 728–729.
date_created: 2018-12-11T12:03:17Z
date_published: 2009-12-11T00:00:00Z
date_updated: 2021-01-12T07:43:24Z
day: '11'
doi: 10.1016/j.molcel.2009.11.027
extern: '1'
intvolume: ' 36'
issue: '5'
language:
- iso: eng
month: '12'
oa_version: None
page: 728 - 729
publication: Molecular Cell
publication_status: published
publisher: Cell Press
publist_id: '2972'
status: public
title: Hydroxyurea triggers cellular responses that actively cause bacterial cell
death
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 36
year: '2009'
...
---
_id: '3503'
abstract:
- lang: eng
text: 'We give polynomial-time algorithms for computing the values of Markov decision
processes (MDPs) with limsup and liminf objectives. A real-valued reward is assigned
to each state, and the value of an infinite path in the MDP is the limsup (resp.
liminf) of all rewards along the path. The value of an MDP is the maximal expected
value of an infinite path that can be achieved by resolving the decisions of the
MDP. Using our result on MDPs, we show that turn-based stochastic games with limsup
and liminf objectives can be solved in NP ∩ coNP. '
alternative_title:
- LNCS
author:
- first_name: Krishnendu
full_name: Krishnendu Chatterjee
id: 2E5DCA20-F248-11E8-B48F-1D18A9856A87
last_name: Chatterjee
orcid: 0000-0002-4561-241X
- first_name: Thomas A
full_name: Thomas Henzinger
id: 40876CD8-F248-11E8-B48F-1D18A9856A87
last_name: Henzinger
orcid: 0000−0002−2985−7724
citation:
ama: 'Chatterjee K, Henzinger TA. Probabilistic systems with limsup and liminf objectives.
In: Vol 5489. Springer; 2009:32-45. doi:10.1007/978-3-642-03092-5_4'
apa: 'Chatterjee, K., & Henzinger, T. A. (2009). Probabilistic systems with
limsup and liminf objectives (Vol. 5489, pp. 32–45). Presented at the ILC: Infinity
in Logic and Computation, Springer. https://doi.org/10.1007/978-3-642-03092-5_4'
chicago: Chatterjee, Krishnendu, and Thomas A Henzinger. “Probabilistic Systems
with Limsup and Liminf Objectives,” 5489:32–45. Springer, 2009. https://doi.org/10.1007/978-3-642-03092-5_4.
ieee: 'K. Chatterjee and T. A. Henzinger, “Probabilistic systems with limsup and
liminf objectives,” presented at the ILC: Infinity in Logic and Computation, 2009,
vol. 5489, pp. 32–45.'
ista: 'Chatterjee K, Henzinger TA. 2009. Probabilistic systems with limsup and liminf
objectives. ILC: Infinity in Logic and Computation, LNCS, vol. 5489, 32–45.'
mla: Chatterjee, Krishnendu, and Thomas A. Henzinger. Probabilistic Systems with
Limsup and Liminf Objectives. Vol. 5489, Springer, 2009, pp. 32–45, doi:10.1007/978-3-642-03092-5_4.
short: K. Chatterjee, T.A. Henzinger, in:, Springer, 2009, pp. 32–45.
conference:
name: 'ILC: Infinity in Logic and Computation'
date_created: 2018-12-11T12:03:40Z
date_published: 2009-12-15T00:00:00Z
date_updated: 2021-01-12T07:43:54Z
day: '15'
doi: 10.1007/978-3-642-03092-5_4
extern: 1
intvolume: ' 5489'
main_file_link:
- open_access: '1'
url: http://arxiv.org/abs/0809.1465
month: '12'
oa: 1
page: 32 - 45
publication_status: published
publisher: Springer
publist_id: '2884'
quality_controlled: 0
status: public
title: Probabilistic systems with limsup and liminf objectives
type: conference
volume: 5489
year: '2009'
...
---
_id: '3547'
abstract:
- lang: eng
text: Neurons possess elaborate dendritic arbors which receive and integrate excitatory
synaptic signals. Individual dendritic subbranches exhibit local membrane potential
supralinearities, termed dendritic spikes, which control transfer of local synaptic
input to the soma. Here, we show that dendritic spikes in CA1 pyramidal cells
are strongly regulated by specific types of prior input. While input in the linear
range is without effect, supralinear input inhibits subsequent spikes, causing
them to attenuate and ultimately fail due to dendritic Na+ channel inactivation.
This mechanism acts locally within the boundaries of the input branch. If an input
is sufficiently strong to trigger axonal action potentials, their back-propagation
into the dendritic tree causes a widespread global reduction in dendritic excitability
which is prominent after firing patterns occurring in vivo. Together, these mechanisms
control the capability of individual dendritic branches to trigger somatic action
potential output. They are invoked at frequencies encountered during learning,
and impose limits on the storage and retrieval rates of information encoded as
branch excitability.
author:
- first_name: Stefan
full_name: Remy,Stefan
last_name: Remy
- first_name: Jozsef L
full_name: Jozsef Csicsvari
id: 3FA14672-F248-11E8-B48F-1D18A9856A87
last_name: Csicsvari
orcid: 0000-0002-5193-4036
- first_name: Heinz
full_name: Beck,Heinz
last_name: Beck
citation:
ama: Remy S, Csicsvari JL, Beck H. Activity-dependent control of neuronal output
by local and global dendritic spike attenuation. Neuron. 2009;61(6):906-916.
doi:10.1016/j.neuron.2009.01.032
apa: Remy, S., Csicsvari, J. L., & Beck, H. (2009). Activity-dependent control
of neuronal output by local and global dendritic spike attenuation. Neuron.
Elsevier. https://doi.org/10.1016/j.neuron.2009.01.032
chicago: Remy, Stefan, Jozsef L Csicsvari, and Heinz Beck. “Activity-Dependent Control
of Neuronal Output by Local and Global Dendritic Spike Attenuation.” Neuron.
Elsevier, 2009. https://doi.org/10.1016/j.neuron.2009.01.032.
ieee: S. Remy, J. L. Csicsvari, and H. Beck, “Activity-dependent control of neuronal
output by local and global dendritic spike attenuation,” Neuron, vol. 61,
no. 6. Elsevier, pp. 906–916, 2009.
ista: Remy S, Csicsvari JL, Beck H. 2009. Activity-dependent control of neuronal
output by local and global dendritic spike attenuation. Neuron. 61(6), 906–916.
mla: Remy, Stefan, et al. “Activity-Dependent Control of Neuronal Output by Local
and Global Dendritic Spike Attenuation.” Neuron, vol. 61, no. 6, Elsevier,
2009, pp. 906–16, doi:10.1016/j.neuron.2009.01.032.
short: S. Remy, J.L. Csicsvari, H. Beck, Neuron 61 (2009) 906–916.
date_created: 2018-12-11T12:03:54Z
date_published: 2009-03-26T00:00:00Z
date_updated: 2021-01-12T07:44:13Z
day: '26'
doi: 10.1016/j.neuron.2009.01.032
extern: 1
intvolume: ' 61'
issue: '6'
month: '03'
page: 906 - 916
publication: Neuron
publication_status: published
publisher: Elsevier
publist_id: '2838'
quality_controlled: 0
status: public
title: Activity-dependent control of neuronal output by local and global dendritic
spike attenuation
type: journal_article
volume: 61
year: '2009'
...
---
_id: '3578'
abstract:
- lang: eng
text: The medial axis of a geometric shape captures its connectivity. In spite of
its inherent instability, it has found applications in a number of areas that
deal with shapes. In this survey paper, we focus on results that shed light on
this instability and use the new insights to generate simplified and stable modifications
of the medial axis.
alternative_title:
- Mathematics and Visualization
author:
- first_name: Dominique
full_name: Attali, Dominique
last_name: Attali
- first_name: Jean
full_name: Boissonnat, Jean-Daniel
last_name: Boissonnat
- first_name: Herbert
full_name: Herbert Edelsbrunner
id: 3FB178DA-F248-11E8-B48F-1D18A9856A87
last_name: Edelsbrunner
orcid: 0000-0002-9823-6833
citation:
ama: 'Attali D, Boissonnat J, Edelsbrunner H. Stability and computation of medial
axes: a state-of-the-art report. In: Mathematical Foundations of Scientific
Visualization, Computer Graphics, and Massive Data Exploration. Springer;
2009:109-125. doi:10.1007/b106657_6'
apa: 'Attali, D., Boissonnat, J., & Edelsbrunner, H. (2009). Stability and computation
of medial axes: a state-of-the-art report. In Mathematical Foundations of Scientific
Visualization, Computer Graphics, and Massive Data Exploration (pp. 109–125).
Springer. https://doi.org/10.1007/b106657_6'
chicago: 'Attali, Dominique, Jean Boissonnat, and Herbert Edelsbrunner. “Stability
and Computation of Medial Axes: A State-of-the-Art Report.” In Mathematical
Foundations of Scientific Visualization, Computer Graphics, and Massive Data Exploration,
109–25. Springer, 2009. https://doi.org/10.1007/b106657_6.'
ieee: 'D. Attali, J. Boissonnat, and H. Edelsbrunner, “Stability and computation
of medial axes: a state-of-the-art report,” in Mathematical Foundations of
Scientific Visualization, Computer Graphics, and Massive Data Exploration,
Springer, 2009, pp. 109–125.'
ista: 'Attali D, Boissonnat J, Edelsbrunner H. 2009.Stability and computation of
medial axes: a state-of-the-art report. In: Mathematical Foundations of Scientific
Visualization, Computer Graphics, and Massive Data Exploration. Mathematics and
Visualization, , 109–125.'
mla: 'Attali, Dominique, et al. “Stability and Computation of Medial Axes: A State-of-the-Art
Report.” Mathematical Foundations of Scientific Visualization, Computer Graphics,
and Massive Data Exploration, Springer, 2009, pp. 109–25, doi:10.1007/b106657_6.'
short: D. Attali, J. Boissonnat, H. Edelsbrunner, in:, Mathematical Foundations
of Scientific Visualization, Computer Graphics, and Massive Data Exploration,
Springer, 2009, pp. 109–125.
date_created: 2018-12-11T12:04:03Z
date_published: 2009-06-22T00:00:00Z
date_updated: 2021-01-12T07:44:25Z
day: '22'
doi: 10.1007/b106657_6
extern: 1
main_file_link:
- open_access: '0'
url: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.103.9122
month: '06'
page: 109 - 125
publication: Mathematical Foundations of Scientific Visualization, Computer Graphics,
and Massive Data Exploration
publication_status: published
publisher: Springer
publist_id: '2807'
quality_controlled: 0
status: public
title: 'Stability and computation of medial axes: a state-of-the-art report'
type: book_chapter
year: '2009'
...
---
_id: '3675'
abstract:
- lang: eng
text: "Sex and recombination have long been seen as adaptations that facilitate
natural selection by generating favorable variations. If recombination is to aid
selection, there must be negative linkage disequilibria—favorable alleles must
be found together less often than expected by chance. These negative linkage disequilibria
can be generated directly by selection, but this must involve negative epistasis
of just the right strength, which is not expected, from either experiment or theory.
Random drift provides a more general source of negative associations: Favorable
mutations almost always arise on different genomes, and negative associations
tend to persist, precisely because they shield variation from selection.\r\n\r\nWe
can understand how recombination aids adaptation by determining the maximum possible
rate of adaptation. With unlinked loci, this rate increases only logarithmically
with the influx of favorable mutations. With a linear genome, a scaling argument
shows that in a large population, the rate of adaptive substitution depends only
on the expected rate in the absence of interference, divided by the total rate
of recombination. A two-locus approximation predicts an upper bound on the rate
of substitution, proportional to recombination rate.\r\n\r\nIf associations between
linked loci do impede adaptation, there can be substantial selection for modifiers
that increase recombination. Whether this can account for the maintenance of high
rates of sex and recombination depends on the extent of selection. It is clear
that the rate of species-wide substitutions is typically far too low to generate
appreciable selection for recombination. However, local sweeps within a subdivided
population may be effective."
acknowledgement: Royal Society and the Engineering and Physical Sciences for support
(GR/ T11753/01)
author:
- first_name: Nicholas H
full_name: Barton, Nicholas H
id: 4880FE40-F248-11E8-B48F-1D18A9856A87
last_name: Barton
orcid: 0000-0002-8548-5240
citation:
ama: 'Barton NH. Why sex and recombination? . In: Cold Spring Harbor Symposia
on Quantitative Biology. Vol 74. Cold Spring Harbor Laboratory Press; 2009:187-195.
doi:10.1101/sqb.2009.74.030'
apa: Barton, N. H. (2009). Why sex and recombination? . In Cold Spring Harbor
Symposia on Quantitative Biology (Vol. 74, pp. 187–195). Cold Spring Harbor
Laboratory Press. https://doi.org/10.1101/sqb.2009.74.030
chicago: Barton, Nicholas H. “Why Sex and Recombination? .” In Cold Spring Harbor
Symposia on Quantitative Biology, 74:187–95. Cold Spring Harbor Laboratory
Press, 2009. https://doi.org/10.1101/sqb.2009.74.030.
ieee: N. H. Barton, “Why sex and recombination? ,” in Cold Spring Harbor Symposia
on Quantitative Biology, vol. 74, Cold Spring Harbor Laboratory Press, 2009,
pp. 187–195.
ista: 'Barton NH. 2009.Why sex and recombination? . In: Cold Spring Harbor Symposia
on Quantitative Biology. vol. 74, 187–195.'
mla: Barton, Nicholas H. “Why Sex and Recombination? .” Cold Spring Harbor Symposia
on Quantitative Biology, vol. 74, Cold Spring Harbor Laboratory Press, 2009,
pp. 187–95, doi:10.1101/sqb.2009.74.030.
short: N.H. Barton, in:, Cold Spring Harbor Symposia on Quantitative Biology, Cold
Spring Harbor Laboratory Press, 2009, pp. 187–195.
date_created: 2018-12-11T12:04:33Z
date_published: 2009-11-10T00:00:00Z
date_updated: 2021-01-12T07:45:04Z
day: '10'
department:
- _id: NiBa
doi: 10.1101/sqb.2009.74.030
intvolume: ' 74'
language:
- iso: eng
month: '11'
oa_version: None
page: 187 - 195
publication: Cold Spring Harbor Symposia on Quantitative Biology
publication_status: published
publisher: Cold Spring Harbor Laboratory Press
publist_id: '2708'
quality_controlled: '1'
scopus_import: 1
status: public
title: 'Why sex and recombination? '
type: book_chapter
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 74
year: '2009'
...
---
_id: '3690'
abstract:
- lang: eng
text: An important cue to high level scene understanding is to analyze the objects
in the scene and their behavior and interactions. In this paper, we study the
problem of classification of activities in videos, as this is an integral component
of any scene understanding system, and present a novel approach for recognizing
human action categories in videos by combining information from appearance and
motion of human body parts. Our approach is based on tracking human body parts
by using mixture particle filters and then clustering the particles using local
non - parametric clustering, hence associating a local set of particles to each
cluster mode. The trajectory of these cluster modes provides the "motion"
information and the "appearance" information is provided by the statistical
information about the relative motion of these local set of particles over a number
of frames. Later we use a "Bag of Words" model to build one histogram
per video sequence from the set of these robust appearance and motion descriptors.
These histograms provide us characteristic information which helps us to discriminate
among various human actions which ultimately helps us in better understanding
of the complete scene. We tested our approach on the standard KTH and Weizmann
human action dataseis and the results were comparable to the state of the art
methods. Additionally our approach is able to distinguish between activities that
involve the motion of complete body from those in which only certain body parts
move. In other words, our method discriminates well between activities with "global
body motion" like running, jogging etc. and "local motion" like
waving, boxing etc.
author:
- first_name: Paramveer
full_name: Dhillon, Paramveer S
last_name: Dhillon
- first_name: Sebastian
full_name: Nowozin, Sebastian
last_name: Nowozin
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Dhillon P, Nowozin S, Lampert C. Combining appearance and motion for human
action classification in videos. In: IEEE; 2009:22-29. doi:10.1109/CVPRW.2009.5204237'
apa: 'Dhillon, P., Nowozin, S., & Lampert, C. (2009). Combining appearance and
motion for human action classification in videos (pp. 22–29). Presented at the
CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPRW.2009.5204237'
chicago: Dhillon, Paramveer, Sebastian Nowozin, and Christoph Lampert. “Combining
Appearance and Motion for Human Action Classification in Videos,” 22–29. IEEE,
2009. https://doi.org/10.1109/CVPRW.2009.5204237.
ieee: 'P. Dhillon, S. Nowozin, and C. Lampert, “Combining appearance and motion
for human action classification in videos,” presented at the CVPR: Computer Vision
and Pattern Recognition, 2009, no. 174, pp. 22–29.'
ista: 'Dhillon P, Nowozin S, Lampert C. 2009. Combining appearance and motion for
human action classification in videos. CVPR: Computer Vision and Pattern Recognition,
22–29.'
mla: Dhillon, Paramveer, et al. Combining Appearance and Motion for Human Action
Classification in Videos. no. 174, IEEE, 2009, pp. 22–29, doi:10.1109/CVPRW.2009.5204237.
short: P. Dhillon, S. Nowozin, C. Lampert, in:, IEEE, 2009, pp. 22–29.
conference:
name: 'CVPR: Computer Vision and Pattern Recognition'
date_created: 2018-12-11T12:04:38Z
date_published: 2009-01-01T00:00:00Z
date_updated: 2021-01-12T07:48:59Z
day: '01'
doi: 10.1109/CVPRW.2009.5204237
extern: 1
issue: '174'
month: '01'
page: 22 - 29
publication_status: published
publisher: IEEE
publist_id: '2675'
quality_controlled: 0
status: public
title: Combining appearance and motion for human action classification in videos
type: conference
year: '2009'
...
---
_id: '3696'
abstract:
- lang: eng
text: Discriminative techniques, such as conditional random fields (CRFs) or structure
aware maximum-margin techniques (maximum margin Markov networks (M3N), structured
output support vector machines (S-SVM)), are state-of-the-art in the prediction
of structured data. However, to achieve good results these techniques require
complete and reliable ground truth, which is not always available in realistic
problems. Furthermore, training either CRFs or margin-based techniques is computationally
costly, because the runtime of current training methods depends not only on the
size of the training set but also on properties of the output space to which the
training samples are assigned. We propose an alternative model for structured
output prediction, Joint Kernel Support Estimation (JKSE), which is rather generative
in nature as it relies on estimating the joint probability density of samples
and labels in the training set. This makes it tolerant against incomplete or incorrect
labels and also opens the possibility of learning in situations where more than
one output label can be considered correct. At the same time, we avoid typical
problems of generative models as we do not attempt to learn the full joint probability
distribution, but we model only its support in a joint reproducing kernel Hilbert
space. As a consequence, JKSE training is possible by an adaption of the classical
one-class SVM procedure. The resulting optimization problem is convex and efficiently
solvable even with tens of thousands of training examples. A particular advantage
of JKSE is that the training speed depends only on the size of the training set,
and not on the total size of the label space. No inference step during training
is required (as M3N and S-SVM would) nor do we have calculate a partition function
(as CRFs do). Experiments on realistic data show that, for suitable kernel functions,
our method works efficiently and robustly in situations that discriminative techniques
have problems with or that are computationally infeasible for them.
author:
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Matthew
full_name: Blaschko,Matthew B
last_name: Blaschko
citation:
ama: Lampert C, Blaschko M. Structured prediction by joint kernel support estimation.
Machine Learning. 2009;77(2-3):249-269. doi:10.1007/s10994-009-5111-0
apa: Lampert, C., & Blaschko, M. (2009). Structured prediction by joint kernel
support estimation. Machine Learning. Springer. https://doi.org/10.1007/s10994-009-5111-0
chicago: Lampert, Christoph, and Matthew Blaschko. “Structured Prediction by Joint
Kernel Support Estimation.” Machine Learning. Springer, 2009. https://doi.org/10.1007/s10994-009-5111-0.
ieee: C. Lampert and M. Blaschko, “Structured prediction by joint kernel support
estimation,” Machine Learning, vol. 77, no. 2–3. Springer, pp. 249–269,
2009.
ista: Lampert C, Blaschko M. 2009. Structured prediction by joint kernel support
estimation. Machine Learning. 77(2–3), 249–269.
mla: Lampert, Christoph, and Matthew Blaschko. “Structured Prediction by Joint Kernel
Support Estimation.” Machine Learning, vol. 77, no. 2–3, Springer, 2009,
pp. 249–69, doi:10.1007/s10994-009-5111-0.
short: C. Lampert, M. Blaschko, Machine Learning 77 (2009) 249–269.
date_created: 2018-12-11T12:04:40Z
date_published: 2009-04-07T00:00:00Z
date_updated: 2021-01-12T07:49:01Z
day: '07'
doi: 10.1007/s10994-009-5111-0
extern: 1
intvolume: ' 77'
issue: 2-3
license: https://creativecommons.org/licenses/by-nc/4.0/
month: '04'
page: 249 - 269
publication: Machine Learning
publication_status: published
publisher: Springer
publist_id: '2663'
quality_controlled: 0
status: public
title: Structured prediction by joint kernel support estimation
tmp:
image: /images/cc_by_nc.png
legal_code_url: https://creativecommons.org/licenses/by-nc/4.0/legalcode
name: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
short: CC BY-NC (4.0)
type: journal_article
volume: 77
year: '2009'
...
---
_id: '3699'
abstract:
- lang: eng
text: Kernel Canonical Correlation Analysis (KCCA) is a general technique for subspace
learning that incorporates principal components analysis (PCA) and Fisher linear
discriminant analysis (LDA) as special cases. By finding directions that maximize
correlation, CCA learns representations tied more closely to underlying process
generating the the data and can ignore high-variance noise directions. However,
for data where acquisition in a given modality is expensive or otherwise limited,
CCA may suffer from small sample effects. We propose to use semisupervised Laplacian
regularization to utilize data that are present in only one modality. This approach
is able to find highly correlated directions that also lie along the data manifold,
resulting in a more robust estimate of correlated subspaces. Functional magnetic
resonance imaging (fMRI) acquired data are naturally amenable to subspace techniques
as data are well aligned. fMRI data of the human brain are a particularly interesting
candidate. In this study we implemented various supervised and semi-supervised
versions of CCA on human fMRI data, with regression to single and multivariate
labels (corresponding to video content subjects viewed during the image acquisition).
In each variate condition, the semi-supervised variants of CCA performed better
than the supervised variants, including a supervised variant with Laplacian regularization.
We additionally analyze the weights learned by the regression in order to infer
brain regions that are important to different types of visual processing.
author:
- first_name: Matthew
full_name: Blaschko,Matthew B
last_name: Blaschko
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Andreas
full_name: Bartels, Andreas
last_name: Bartels
citation:
ama: Blaschko M, Lampert C, Bartels A. Semi-Supervised Analysis of Human FMRI
Data. Berlin Institute of Technology; 2009.
apa: 'Blaschko, M., Lampert, C., & Bartels, A. (2009). Semi-supervised analysis
of human fMRI data. BBCI: Berlin Brain-Computer Interface Workshop - Advances
in Neurotechnology. Berlin Institute of Technology.'
chicago: 'Blaschko, Matthew, Christoph Lampert, and Andreas Bartels. Semi-Supervised
Analysis of Human FMRI Data. BBCI: Berlin Brain-Computer Interface Workshop
- Advances in Neurotechnology. Berlin Institute of Technology, 2009.'
ieee: M. Blaschko, C. Lampert, and A. Bartels, Semi-supervised analysis of human
fMRI data. Berlin Institute of Technology, 2009.
ista: Blaschko M, Lampert C, Bartels A. 2009. Semi-supervised analysis of human
fMRI data, Berlin Institute of Technology,p.
mla: 'Blaschko, Matthew, et al. “Semi-Supervised Analysis of Human FMRI Data.” BBCI:
Berlin Brain-Computer Interface Workshop - Advances in Neurotechnology, Berlin
Institute of Technology, 2009.'
short: M. Blaschko, C. Lampert, A. Bartels, Semi-Supervised Analysis of Human FMRI
Data, Berlin Institute of Technology, 2009.
date_created: 2018-12-11T12:04:41Z
date_published: 2009-07-10T00:00:00Z
date_updated: 2019-04-26T07:22:33Z
day: '10'
extern: 1
main_file_link:
- open_access: '0'
url: http://pubman.mpdl.mpg.de/pubman/faces/viewItemOverviewPage.jsp?itemId=escidoc:1789281
month: '07'
publication: 'BBCI: Berlin Brain-Computer Interface Workshop - Advances in Neurotechnology'
publication_status: published
publisher: Berlin Institute of Technology
publist_id: '2661'
quality_controlled: 0
status: public
title: Semi-supervised analysis of human fMRI data
type: conference_poster
year: '2009'
...
---
_id: '3703'
abstract:
- lang: eng
text: Recent research has shown that the use of contextual cues significantly improves
performance in sliding window type localization systems. In this work, we propose
a method that incorporates both global and local context information through appropriately
defined kernel functions. In particular, we make use of a weighted combination
of kernels defined over local spatial regions, as well as a global context kernel.
The relative importance of the context contributions is learned automatically,
and the resulting discriminant function is of a form such that localization at
test time can be solved efficiently using a branch and bound optimization scheme.
By specifying context directly with a kernel learning approach, we achieve high
localization accuracy with a simple and efficient representation. This is in contrast
to other systems that incorporate context for which expensive inference needs
to be done at test time. We show experimentally on the PASCAL VOC datasets that
the inclusion of context can significantly improve localization performance, provided
the relative contributions of context cues are learned appropriately.
acknowledgement: The research leading to these results has received funding from the
European Research Council under the European Community’s Seventh Framework Programme
(FP7/2007- 2013) / ERC grant agreement no. 228180. This work was funded in part
by the EC project CLASS, IST 027978, and the PASCAL2 network of excellence. The
first author is supported by the Royal Academy of Engineering through a Newton International
Fellowship.
alternative_title:
- Proceedings of the BMVC
author:
- first_name: Matthew
full_name: Blaschko,Matthew B
last_name: Blaschko
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Blaschko M, Lampert C. Object localization with global and local context kernels.
In: BMVA Press; 2009:1-11. doi:10.5244/C.23.63'
apa: 'Blaschko, M., & Lampert, C. (2009). Object localization with global and
local context kernels (pp. 1–11). Presented at the BMVC: British Machine Vision
Conference, BMVA Press. https://doi.org/10.5244/C.23.63'
chicago: Blaschko, Matthew, and Christoph Lampert. “Object Localization with Global
and Local Context Kernels,” 1–11. BMVA Press, 2009. https://doi.org/10.5244/C.23.63.
ieee: 'M. Blaschko and C. Lampert, “Object localization with global and local context
kernels,” presented at the BMVC: British Machine Vision Conference, 2009, pp.
1–11.'
ista: 'Blaschko M, Lampert C. 2009. Object localization with global and local context
kernels. BMVC: British Machine Vision Conference, Proceedings of the BMVC, , 1–11.'
mla: Blaschko, Matthew, and Christoph Lampert. Object Localization with Global
and Local Context Kernels. BMVA Press, 2009, pp. 1–11, doi:10.5244/C.23.63.
short: M. Blaschko, C. Lampert, in:, BMVA Press, 2009, pp. 1–11.
conference:
name: 'BMVC: British Machine Vision Conference'
date_created: 2018-12-11T12:04:42Z
date_published: 2009-09-10T00:00:00Z
date_updated: 2021-01-12T07:51:36Z
day: '10'
doi: 10.5244/C.23.63
extern: 1
main_file_link:
- open_access: '0'
url: http://www.bmva.org/bmvc/2009/Papers/Paper228/Paper228.pdf
month: '09'
page: 1 - 11
publication_status: published
publisher: BMVA Press
publist_id: '2655'
quality_controlled: 0
status: public
title: Object localization with global and local context kernels
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: conference
year: '2009'
...
---
_id: '3704'
abstract:
- lang: eng
text: We study the problem of object classification when training and test classes
are disjoint, i.e. no training examples of the target classes are available. This
setup has hardly been studied in computer vision research, but it is the rule
rather than the exception, because the world contains tens of thousands of different
object classes and for only a very few of them image, collections have been formed
and annotated with suitable class labels. In this paper, we tackle the problem
by introducing attribute-based classification. It performs object detection based
on a human-specified high-level description of the target objects instead of training
images. The description consists of arbitrary semantic attributes, like shape,
color or even geographic information. Because such properties transcend the specific
learning task at hand, they can be pre-learned, e.g. from image datasets unrelated
to the current task. Afterwards, new classes can be detected based on their attribute
representation, without the need for a new training phase. In order to evaluate
our method and to facilitate research in this area, we have assembled a new large-scale
dataset, ldquoAnimals with Attributesrdquo, of over 30,000 animal images that
match the 50 classes in Osherson‘s classic table of how strongly humans associate
85 semantic attributes with animal classes. Our experiments show that by using
an attribute layer it is indeed possible to build a learning object detection
system that does not require any training images of the target classes.
acknowledgement: This work was funded in part by the EC project CLASS, IST 027978,
and the PASCAL2 network of excellence.
author:
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Hannes
full_name: Nickisch,Hannes
last_name: Nickisch
- first_name: Stefan
full_name: Harmeling,Stefan
last_name: Harmeling
citation:
ama: 'Lampert C, Nickisch H, Harmeling S. Learning to detect unseen object classes
by between-class attribute transfer. In: IEEE; 2009:951-958. doi:10.1109/CVPR.2009.5206594'
apa: 'Lampert, C., Nickisch, H., & Harmeling, S. (2009). Learning to detect
unseen object classes by between-class attribute transfer (pp. 951–958). Presented
at the CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPR.2009.5206594'
chicago: Lampert, Christoph, Hannes Nickisch, and Stefan Harmeling. “Learning to
Detect Unseen Object Classes by Between-Class Attribute Transfer,” 951–58. IEEE,
2009. https://doi.org/10.1109/CVPR.2009.5206594.
ieee: 'C. Lampert, H. Nickisch, and S. Harmeling, “Learning to detect unseen object
classes by between-class attribute transfer,” presented at the CVPR: Computer
Vision and Pattern Recognition, 2009, pp. 951–958.'
ista: 'Lampert C, Nickisch H, Harmeling S. 2009. Learning to detect unseen object
classes by between-class attribute transfer. CVPR: Computer Vision and Pattern
Recognition, 951–958.'
mla: Lampert, Christoph, et al. Learning to Detect Unseen Object Classes by Between-Class
Attribute Transfer. IEEE, 2009, pp. 951–58, doi:10.1109/CVPR.2009.5206594.
short: C. Lampert, H. Nickisch, S. Harmeling, in:, IEEE, 2009, pp. 951–958.
conference:
name: 'CVPR: Computer Vision and Pattern Recognition'
date_created: 2018-12-11T12:04:43Z
date_published: 2009-06-20T00:00:00Z
date_updated: 2021-01-12T07:51:36Z
day: '20'
doi: 10.1109/CVPR.2009.5206594
extern: 1
month: '06'
page: 951 - 958
publication_status: published
publisher: IEEE
publist_id: '2652'
quality_controlled: 0
status: public
title: Learning to detect unseen object classes by between-class attribute transfer
type: conference
year: '2009'
...
---
_id: '3707'
abstract:
- lang: eng
text: Over the last years, kernel methods have established themselves as powerful
tools for computer vision researchers as well as for practitioners. In this tutorial,
we give an introduction to kernel methods in computer vision from a geometric
perspective, introducing not only the ubiquitous support vector machines, but
also less known techniques for regression, dimensionality reduction, outlier detection
and clustering. Additionally, we give an outlook on very recent, non-classical
techniques for the prediction of structure data, for the estimation of statistical
dependency and for learning the kernel function itself. All methods are illustrated
with examples of successful application from the recent computer vision research
literature.
alternative_title:
- Foundations and Trends® in Computer Graphics and Vision
article_processing_charge: No
author:
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: Lampert C. Kernel Methods in Computer Vision. Vol 4. now publishers;
2009. doi:10.1561/0600000027
apa: Lampert, C. (2009). Kernel Methods in Computer Vision (Vol. 4). now
publishers. https://doi.org/10.1561/0600000027
chicago: Lampert, Christoph. Kernel Methods in Computer Vision. Vol. 4. now
publishers, 2009. https://doi.org/10.1561/0600000027.
ieee: C. Lampert, Kernel Methods in Computer Vision, vol. 4. now publishers,
2009.
ista: Lampert C. 2009. Kernel Methods in Computer Vision, now publishers, 112p.
mla: Lampert, Christoph. Kernel Methods in Computer Vision. Vol. 4, now publishers,
2009, doi:10.1561/0600000027.
short: C. Lampert, Kernel Methods in Computer Vision, now publishers, 2009.
date_created: 2018-12-11T12:04:44Z
date_published: 2009-09-03T00:00:00Z
date_updated: 2021-12-21T15:38:43Z
day: '03'
doi: 10.1561/0600000027
extern: '1'
intvolume: ' 4'
language:
- iso: eng
month: '09'
oa_version: None
page: '112'
publication_identifier:
eisbn:
- 978-1-60198-269-8
isbn:
- 978-1-60198-268-1
publication_status: published
publisher: now publishers
publist_id: '2651'
quality_controlled: '1'
status: public
title: Kernel Methods in Computer Vision
type: book
user_id: 8b945eb4-e2f2-11eb-945a-df72226e66a9
volume: 4
year: '2009'
...
---
_id: '3708'
abstract:
- lang: eng
text: Markov random field (MRF, CRF) models are popular in computer vision. However,
in order to be computationally tractable they are limited to incorporate only
local interactions and cannot model global properties, such as connectedness,
which is a potentially useful high-level prior for object segmentation. In this
work, we overcome this limitation by deriving a potential function that enforces
the output labeling to be connected and that can naturally be used in the framework
of recent MAP-MRF LP relaxations. Using techniques from polyhedral combinatorics,
we show that a provably tight approximation to the MAP solution of the resulting
MRF can still be found efficiently by solving a sequence of max-flow problems.
The efficiency of the inference procedure also allows us to learn the parameters
of a MRF with global connectivity potentials by means of a cutting plane algorithm.
We experimentally evaluate our algorithm on both synthetic data and on the challenging
segmentation task of the PASCAL VOC 2008 data set. We show that in both cases
the addition of a connectedness prior significantly reduces the segmentation error.
acknowledgement: |-
Conference Information URL:
http://www.cvpr2009.org/
author:
- first_name: Sebastian
full_name: Nowozin, Sebastian
last_name: Nowozin
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Nowozin S, Lampert C. Global connectivity potentials for random field models.
In: IEEE; 2009:818-825. doi:10.1109/CVPR.2009.5206567'
apa: 'Nowozin, S., & Lampert, C. (2009). Global connectivity potentials for
random field models (pp. 818–825). Presented at the CVPR: Computer Vision and
Pattern Recognition, IEEE. https://doi.org/10.1109/CVPR.2009.5206567'
chicago: Nowozin, Sebastian, and Christoph Lampert. “Global Connectivity Potentials
for Random Field Models,” 818–25. IEEE, 2009. https://doi.org/10.1109/CVPR.2009.5206567.
ieee: 'S. Nowozin and C. Lampert, “Global connectivity potentials for random field
models,” presented at the CVPR: Computer Vision and Pattern Recognition, 2009,
pp. 818–825.'
ista: 'Nowozin S, Lampert C. 2009. Global connectivity potentials for random field
models. CVPR: Computer Vision and Pattern Recognition, 818–825.'
mla: Nowozin, Sebastian, and Christoph Lampert. Global Connectivity Potentials
for Random Field Models. IEEE, 2009, pp. 818–25, doi:10.1109/CVPR.2009.5206567.
short: S. Nowozin, C. Lampert, in:, IEEE, 2009, pp. 818–825.
conference:
name: 'CVPR: Computer Vision and Pattern Recognition'
date_created: 2018-12-11T12:04:44Z
date_published: 2009-06-20T00:00:00Z
date_updated: 2021-01-12T07:51:38Z
day: '20'
doi: 10.1109/CVPR.2009.5206567
extern: 1
month: '06'
page: 818 - 825
publication_status: published
publisher: IEEE
publist_id: '2649'
quality_controlled: 0
status: public
title: Global connectivity potentials for random field models
type: conference
year: '2009'
...
---
_id: '3709'
abstract:
- lang: eng
text: We study the task of detecting the occurrence of objects in large image collections
or in videos, a problem that combines aspects of content based image retrieval
and object localization. While most previous approaches are either limited to
special kinds of queries, or do not scale to large image sets, we propose a new
method, efficient subimage retrieval (ESR), which is at the same time very flexible
and very efficient. Relying on a two-layered branch-and-bound setup, ESR performs
object-based image retrieval in sets of 100,000 or more images within seconds.
An extensive evaluation on several datasets shows that ESR is not only very fast,
but it also achieves detection accuracies that are on par with or superior to
previously published methods for object-based image retrieval.
acknowledgement: |-
Conference Information URL:
http://www.iccv2009.org/
author:
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Lampert C. Detecting objects in large image collections and videos by efficient
subimage retrieval. In: IEEE; 2009:987-994. doi:10.1109/ICCV.2009.5459359'
apa: 'Lampert, C. (2009). Detecting objects in large image collections and videos
by efficient subimage retrieval (pp. 987–994). Presented at the ICCV: International
Conference on Computer Vision, IEEE. https://doi.org/10.1109/ICCV.2009.5459359'
chicago: Lampert, Christoph. “Detecting Objects in Large Image Collections and Videos
by Efficient Subimage Retrieval,” 987–94. IEEE, 2009. https://doi.org/10.1109/ICCV.2009.5459359.
ieee: 'C. Lampert, “Detecting objects in large image collections and videos by efficient
subimage retrieval,” presented at the ICCV: International Conference on Computer
Vision, 2009, pp. 987–994.'
ista: 'Lampert C. 2009. Detecting objects in large image collections and videos
by efficient subimage retrieval. ICCV: International Conference on Computer Vision,
987–994.'
mla: Lampert, Christoph. Detecting Objects in Large Image Collections and Videos
by Efficient Subimage Retrieval. IEEE, 2009, pp. 987–94, doi:10.1109/ICCV.2009.5459359.
short: C. Lampert, in:, IEEE, 2009, pp. 987–994.
conference:
name: 'ICCV: International Conference on Computer Vision'
date_created: 2018-12-11T12:04:44Z
date_published: 2009-09-29T00:00:00Z
date_updated: 2021-01-12T07:51:38Z
day: '29'
doi: 10.1109/ICCV.2009.5459359
extern: 1
month: '09'
page: 987 - 994
publication_status: published
publisher: IEEE
publist_id: '2647'
quality_controlled: 0
status: public
title: Detecting objects in large image collections and videos by efficient subimage
retrieval
type: conference
year: '2009'
...
---
_id: '3710'
abstract:
- lang: eng
text: Most successful object recognition systems rely on binary classification,
deciding only if an object is present or not, but not providing information on
the actual object location. To estimate the object‘s location, one can take a
sliding window approach, but this strongly increases the computational cost because
the classifier or similarity function has to be evaluated over a large set of
candidate subwindows. In this paper, we propose a simple yet powerful branch and
bound scheme that allows efficient maximization of a large class of quality functions
over all possible subimages. It converges to a globally optimal solution typically
in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive
or sliding window search. We show how our method is applicable to different object
detection and image retrieval scenarios. The achieved speedup allows the use of
classifiers for localization that formerly were considered too slow for this task,
such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based
on the chi^2 distance. We demonstrate state-of-the-art localization performance
of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set,
and in the PASCAL VOC 2007 competition.
acknowledgement: 'This work was funded in part by the EU projects CLASS, IST 027978,
and PerAct, EST 504321. '
author:
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Matthew
full_name: Blaschko,Matthew B
last_name: Blaschko
- first_name: Thomas
full_name: Hofmann,Thomas
last_name: Hofmann
citation:
ama: 'Lampert C, Blaschko M, Hofmann T. Efficient subwindow search: A branch and
bound framework for object localization. IEEE Transactions on Pattern Analysis
and Machine Intelligence. 2009;31(12):2129-2142. doi:10.1109/TPAMI.2009.144'
apa: 'Lampert, C., Blaschko, M., & Hofmann, T. (2009). Efficient subwindow search:
A branch and bound framework for object localization. IEEE Transactions on
Pattern Analysis and Machine Intelligence. IEEE. https://doi.org/10.1109/TPAMI.2009.144'
chicago: 'Lampert, Christoph, Matthew Blaschko, and Thomas Hofmann. “Efficient Subwindow
Search: A Branch and Bound Framework for Object Localization.” IEEE Transactions
on Pattern Analysis and Machine Intelligence. IEEE, 2009. https://doi.org/10.1109/TPAMI.2009.144.'
ieee: 'C. Lampert, M. Blaschko, and T. Hofmann, “Efficient subwindow search: A branch
and bound framework for object localization,” IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 31, no. 12. IEEE, pp. 2129–2142, 2009.'
ista: 'Lampert C, Blaschko M, Hofmann T. 2009. Efficient subwindow search: A branch
and bound framework for object localization. IEEE Transactions on Pattern Analysis
and Machine Intelligence. 31(12), 2129–2142.'
mla: 'Lampert, Christoph, et al. “Efficient Subwindow Search: A Branch and Bound
Framework for Object Localization.” IEEE Transactions on Pattern Analysis and
Machine Intelligence, vol. 31, no. 12, IEEE, 2009, pp. 2129–42, doi:10.1109/TPAMI.2009.144.'
short: C. Lampert, M. Blaschko, T. Hofmann, IEEE Transactions on Pattern Analysis
and Machine Intelligence 31 (2009) 2129–2142.
date_created: 2018-12-11T12:04:45Z
date_published: 2009-12-01T00:00:00Z
date_updated: 2021-01-12T07:51:39Z
day: '01'
doi: 10.1109/TPAMI.2009.144
extern: 1
intvolume: ' 31'
issue: '12'
main_file_link:
- open_access: '0'
url: http://www2.computer.org/portal/web/csdl/doi/10.1109/TPAMI.2009.144
month: '12'
page: 2129 - 2142
publication: IEEE Transactions on Pattern Analysis and Machine Intelligence
publication_status: published
publisher: IEEE
publist_id: '2648'
quality_controlled: 0
status: public
title: 'Efficient subwindow search: A branch and bound framework for object localization'
type: journal_article
volume: 31
year: '2009'
...
---
_id: '3711'
abstract:
- lang: eng
text: An important cue to high level scene understanding is to analyze the objects
in the scene and their behavior and interactions. In this paper, we study the
problem of classification of activities in videos, as this is an integral component
of any scene understanding system, and present a novel approach for recognizing
human action categories in videos by combining information from appearance and
motion of human body parts. Our approach is based on tracking human body parts
by using mixture particle filters and then clustering the particles using local
non - parametric clustering, hence associating a local set of particles to each
cluster mode. The trajectory of these cluster modes provides the ldquomotionrdquo
information and the ldquoappearancerdquo information is provided by the statistical
information about the relative motion of these local set of particles over a number
of frames. Later we use a ldquoBag of Wordsrdquo model to build one histogram
per video sequence from the set of these robust appearance and motion descriptors.
These histograms provide us characteristic information which helps us to discriminate
among various human actions which ultimately helps us in better understanding
of the complete scene. We tested our approach on the standard KTH and Weizmann
human action datasets and the results were comparable to the state of the art
methods. Additionally our approach is able to distinguish between activities that
involve the motion of complete body from those in which only certain body parts
move. In other words, our method discriminates well between activities with ldquoglobal
body motionrdquo like running, jogging etc. and ldquolocal motionrdquo like waving,
boxing etc.
author:
- first_name: Paramveer
full_name: Dhillon, Paramveer S
last_name: Dhillon
- first_name: Sebastian
full_name: Nowozin, Sebastian
last_name: Nowozin
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Dhillon P, Nowozin S, Lampert C. Combining appearance and motion for human
action classification in videos. In: IEEE; 2009:22-29. doi:10.1109/CVPRW.2009.5204237'
apa: 'Dhillon, P., Nowozin, S., & Lampert, C. (2009). Combining appearance and
motion for human action classification in videos (pp. 22–29). Presented at the
CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPRW.2009.5204237'
chicago: Dhillon, Paramveer, Sebastian Nowozin, and Christoph Lampert. “Combining
Appearance and Motion for Human Action Classification in Videos,” 22–29. IEEE,
2009. https://doi.org/10.1109/CVPRW.2009.5204237.
ieee: 'P. Dhillon, S. Nowozin, and C. Lampert, “Combining appearance and motion
for human action classification in videos,” presented at the CVPR: Computer Vision
and Pattern Recognition, 2009, pp. 22–29.'
ista: 'Dhillon P, Nowozin S, Lampert C. 2009. Combining appearance and motion for
human action classification in videos. CVPR: Computer Vision and Pattern Recognition,
22–29.'
mla: Dhillon, Paramveer, et al. Combining Appearance and Motion for Human Action
Classification in Videos. IEEE, 2009, pp. 22–29, doi:10.1109/CVPRW.2009.5204237.
short: P. Dhillon, S. Nowozin, C. Lampert, in:, IEEE, 2009, pp. 22–29.
conference:
name: 'CVPR: Computer Vision and Pattern Recognition'
date_created: 2018-12-11T12:04:45Z
date_published: 2009-08-18T00:00:00Z
date_updated: 2021-01-12T07:51:39Z
day: '18'
doi: 10.1109/CVPRW.2009.5204237
extern: 1
main_file_link:
- open_access: '0'
url: http://www.nowozin.net/sebastian/papers/dhillon2008actionclassification.pdf
month: '08'
page: 22 - 29
publication_status: published
publisher: IEEE
publist_id: '2645'
quality_controlled: 0
status: public
title: Combining appearance and motion for human action classification in videos
type: conference
year: '2009'
...
---
_id: '3715'
abstract:
- lang: eng
text: High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured
environments is essential for robotics and human motion analysis. However, building
a system that can adapt to arbitrary objects and a wide range of lighting conditions
is a challenging problem, especially if hard real-time constraints apply like
in robotics scenarios. In this work, we introduce a method for learning a discriminative
object tracking system based on the recent structured regression framework for
object localization. Using a kernel function that allows fast evaluation on the
GPU, the resulting system can process video streams at speed of 100 frames per
second or more. Consecutive frames in high speed video sequences are typically
very redundant, and for training an object detection system, it is sufficient
to have training labels from only a subset of all images. We propose an active
learning method that select training examples in a data-driven way, thereby minimizing
the required number of training labeling. Experiments on realistic data show that
the active learning is superior to previously used methods for dataset subsampling
for this task.
acknowledgement: |-
This work was funded in part by the EU project CLASS, IST 027978.
Conference Information URL: http://www.optecnet.de/veranstaltungen/2009/09/dagm-2009/
alternative_title:
- LNCS
author:
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Jan
full_name: Peters, Jan
last_name: Peters
citation:
ama: 'Lampert C, Peters J. Active structured learning for high-speed object detection.
In: Vol 5748. Springer; 2009:221-231. doi:10.1007/978-3-642-03798-6_23'
apa: 'Lampert, C., & Peters, J. (2009). Active structured learning for high-speed
object detection (Vol. 5748, pp. 221–231). Presented at the DAGM: German Association
For Pattern Recognition, Springer. https://doi.org/10.1007/978-3-642-03798-6_23'
chicago: Lampert, Christoph, and Jan Peters. “Active Structured Learning for High-Speed
Object Detection,” 5748:221–31. Springer, 2009. https://doi.org/10.1007/978-3-642-03798-6_23.
ieee: 'C. Lampert and J. Peters, “Active structured learning for high-speed object
detection,” presented at the DAGM: German Association For Pattern Recognition,
2009, vol. 5748, pp. 221–231.'
ista: 'Lampert C, Peters J. 2009. Active structured learning for high-speed object
detection. DAGM: German Association For Pattern Recognition, LNCS, vol. 5748,
221–231.'
mla: Lampert, Christoph, and Jan Peters. Active Structured Learning for High-Speed
Object Detection. Vol. 5748, Springer, 2009, pp. 221–31, doi:10.1007/978-3-642-03798-6_23.
short: C. Lampert, J. Peters, in:, Springer, 2009, pp. 221–231.
conference:
name: 'DAGM: German Association For Pattern Recognition'
date_created: 2018-12-11T12:04:46Z
date_published: 2009-10-07T00:00:00Z
date_updated: 2021-01-12T07:51:41Z
day: '07'
doi: 10.1007/978-3-642-03798-6_23
extern: 1
intvolume: ' 5748'
month: '10'
page: 221 - 231
publication_status: published
publisher: Springer
publist_id: '2642'
quality_controlled: 0
status: public
title: Active structured learning for high-speed object detection
type: conference
volume: 5748
year: '2009'
...
---
_id: '3717'
abstract:
- lang: eng
text: We introduce RTblob, an open-source real-time vision system for 3D object
detection that achieves over 200 Hz tracking speed with only off-the-shelf hardware
component. It allows fast and accurate tracking of colored objects in 3D without
expensive and often custom-built hardware, instead making use of the PC graphics
cards for the necessary image processing operations.
acknowledgement: 'IEEE Workshop URL: http://humanoidscv.ime.cmc.osaka-u.ac.jp/'
author:
- first_name: Christoph
full_name: Christoph Lampert
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Jan
full_name: Peters, Jan
last_name: Peters
citation:
ama: Lampert C, Peters J. A High-Speed Object Tracker from off-the-Shelf Components.
IEEE; 2009.
apa: 'Lampert, C., & Peters, J. (2009). A high-speed object tracker from
off-the-shelf components. ICCV: International Conference on Computer Vision.
IEEE.'
chicago: 'Lampert, Christoph, and Jan Peters. A High-Speed Object Tracker from
off-the-Shelf Components. ICCV: International Conference on Computer Vision.
IEEE, 2009.'
ieee: C. Lampert and J. Peters, A high-speed object tracker from off-the-shelf
components. IEEE, 2009.
ista: Lampert C, Peters J. 2009. A high-speed object tracker from off-the-shelf
components, IEEE,p.
mla: 'Lampert, Christoph, and Jan Peters. “A High-Speed Object Tracker from off-the-Shelf
Components.” ICCV: International Conference on Computer Vision, IEEE, 2009.'
short: C. Lampert, J. Peters, A High-Speed Object Tracker from off-the-Shelf Components,
IEEE, 2009.
date_created: 2018-12-11T12:04:47Z
date_published: 2009-09-27T00:00:00Z
date_updated: 2020-07-14T12:46:14Z
day: '27'
extern: 1
main_file_link:
- open_access: '0'
url: http://pubman.mpdl.mpg.de/pubman/faces/viewItemOverviewPage.jsp?itemId=escidoc:1789154
month: '09'
publication: 'ICCV: International Conference on Computer Vision'
publication_status: published
publisher: IEEE
publist_id: '2640'
quality_controlled: 0
status: public
title: A high-speed object tracker from off-the-shelf components
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: conference_poster
year: '2009'
...
---
_id: '3732'
abstract:
- lang: eng
text: 'Ising models with pairwise interactions are the least structured, or maximum-entropy,
probability distributions that exactly reproduce measured pairwise correlations
between spins. Here we use this equivalence to construct Ising models that describe
the correlated spiking activity of populations of 40 neurons in the salamander
retina responding to natural movies. We show that pairwise interactions between
neurons account for observed higher-order correlations, and that for groups of
10 or more neurons pairwise interactions can no longer be regarded as small perturbations
in an independent system. We then construct network ensembles that generalize
the network instances observed in the experiment, and study their thermodynamic
behavior and coding capacity. Based on this construction, we can also create synthetic
networks of 120 neurons, and find that with increasing size the networks operate
closer to a critical point and start exhibiting collective behaviors reminiscent
of spin glasses. We examine closely two such behaviors that could be relevant
for neural code: tuning of the network to the critical point to maximize the ability
to encode diverse stimuli, and using the metastable states of the Ising Hamiltonian
as neural code words.'
author:
- first_name: Gasper
full_name: Gasper Tkacik
id: 3D494DCA-F248-11E8-B48F-1D18A9856A87
last_name: Tkacik
orcid: 0000-0002-6699-1455
- first_name: Elad
full_name: Schneidman, Elad
last_name: Schneidman
- first_name: Michael
full_name: Berry, Michael J
last_name: Berry
- first_name: William
full_name: Bialek, William S
last_name: Bialek
citation:
ama: Tkačik G, Schneidman E, Berry M, Bialek W. Spin glass models for a network
of real neurons. ArXiv. 2009;q-NC.
apa: Tkačik, G., Schneidman, E., Berry, M., & Bialek, W. (2009). Spin glass
models for a network of real neurons. ArXiv. ArXiv.
chicago: Tkačik, Gašper, Elad Schneidman, Michael Berry, and William Bialek. “Spin
Glass Models for a Network of Real Neurons.” ArXiv. ArXiv, 2009.
ieee: G. Tkačik, E. Schneidman, M. Berry, and W. Bialek, “Spin glass models for
a network of real neurons,” ArXiv, vol. q-NC. ArXiv, 2009.
ista: Tkačik G, Schneidman E, Berry M, Bialek W. 2009. Spin glass models for a network
of real neurons. ArXiv, q-NC, .
mla: Tkačik, Gašper, et al. “Spin Glass Models for a Network of Real Neurons.” ArXiv,
vol. q-NC, ArXiv, 2009.
short: G. Tkačik, E. Schneidman, M. Berry, W. Bialek, ArXiv q-NC (2009).
date_created: 2018-12-11T12:04:52Z
date_published: 2009-01-01T00:00:00Z
date_updated: 2021-01-12T07:51:48Z
day: '01'
extern: 1
main_file_link:
- open_access: '1'
url: http://arxiv.org/abs/0912.5409v1
month: '01'
oa: 1
publication: ArXiv
publication_status: published
publisher: ArXiv
publist_id: '2496'
quality_controlled: 0
status: public
title: Spin glass models for a network of real neurons
type: preprint
volume: q-bio.NC
year: '2009'
...
---
_id: '3733'
abstract:
- lang: eng
text: Evolutionary theory predicts that a population in a new environment will accumulate
adaptive substitutions, but precisely how they accumulate is poorly understood.
The dynamics of adaptation depend on the underlying fitness landscape. Virtually
nothing is known about fitness landscapes in nature, and few methods allow us
to infer the landscape from empirical data. With a view toward this inference
problem, we have developed a theory that, in the weak-mutation limit, predicts
how a population's mean fitness and the number of accumulated substitutions are
expected to increase over time, depending on the underlying fitness landscape.
We find that fitness and substitution trajectories depend not on the full distribution
of fitness effects of available mutations but rather on the expected fixation
probability and the expected fitness increment of mutations. We introduce a scheme
that classifies landscapes in terms of the qualitative evolutionary dynamics they
produce. We show that linear substitution trajectories, long considered the hallmark
of neutral evolution, can arise even when mutations are strongly selected. Our
results provide a basis for understanding the dynamics of adaptation and for inferring
properties of an organism's fitness landscape from temporal data. Applying these
methods to data from a long-term experiment, we infer the sign and strength of
epistasis among beneficial mutations in the Escherichia coli genome.
author:
- first_name: Sergey
full_name: Kryazhimskiy,Sergey
last_name: Kryazhimskiy
- first_name: Gasper
full_name: Gasper Tkacik
id: 3D494DCA-F248-11E8-B48F-1D18A9856A87
last_name: Tkacik
orcid: 0000-0002-6699-1455
- first_name: Joshua
full_name: Plotkin,Joshua B
last_name: Plotkin
citation:
ama: Kryazhimskiy S, Tkačik G, Plotkin J. The dynamics of adaptation on correlated
fitness landscapes. PNAS. 2009;106(44):18638-18643. doi:10.1073/pnas.0905497106
apa: Kryazhimskiy, S., Tkačik, G., & Plotkin, J. (2009). The dynamics of adaptation
on correlated fitness landscapes. PNAS. National Academy of Sciences. https://doi.org/10.1073/pnas.0905497106
chicago: Kryazhimskiy, Sergey, Gašper Tkačik, and Joshua Plotkin. “The Dynamics
of Adaptation on Correlated Fitness Landscapes.” PNAS. National Academy
of Sciences, 2009. https://doi.org/10.1073/pnas.0905497106.
ieee: S. Kryazhimskiy, G. Tkačik, and J. Plotkin, “The dynamics of adaptation on
correlated fitness landscapes,” PNAS, vol. 106, no. 44. National Academy
of Sciences, pp. 18638–18643, 2009.
ista: Kryazhimskiy S, Tkačik G, Plotkin J. 2009. The dynamics of adaptation on correlated
fitness landscapes. PNAS. 106(44), 18638–18643.
mla: Kryazhimskiy, Sergey, et al. “The Dynamics of Adaptation on Correlated Fitness
Landscapes.” PNAS, vol. 106, no. 44, National Academy of Sciences, 2009,
pp. 18638–43, doi:10.1073/pnas.0905497106.
short: S. Kryazhimskiy, G. Tkačik, J. Plotkin, PNAS 106 (2009) 18638–18643.
date_created: 2018-12-11T12:04:52Z
date_published: 2009-01-01T00:00:00Z
date_updated: 2021-01-12T07:51:48Z
day: '01'
doi: 10.1073/pnas.0905497106
extern: 1
intvolume: ' 106'
issue: '44'
main_file_link:
- open_access: '0'
url: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2767361
month: '01'
page: 18638 - 18643
publication: PNAS
publication_status: published
publisher: National Academy of Sciences
publist_id: '2497'
quality_controlled: 0
status: public
title: The dynamics of adaptation on correlated fitness landscapes
type: journal_article
volume: 106
year: '2009'
...
---
_id: '3737'
abstract:
- lang: eng
text: In order to survive, reproduce, and (in multicellular organisms) differentiate,
cells must control the concentrations of the myriad different proteins that are
encoded in the genome. The precision of this control is limited by the inevitable
randomness of individual molecular events. Here we explore how cells can maximize
their control power in the presence of these physical limits; formally, we solve
the theoretical problem of maximizing the information transferred from inputs
to outputs when the number of available molecules is held fixed. We start with
the simplest version of the problem, in which a single transcription factor protein
controls the readout of one or more genes by binding to DNA. We further simplify
by assuming that this regulatory network operates in steady state, that the noise
is small relative to the available dynamic range, and that the target genes do
not interact. Even in this simple limit, we find a surprisingly rich set of optimal
solutions. Importantly, for each locally optimal regulatory network, all parameters
are determined once the physical constraints on the number of available molecules
are specified. Although we are solving an oversimplified version of the problem
facing real cells, we see parallels between the structure of these optimal solutions
and the behavior of actual genetic regulatory networks. Subsequent papers will
discuss more complete versions of the problem.
author:
- first_name: Gasper
full_name: Gasper Tkacik
id: 3D494DCA-F248-11E8-B48F-1D18A9856A87
last_name: Tkacik
orcid: 0000-0002-6699-1455
- first_name: Aleksandra
full_name: Walczak, Aleksandra M
last_name: Walczak
- first_name: William
full_name: Bialek, William S
last_name: Bialek
citation:
ama: Tkačik G, Walczak A, Bialek W. Optimizing information flow in small genetic
networks. Physical Review E Statistical Nonlinear and Soft Matter Physics.
2009;80(3). doi:10.1103/PhysRevE.80.031920
apa: Tkačik, G., Walczak, A., & Bialek, W. (2009). Optimizing information flow
in small genetic networks. Physical Review E Statistical Nonlinear and Soft
Matter Physics. American Institute of Physics. https://doi.org/10.1103/PhysRevE.80.031920
chicago: Tkačik, Gašper, Aleksandra Walczak, and William Bialek. “Optimizing Information
Flow in Small Genetic Networks.” Physical Review E Statistical Nonlinear and
Soft Matter Physics. American Institute of Physics, 2009. https://doi.org/10.1103/PhysRevE.80.031920.
ieee: G. Tkačik, A. Walczak, and W. Bialek, “Optimizing information flow in small
genetic networks,” Physical Review E Statistical Nonlinear and Soft Matter
Physics, vol. 80, no. 3. American Institute of Physics, 2009.
ista: Tkačik G, Walczak A, Bialek W. 2009. Optimizing information flow in small
genetic networks. Physical Review E Statistical Nonlinear and Soft Matter Physics.
80(3).
mla: Tkačik, Gašper, et al. “Optimizing Information Flow in Small Genetic Networks.”
Physical Review E Statistical Nonlinear and Soft Matter Physics, vol. 80,
no. 3, American Institute of Physics, 2009, doi:10.1103/PhysRevE.80.031920.
short: G. Tkačik, A. Walczak, W. Bialek, Physical Review E Statistical Nonlinear
and Soft Matter Physics 80 (2009).
date_created: 2018-12-11T12:04:53Z
date_published: 2009-09-29T00:00:00Z
date_updated: 2021-01-12T07:51:50Z
day: '29'
doi: 10.1103/PhysRevE.80.031920
extern: 1
intvolume: ' 80'
issue: '3 '
main_file_link:
- open_access: '0'
url: http://arxiv.org/abs/0903.4491
month: '09'
publication: Physical Review E Statistical Nonlinear and Soft Matter Physics
publication_status: published
publisher: American Institute of Physics
publist_id: '2493'
quality_controlled: 0
status: public
title: Optimizing information flow in small genetic networks
type: journal_article
volume: 80
year: '2009'
...