---
_id: '2948'
abstract:
- lang: eng
text: 'Many visual datasets are traditionally used to analyze the performance of
different learning techniques. The evaluation is usually done within each dataset,
therefore it is questionable if such results are a reliable indicator of true
generalization ability. We propose here an algorithm to exploit the existing data
resources when learning on a new multiclass problem. Our main idea is to identify
an image representation that decomposes orthogonally into two subspaces: a part
specific to each dataset, and a part generic to, and therefore shared between,
all the considered source sets. This allows us to use the generic representation
as un-biased reference knowledge for a novel classification task. By casting the
method in the multi-view setting, we also make it possible to use different features
for different databases. We call the algorithm MUST, Multitask Unaligned Shared
knowledge Transfer. Through extensive experiments on five public datasets, we
show that MUST consistently improves the cross-datasets generalization performance.'
acknowledgement: This work was supported by the PASCAL 2 Network of Excellence (TT)
and by the Newton International Fellowship (NQ)
alternative_title:
- LNCS
author:
- first_name: Tatiana
full_name: Tommasi, Tatiana
last_name: Tommasi
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Barbara
full_name: Caputo, Barbara
last_name: Caputo
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Tommasi T, Quadrianto N, Caputo B, Lampert C. Beyond dataset bias: Multi-task
unaligned shared knowledge transfer. 2013;7724:1-15. doi:10.1007/978-3-642-37331-2_1'
apa: 'Tommasi, T., Quadrianto, N., Caputo, B., & Lampert, C. (2013). Beyond
dataset bias: Multi-task unaligned shared knowledge transfer. Presented at the
ACCV: Asian Conference on Computer Vision, Daejeon, Korea: Springer. https://doi.org/10.1007/978-3-642-37331-2_1'
chicago: 'Tommasi, Tatiana, Novi Quadrianto, Barbara Caputo, and Christoph Lampert.
“Beyond Dataset Bias: Multi-Task Unaligned Shared Knowledge Transfer.” Lecture
Notes in Computer Science. Springer, 2013. https://doi.org/10.1007/978-3-642-37331-2_1.'
ieee: 'T. Tommasi, N. Quadrianto, B. Caputo, and C. Lampert, “Beyond dataset bias:
Multi-task unaligned shared knowledge transfer,” vol. 7724. Springer, pp. 1–15,
2013.'
ista: 'Tommasi T, Quadrianto N, Caputo B, Lampert C. 2013. Beyond dataset bias:
Multi-task unaligned shared knowledge transfer. 7724, 1–15.'
mla: 'Tommasi, Tatiana, et al. Beyond Dataset Bias: Multi-Task Unaligned Shared
Knowledge Transfer. Vol. 7724, Springer, 2013, pp. 1–15, doi:10.1007/978-3-642-37331-2_1.'
short: T. Tommasi, N. Quadrianto, B. Caputo, C. Lampert, 7724 (2013) 1–15.
conference:
end_date: 2012-11-09
location: Daejeon, Korea
name: 'ACCV: Asian Conference on Computer Vision'
start_date: 2012-11-05
date_created: 2018-12-11T12:00:30Z
date_published: 2013-04-04T00:00:00Z
date_updated: 2020-08-11T10:09:54Z
day: '04'
ddc:
- '000'
department:
- _id: ChLa
doi: 10.1007/978-3-642-37331-2_1
file:
- access_level: open_access
checksum: a0a7234a89e2192af655b0d0ae3bf445
content_type: application/pdf
creator: dernst
date_created: 2019-01-22T14:03:11Z
date_updated: 2020-07-14T12:45:55Z
file_id: '5874'
file_name: 2012_ACCV_Tommasi.pdf
file_size: 1513620
relation: main_file
file_date_updated: 2020-07-14T12:45:55Z
has_accepted_license: '1'
intvolume: ' 7724'
language:
- iso: eng
month: '04'
oa: 1
oa_version: Submitted Version
page: 1 - 15
publication_status: published
publisher: Springer
publist_id: '3784'
quality_controlled: '1'
scopus_import: 1
series_title: Lecture Notes in Computer Science
status: public
title: 'Beyond dataset bias: Multi-task unaligned shared knowledge transfer'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 7724
year: '2013'
...
---
_id: '3321'
author:
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Quadrianto N, Lampert C. Kernel based learning. In: Dubitzky W, Wolkenhauer
O, Cho K, Yokota H, eds. Encyclopedia of Systems Biology. Vol 3. Springer;
2013:1069-1069. doi:10.1007/978-1-4419-9863-7_604'
apa: Quadrianto, N., & Lampert, C. (2013). Kernel based learning. In W. Dubitzky,
O. Wolkenhauer, K. Cho, & H. Yokota (Eds.), Encyclopedia of Systems Biology
(Vol. 3, pp. 1069–1069). Springer. https://doi.org/10.1007/978-1-4419-9863-7_604
chicago: Quadrianto, Novi, and Christoph Lampert. “Kernel Based Learning.” In Encyclopedia
of Systems Biology, edited by Werner Dubitzky, Olaf Wolkenhauer, Kwang Cho,
and Hiroki Yokota, 3:1069–1069. Springer, 2013. https://doi.org/10.1007/978-1-4419-9863-7_604.
ieee: N. Quadrianto and C. Lampert, “Kernel based learning,” in Encyclopedia
of Systems Biology, vol. 3, W. Dubitzky, O. Wolkenhauer, K. Cho, and H. Yokota,
Eds. Springer, 2013, pp. 1069–1069.
ista: 'Quadrianto N, Lampert C. 2013.Kernel based learning. In: Encyclopedia of
Systems Biology. vol. 3, 1069–1069.'
mla: Quadrianto, Novi, and Christoph Lampert. “Kernel Based Learning.” Encyclopedia
of Systems Biology, edited by Werner Dubitzky et al., vol. 3, Springer, 2013,
pp. 1069–1069, doi:10.1007/978-1-4419-9863-7_604.
short: N. Quadrianto, C. Lampert, in:, W. Dubitzky, O. Wolkenhauer, K. Cho, H. Yokota
(Eds.), Encyclopedia of Systems Biology, Springer, 2013, pp. 1069–1069.
date_created: 2018-12-11T12:02:39Z
date_published: 2013-01-01T00:00:00Z
date_updated: 2021-01-12T07:42:38Z
day: '01'
department:
- _id: ChLa
doi: 10.1007/978-1-4419-9863-7_604
editor:
- first_name: Werner
full_name: Dubitzky, Werner
last_name: Dubitzky
- first_name: Olaf
full_name: Wolkenhauer, Olaf
last_name: Wolkenhauer
- first_name: Kwang
full_name: Cho, Kwang
last_name: Cho
- first_name: Hiroki
full_name: Yokota, Hiroki
last_name: Yokota
intvolume: ' 3'
language:
- iso: eng
month: '01'
oa_version: None
page: 1069 - 1069
publication: Encyclopedia of Systems Biology
publication_status: published
publisher: Springer
publist_id: '3314'
quality_controlled: '1'
status: public
title: Kernel based learning
type: encyclopedia_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 3
year: '2013'
...
---
_id: '2293'
abstract:
- lang: eng
text: Many computer vision problems have an asymmetric distribution of information
between training and test time. In this work, we study the case where we are given
additional information about the training data, which however will not be available
at test time. This situation is called learning using privileged information (LUPI).
We introduce two maximum-margin techniques that are able to make use of this additional
source of information, and we show that the framework is applicable to several
scenarios that have been studied in computer vision before. Experiments with attributes,
bounding boxes, image tags and rationales as additional information in object
classification show promising results.
article_processing_charge: No
author:
- first_name: Viktoriia
full_name: Sharmanska, Viktoriia
id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87
last_name: Sharmanska
orcid: 0000-0003-0192-9308
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Sharmanska V, Quadrianto N, Lampert C. Learning to rank using privileged information.
In: IEEE; 2013:825-832. doi:10.1109/ICCV.2013.107'
apa: 'Sharmanska, V., Quadrianto, N., & Lampert, C. (2013). Learning to rank
using privileged information (pp. 825–832). Presented at the ICCV: International
Conference on Computer Vision, Sydney, Australia: IEEE. https://doi.org/10.1109/ICCV.2013.107'
chicago: Sharmanska, Viktoriia, Novi Quadrianto, and Christoph Lampert. “Learning
to Rank Using Privileged Information,” 825–32. IEEE, 2013. https://doi.org/10.1109/ICCV.2013.107.
ieee: 'V. Sharmanska, N. Quadrianto, and C. Lampert, “Learning to rank using privileged
information,” presented at the ICCV: International Conference on Computer Vision,
Sydney, Australia, 2013, pp. 825–832.'
ista: 'Sharmanska V, Quadrianto N, Lampert C. 2013. Learning to rank using privileged
information. ICCV: International Conference on Computer Vision, 825–832.'
mla: Sharmanska, Viktoriia, et al. Learning to Rank Using Privileged Information.
IEEE, 2013, pp. 825–32, doi:10.1109/ICCV.2013.107.
short: V. Sharmanska, N. Quadrianto, C. Lampert, in:, IEEE, 2013, pp. 825–832.
conference:
end_date: 2013-12-08
location: Sydney, Australia
name: 'ICCV: International Conference on Computer Vision'
start_date: 2013-12-01
date_created: 2018-12-11T11:56:49Z
date_published: 2013-12-01T00:00:00Z
date_updated: 2025-09-29T14:20:45Z
day: '01'
department:
- _id: ChLa
doi: 10.1109/ICCV.2013.107
ec_funded: 1
external_id:
isi:
- '000351830500103'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: www.cv-foundation.org/openaccess/content_iccv_2013/papers/Sharmanska_Learning_to_Rank_2013_ICCV_paper.pdf
month: '12'
oa: 1
oa_version: Submitted Version
page: 825 - 832
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_status: published
publisher: IEEE
publist_id: '4635'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Learning to rank using privileged information
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
year: '2013'
...
---
_id: '2294'
abstract:
- lang: eng
text: "In this work we propose a system for automatic classification of Drosophila
embryos into developmental stages.\r\nWhile the system is designed to solve an
actual problem in biological research, we believe that the principle underly-\r\ning
it is interesting not only for biologists, but also for researchers in computer
vision. The main idea is to combine two orthogonal sources of information: one
is a classifier trained on strongly invariant features, which makes it applicable
to images of very different conditions, but also leads to rather noisy predictions.
The other is a label propagation step based on a more powerful similarity measure
that however is only consistent within specific subsets of the data at a time.\r\nIn
our biological setup, the information sources are the shape and the staining patterns
of embryo images. We show\r\nexperimentally that while neither of the methods
\ can be used by itself to achieve satisfactory results, their combina-\r\ntion
achieves prediction quality comparable to human performance."
article_processing_charge: No
author:
- first_name: Tomas
full_name: Kazmar, Tomas
last_name: Kazmar
- first_name: Evgeny
full_name: Kvon, Evgeny
last_name: Kvon
- first_name: Alexander
full_name: Stark, Alexander
last_name: Stark
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Kazmar T, Kvon E, Stark A, Lampert C. Drosophila Embryo Stage Annotation using
Label Propagation. In: IEEE; 2013. doi:10.1109/ICCV.2013.139'
apa: 'Kazmar, T., Kvon, E., Stark, A., & Lampert, C. (2013). Drosophila Embryo
Stage Annotation using Label Propagation. Presented at the ICCV: International
Conference on Computer Vision, Sydney, Australia: IEEE. https://doi.org/10.1109/ICCV.2013.139'
chicago: Kazmar, Tomas, Evgeny Kvon, Alexander Stark, and Christoph Lampert. “Drosophila
Embryo Stage Annotation Using Label Propagation.” IEEE, 2013. https://doi.org/10.1109/ICCV.2013.139.
ieee: 'T. Kazmar, E. Kvon, A. Stark, and C. Lampert, “Drosophila Embryo Stage Annotation
using Label Propagation,” presented at the ICCV: International Conference on Computer
Vision, Sydney, Australia, 2013.'
ista: 'Kazmar T, Kvon E, Stark A, Lampert C. 2013. Drosophila Embryo Stage Annotation
using Label Propagation. ICCV: International Conference on Computer Vision.'
mla: Kazmar, Tomas, et al. Drosophila Embryo Stage Annotation Using Label Propagation.
IEEE, 2013, doi:10.1109/ICCV.2013.139.
short: T. Kazmar, E. Kvon, A. Stark, C. Lampert, in:, IEEE, 2013.
conference:
end_date: 2013-12-08
location: Sydney, Australia
name: 'ICCV: International Conference on Computer Vision'
start_date: 2013-12-01
date_created: 2018-12-11T11:56:49Z
date_published: 2013-12-01T00:00:00Z
date_updated: 2025-09-29T14:20:15Z
day: '01'
department:
- _id: ChLa
doi: 10.1109/ICCV.2013.139
ec_funded: 1
external_id:
isi:
- '000351830500136'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://www.cv-foundation.org/openaccess/ICCV2013.py
month: '12'
oa: 1
oa_version: Submitted Version
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication_status: published
publisher: IEEE
publist_id: '4634'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Drosophila Embryo Stage Annotation using Label Propagation
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
year: '2013'
...
---
_id: '2516'
abstract:
- lang: eng
text: 'We study the problem of object recognition for categories for which we have
no training examples, a task also called zero-data or zero-shot learning. This
situation has hardly been studied in computer vision research, even though it
occurs frequently: the world contains tens of thousands of different object classes
and for only few of them image collections have been formed and suitably annotated.
To tackle the problem we introduce attribute-based classification: objects are
identified based on a high-level description that is phrased in terms of semantic
attributes, such as the object''s color or shape. Because the identification of
each such property transcends the specific learning task at hand, the attribute
classifiers can be pre-learned independently, e.g. from existing 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
this paper we also introduce a new dataset, Animals with Attributes, of over 30,000
images of 50 animal classes, annotated with 85 semantic attributes. Extensive
experiments on this and two more datasets show that attribute-based classification
indeed is able to categorize images without access to any training images of the
target classes.'
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
- 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. Attribute-based classification for zero-shot
learning of object categories. IEEE Transactions on Pattern Analysis and Machine
Intelligence. 2013;36(3):453-465. doi:10.1109/TPAMI.2013.140
apa: Lampert, C., Nickisch, H., & Harmeling, S. (2013). Attribute-based classification
for zero-shot learning of object categories. IEEE Transactions on Pattern Analysis
and Machine Intelligence. IEEE. https://doi.org/10.1109/TPAMI.2013.140
chicago: Lampert, Christoph, Hannes Nickisch, and Stefan Harmeling. “Attribute-Based
Classification for Zero-Shot Learning of Object Categories.” IEEE Transactions
on Pattern Analysis and Machine Intelligence. IEEE, 2013. https://doi.org/10.1109/TPAMI.2013.140.
ieee: C. Lampert, H. Nickisch, and S. Harmeling, “Attribute-based classification
for zero-shot learning of object categories,” IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 36, no. 3. IEEE, pp. 453–465, 2013.
ista: Lampert C, Nickisch H, Harmeling S. 2013. Attribute-based classification for
zero-shot learning of object categories. IEEE Transactions on Pattern Analysis
and Machine Intelligence. 36(3), 453–465.
mla: Lampert, Christoph, et al. “Attribute-Based Classification for Zero-Shot Learning
of Object Categories.” IEEE Transactions on Pattern Analysis and Machine Intelligence,
vol. 36, no. 3, IEEE, 2013, pp. 453–65, doi:10.1109/TPAMI.2013.140.
short: C. Lampert, H. Nickisch, S. Harmeling, IEEE Transactions on Pattern Analysis
and Machine Intelligence 36 (2013) 453–465.
date_created: 2018-12-11T11:58:08Z
date_published: 2013-07-30T00:00:00Z
date_updated: 2025-09-29T14:09:57Z
day: '30'
department:
- _id: ChLa
doi: 10.1109/TPAMI.2013.140
external_id:
isi:
- '000331450100005'
intvolume: ' 36'
isi: 1
issue: '3'
language:
- iso: eng
month: '07'
oa_version: None
page: 453 - 465
publication: IEEE Transactions on Pattern Analysis and Machine Intelligence
publication_status: published
publisher: IEEE
publist_id: '4385'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Attribute-based classification for zero-shot learning of object categories
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 36
year: '2013'
...
---
_id: '2520'
abstract:
- lang: eng
text: "We propose a probabilistic model to infer supervised latent variables in\r\nthe
Hamming space from observed data. Our model allows simultaneous\r\ninference of
the number of binary latent variables, and their values. The\r\nlatent variables
preserve neighbourhood structure of the data in a sense\r\nthat objects in the
same semantic concept have similar latent values, and\r\nobjects in different
concepts have dissimilar latent values. We formulate\r\nthe supervised infinite
latent variable problem based on an intuitive\r\nprinciple of pulling objects
together if they are of the same type, and\r\npushing them apart if they are not.
We then combine this principle with a\r\nflexible Indian Buffet Process prior
on the latent variables. We show that\r\nthe inferred supervised latent variables
can be directly used to perform a\r\nnearest neighbour search for the purpose
of retrieval. We introduce a new\r\napplication of dynamically extending hash
codes, and show how to\r\neffectively couple the structure of the hash codes with
continuously\r\ngrowing structure of the neighbourhood preserving infinite latent
feature\r\nspace."
author:
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Viktoriia
full_name: Sharmanska, Viktoriia
id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87
last_name: Sharmanska
orcid: 0000-0003-0192-9308
- first_name: David
full_name: Knowles, David
last_name: Knowles
- first_name: Zoubin
full_name: Ghahramani, Zoubin
last_name: Ghahramani
citation:
ama: 'Quadrianto N, Sharmanska V, Knowles D, Ghahramani Z. The supervised IBP: Neighbourhood
preserving infinite latent feature models. In: Proceedings of the 29th Conference
Uncertainty in Artificial Intelligence. AUAI Press; 2013:527-536.'
apa: 'Quadrianto, N., Sharmanska, V., Knowles, D., & Ghahramani, Z. (2013).
The supervised IBP: Neighbourhood preserving infinite latent feature models. In
Proceedings of the 29th conference uncertainty in Artificial Intelligence
(pp. 527–536). Bellevue, WA, United States: AUAI Press.'
chicago: 'Quadrianto, Novi, Viktoriia Sharmanska, David Knowles, and Zoubin Ghahramani.
“The Supervised IBP: Neighbourhood Preserving Infinite Latent Feature Models.”
In Proceedings of the 29th Conference Uncertainty in Artificial Intelligence,
527–36. AUAI Press, 2013.'
ieee: 'N. Quadrianto, V. Sharmanska, D. Knowles, and Z. Ghahramani, “The supervised
IBP: Neighbourhood preserving infinite latent feature models,” in Proceedings
of the 29th conference uncertainty in Artificial Intelligence, Bellevue, WA,
United States, 2013, pp. 527–536.'
ista: 'Quadrianto N, Sharmanska V, Knowles D, Ghahramani Z. 2013. The supervised
IBP: Neighbourhood preserving infinite latent feature models. Proceedings of the
29th conference uncertainty in Artificial Intelligence. UAI: Uncertainty in Artificial
Intelligence, 527–536.'
mla: 'Quadrianto, Novi, et al. “The Supervised IBP: Neighbourhood Preserving Infinite
Latent Feature Models.” Proceedings of the 29th Conference Uncertainty in Artificial
Intelligence, AUAI Press, 2013, pp. 527–36.'
short: N. Quadrianto, V. Sharmanska, D. Knowles, Z. Ghahramani, in:, Proceedings
of the 29th Conference Uncertainty in Artificial Intelligence, AUAI Press, 2013,
pp. 527–536.
conference:
end_date: 2013-07-15
location: Bellevue, WA, United States
name: 'UAI: Uncertainty in Artificial Intelligence'
start_date: 2013-07-11
date_created: 2018-12-11T11:58:09Z
date_published: 2013-07-11T00:00:00Z
date_updated: 2023-02-23T10:46:36Z
day: '11'
ddc:
- '000'
department:
- _id: ChLa
file:
- access_level: open_access
checksum: 325f20c4b926bd74d39006b97df572bd
content_type: application/pdf
creator: system
date_created: 2018-12-12T10:15:16Z
date_updated: 2020-07-14T12:45:42Z
file_id: '5134'
file_name: IST-2013-137-v1+1_QuaShaKnoGha13.pdf
file_size: 1117100
relation: main_file
file_date_updated: 2020-07-14T12:45:42Z
has_accepted_license: '1'
language:
- iso: eng
month: '07'
oa: 1
oa_version: Submitted Version
page: 527 - 536
publication: Proceedings of the 29th conference uncertainty in Artificial Intelligence
publication_identifier:
isbn:
- '9780974903996'
publication_status: published
publisher: AUAI Press
publist_id: '4381'
pubrep_id: '137'
quality_controlled: '1'
scopus_import: 1
status: public
title: 'The supervised IBP: Neighbourhood preserving infinite latent feature models'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2013'
...
---
_id: '2825'
abstract:
- lang: eng
text: 'We study the problem of maximum marginal prediction (MMP) in probabilistic
graphical models, a task that occurs, for example, as the Bayes optimal decision
rule under a Hamming loss. MMP is typically performed as a two-stage procedure:
one estimates each variable''s marginal probability and then forms a prediction
from the states of maximal probability. In this work we propose a simple yet effective
technique for accelerating MMP when inference is sampling-based: instead of the
above two-stage procedure we directly estimate the posterior probability of each
decision variable. This allows us to identify the point of time when we are sufficiently
certain about any individual decision. Whenever this is the case, we dynamically
prune the variables we are confident about from the underlying factor graph. Consequently,
at any time only samples of variables whose decision is still uncertain need to
be created. Experiments in two prototypical scenarios, multi-label classification
and image inpainting, show that adaptive sampling can drastically accelerate MMP
without sacrificing prediction accuracy.'
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. Dynamic pruning of factor graphs for maximum marginal prediction.
In: Vol 1. Neural Information Processing Systems Foundation; 2012:82-90.'
apa: 'Lampert, C. (2012). Dynamic pruning of factor graphs for maximum marginal
prediction (Vol. 1, pp. 82–90). Presented at the NIPS: Neural Information Processing
Systems, Lake Tahoe, NV, United States: Neural Information Processing Systems
Foundation.'
chicago: Lampert, Christoph. “Dynamic Pruning of Factor Graphs for Maximum Marginal
Prediction,” 1:82–90. Neural Information Processing Systems Foundation, 2012.
ieee: 'C. Lampert, “Dynamic pruning of factor graphs for maximum marginal prediction,”
presented at the NIPS: Neural Information Processing Systems, Lake Tahoe, NV,
United States, 2012, vol. 1, pp. 82–90.'
ista: 'Lampert C. 2012. Dynamic pruning of factor graphs for maximum marginal prediction.
NIPS: Neural Information Processing Systems vol. 1, 82–90.'
mla: Lampert, Christoph. Dynamic Pruning of Factor Graphs for Maximum Marginal
Prediction. Vol. 1, Neural Information Processing Systems Foundation, 2012,
pp. 82–90.
short: C. Lampert, in:, Neural Information Processing Systems Foundation, 2012,
pp. 82–90.
conference:
end_date: 2012-12-06
location: Lake Tahoe, NV, United States
name: 'NIPS: Neural Information Processing Systems'
start_date: 2012-12-03
corr_author: '1'
date_created: 2018-12-11T11:59:48Z
date_published: 2012-12-01T00:00:00Z
date_updated: 2025-06-03T11:46:36Z
day: '01'
department:
- _id: ChLa
intvolume: ' 1'
language:
- iso: eng
month: '12'
oa_version: None
page: 82 - 90
publication_status: published
publisher: Neural Information Processing Systems Foundation
publist_id: '3975'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Dynamic pruning of factor graphs for maximum marginal prediction
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 1
year: '2012'
...
---
_id: '2915'
acknowledgement: "The project receives funding from the European Community’s Seventh
Framework Programme under grant agreement\r\nno. ICT- 248273 GeRT."
article_processing_charge: No
author:
- first_name: Oliver
full_name: Kroemer, Oliver
last_name: Kroemer
- first_name: Christoph
full_name: Lampert, Christoph
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: 'Kroemer O, Lampert C, Peters J. Multi-modal learning for dynamic tactile sensing.
In: Deutsches Zentrum für Luft und Raumfahrt; 2012.'
apa: Kroemer, O., Lampert, C., & Peters, J. (2012). Multi-modal learning for
dynamic tactile sensing. Deutsches Zentrum für Luft und Raumfahrt.
chicago: Kroemer, Oliver, Christoph Lampert, and Jan Peters. “Multi-Modal Learning
for Dynamic Tactile Sensing.” Deutsches Zentrum für Luft und Raumfahrt, 2012.
ieee: O. Kroemer, C. Lampert, and J. Peters, “Multi-modal learning for dynamic tactile
sensing,” 2012.
ista: Kroemer O, Lampert C, Peters J. 2012. Multi-modal learning for dynamic tactile
sensing
mla: Kroemer, Oliver, et al. Multi-Modal Learning for Dynamic Tactile Sensing.
Deutsches Zentrum für Luft und Raumfahrt, 2012.
short: O. Kroemer, C. Lampert, J. Peters, in:, Deutsches Zentrum für Luft und Raumfahrt,
2012.
date_created: 2018-12-11T12:00:19Z
date_published: 2012-10-11T00:00:00Z
date_updated: 2023-10-17T07:58:59Z
day: '11'
department:
- _id: ChLa
language:
- iso: eng
month: '10'
oa_version: None
publication_status: published
publisher: Deutsches Zentrum für Luft und Raumfahrt
publist_id: '3828'
quality_controlled: '1'
status: public
title: Multi-modal learning for dynamic tactile sensing
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2012'
...
---
_id: '3124'
abstract:
- lang: eng
text: "We consider the problem of inference in a graphical model with binary variables.
While in theory it is arguably preferable to compute marginal probabilities, in
practice researchers often use MAP inference due to the availability of efficient
discrete optimization algorithms. We bridge the gap between the two approaches
by introducing the Discrete Marginals technique in which approximate marginals
are obtained by minimizing an objective function with unary and pairwise terms
over a discretized domain. This allows the use of techniques originally developed
for MAP-MRF inference and learning. We explore two ways to set up the objective
function - by discretizing the Bethe free energy and by learning it from training
data. Experimental results show that for certain types of graphs a learned function
can outperform the Bethe approximation. We also establish a link between the Bethe
free energy and submodular functions.\r\n"
alternative_title:
- Inferning 2012
author:
- first_name: Filip
full_name: Korc, Filip
id: 476A2FD6-F248-11E8-B48F-1D18A9856A87
last_name: Korc
- first_name: Vladimir
full_name: Kolmogorov, Vladimir
id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
last_name: Kolmogorov
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Korc F, Kolmogorov V, Lampert C. Approximating marginals using discrete energy
minimization. In: ICML; 2012.'
apa: 'Korc, F., Kolmogorov, V., & Lampert, C. (2012). Approximating marginals
using discrete energy minimization. Presented at the ICML: International Conference
on Machine Learning, Edinburgh, Scotland: ICML.'
chicago: Korc, Filip, Vladimir Kolmogorov, and Christoph Lampert. “Approximating
Marginals Using Discrete Energy Minimization.” ICML, 2012.
ieee: 'F. Korc, V. Kolmogorov, and C. Lampert, “Approximating marginals using discrete
energy minimization,” presented at the ICML: International Conference on Machine
Learning, Edinburgh, Scotland, 2012.'
ista: 'Korc F, Kolmogorov V, Lampert C. 2012. Approximating marginals using discrete
energy minimization. ICML: International Conference on Machine Learning, Inferning
2012, .'
mla: Korc, Filip, et al. Approximating Marginals Using Discrete Energy Minimization.
ICML, 2012.
short: F. Korc, V. Kolmogorov, C. Lampert, in:, ICML, 2012.
conference:
end_date: 2012-07-01
location: Edinburgh, Scotland
name: 'ICML: International Conference on Machine Learning'
start_date: 2012-06-26
corr_author: '1'
date_created: 2018-12-11T12:01:31Z
date_published: 2012-06-30T00:00:00Z
date_updated: 2024-10-09T20:54:48Z
day: '30'
ddc:
- '000'
department:
- _id: ChLa
- _id: VlKo
file:
- access_level: open_access
checksum: 3d0d4246548c736857302aadb2ff5d15
content_type: application/pdf
creator: system
date_created: 2018-12-12T10:11:34Z
date_updated: 2020-07-14T12:46:00Z
file_id: '4889'
file_name: IST-2016-565-v1+1_DM-inferning2012.pdf
file_size: 305836
relation: main_file
file_date_updated: 2020-07-14T12:46:00Z
has_accepted_license: '1'
language:
- iso: eng
month: '06'
oa: 1
oa_version: Submitted Version
publication_status: published
publisher: ICML
publist_id: '3575'
pubrep_id: '565'
quality_controlled: '1'
related_material:
record:
- id: '5396'
relation: later_version
status: public
status: public
title: Approximating marginals using discrete energy minimization
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2012'
...
---
_id: '3125'
abstract:
- lang: eng
text: We propose a new learning method to infer a mid-level feature representation
that combines the advantage of semantic attribute representations with the higher
expressive power of non-semantic features. The idea lies in augmenting an existing
attribute-based representation with additional dimensions for which an autoencoder
model is coupled with a large-margin principle. This construction allows a smooth
transition between the zero-shot regime with no training example, the unsupervised
regime with training examples but without class labels, and the supervised regime
with training examples and with class labels. The resulting optimization problem
can be solved efficiently, because several of the necessity steps have closed-form
solutions. Through extensive experiments we show that the augmented representation
achieves better results in terms of object categorization accuracy than the semantic
representation alone.
alternative_title:
- LNCS
article_processing_charge: No
author:
- first_name: Viktoriia
full_name: Sharmanska, Viktoriia
id: 2EA6D09E-F248-11E8-B48F-1D18A9856A87
last_name: Sharmanska
orcid: 0000-0003-0192-9308
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Sharmanska V, Quadrianto N, Lampert C. Augmented attribute representations.
In: Vol 7576. Springer; 2012:242-255. doi:10.1007/978-3-642-33715-4_18'
apa: 'Sharmanska, V., Quadrianto, N., & Lampert, C. (2012). Augmented attribute
representations (Vol. 7576, pp. 242–255). Presented at the ECCV: European Conference
on Computer Vision, Florence, Italy: Springer. https://doi.org/10.1007/978-3-642-33715-4_18'
chicago: Sharmanska, Viktoriia, Novi Quadrianto, and Christoph Lampert. “Augmented
Attribute Representations,” 7576:242–55. Springer, 2012. https://doi.org/10.1007/978-3-642-33715-4_18.
ieee: 'V. Sharmanska, N. Quadrianto, and C. Lampert, “Augmented attribute representations,”
presented at the ECCV: European Conference on Computer Vision, Florence, Italy,
2012, vol. 7576, no. PART 5, pp. 242–255.'
ista: 'Sharmanska V, Quadrianto N, Lampert C. 2012. Augmented attribute representations.
ECCV: European Conference on Computer Vision, LNCS, vol. 7576, 242–255.'
mla: Sharmanska, Viktoriia, et al. Augmented Attribute Representations. Vol.
7576, no. PART 5, Springer, 2012, pp. 242–55, doi:10.1007/978-3-642-33715-4_18.
short: V. Sharmanska, N. Quadrianto, C. Lampert, in:, Springer, 2012, pp. 242–255.
conference:
end_date: 2012-10-13
location: Florence, Italy
name: 'ECCV: European Conference on Computer Vision'
start_date: 2012-10-07
date_created: 2018-12-11T12:01:32Z
date_published: 2012-10-01T00:00:00Z
date_updated: 2023-02-23T11:13:25Z
day: '01'
ddc:
- '000'
department:
- _id: ChLa
doi: 10.1007/978-3-642-33715-4_18
file:
- access_level: open_access
checksum: bccdbe0663780d25a1e0524002b2d896
content_type: application/pdf
creator: dernst
date_created: 2020-05-15T12:29:04Z
date_updated: 2020-07-14T12:46:00Z
file_id: '7861'
file_name: 2012_ECCV_Sharmanska.pdf
file_size: 6073897
relation: main_file
file_date_updated: 2020-07-14T12:46:00Z
has_accepted_license: '1'
intvolume: ' 7576'
issue: PART 5
language:
- iso: eng
month: '10'
oa: 1
oa_version: Submitted Version
page: 242 - 255
publication_status: published
publisher: Springer
publist_id: '3574'
quality_controlled: '1'
scopus_import: 1
status: public
title: Augmented attribute representations
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 7576
year: '2012'
...
---
_id: '3126'
abstract:
- lang: eng
text: "In this work we propose a new information-theoretic clustering algorithm
that infers cluster memberships by direct optimization of a non-parametric mutual
information estimate between data distribution and cluster assignment. Although
the optimization objective has a solid theoretical foundation it is hard to optimize.
We propose an approximate optimization formulation that leads to an efficient
algorithm with low runtime complexity. The algorithm has a single free parameter,
the number of clusters to find. We demonstrate superior performance on several
synthetic and real datasets.\r\n"
alternative_title:
- LNCS
author:
- first_name: Andreas
full_name: Müller, Andreas
last_name: Müller
- first_name: Sebastian
full_name: Nowozin, Sebastian
last_name: Nowozin
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Müller A, Nowozin S, Lampert C. Information theoretic clustering using minimal
spanning trees. In: Vol 7476. Springer; 2012:205-215. doi:10.1007/978-3-642-32717-9_21'
apa: 'Müller, A., Nowozin, S., & Lampert, C. (2012). Information theoretic clustering
using minimal spanning trees (Vol. 7476, pp. 205–215). Presented at the DAGM:
German Association For Pattern Recognition, Graz, Austria: Springer. https://doi.org/10.1007/978-3-642-32717-9_21'
chicago: Müller, Andreas, Sebastian Nowozin, and Christoph Lampert. “Information
Theoretic Clustering Using Minimal Spanning Trees,” 7476:205–15. Springer, 2012.
https://doi.org/10.1007/978-3-642-32717-9_21.
ieee: 'A. Müller, S. Nowozin, and C. Lampert, “Information theoretic clustering
using minimal spanning trees,” presented at the DAGM: German Association For Pattern
Recognition, Graz, Austria, 2012, vol. 7476, pp. 205–215.'
ista: 'Müller A, Nowozin S, Lampert C. 2012. Information theoretic clustering using
minimal spanning trees. DAGM: German Association For Pattern Recognition, LNCS,
vol. 7476, 205–215.'
mla: Müller, Andreas, et al. Information Theoretic Clustering Using Minimal Spanning
Trees. Vol. 7476, Springer, 2012, pp. 205–15, doi:10.1007/978-3-642-32717-9_21.
short: A. Müller, S. Nowozin, C. Lampert, in:, Springer, 2012, pp. 205–215.
conference:
end_date: 2012-08-31
location: Graz, Austria
name: 'DAGM: German Association For Pattern Recognition'
start_date: 2012-08-28
date_created: 2018-12-11T12:01:32Z
date_published: 2012-08-14T00:00:00Z
date_updated: 2021-01-12T07:41:14Z
day: '14'
department:
- _id: ChLa
doi: 10.1007/978-3-642-32717-9_21
intvolume: ' 7476'
language:
- iso: eng
month: '08'
oa_version: None
page: 205 - 215
publication_status: published
publisher: Springer
publist_id: '3573'
quality_controlled: '1'
scopus_import: 1
status: public
title: Information theoretic clustering using minimal spanning trees
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
volume: 7476
year: '2012'
...
---
_id: '3127'
abstract:
- lang: eng
text: "When searching for characteristic subpatterns in potentially noisy graph
data, it appears self-evident that having multiple observations would be better
than having just one. However, it turns out that the inconsistencies introduced
when different graph instances have different edge sets pose a serious challenge.
In this work we address this challenge for the problem of finding maximum weighted
cliques.\r\n We introduce the concept of most persistent soft-clique. This
is subset of vertices, that 1) is almost fully or at least densely connected,
2) occurs in all or almost all graph instances, and 3) has the maximum weight.
We present a measure of clique-ness, that essentially counts the number of edge
missing to make a subset of vertices into a clique. With this measure, we show
that the problem of finding the most persistent soft-clique problem can be cast
either as: a) a max-min two person game optimization problem, or b) a min-min
soft margin optimization problem. Both formulations lead to the same solution
when using a partial Lagrangian method to solve the optimization problems. By
experiments on synthetic data and on real social network data, we show that the
proposed method is able to reliably find soft cliques in graph data, even if that
is distorted by random noise or unreliable observations."
article_processing_charge: No
arxiv: 1
author:
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Chao
full_name: Chen, Chao
id: 3E92416E-F248-11E8-B48F-1D18A9856A87
last_name: Chen
citation:
ama: 'Quadrianto N, Lampert C, Chen C. The most persistent soft-clique in a set
of sampled graphs. In: Proceedings of the 29th International Conference on
Machine Learning. ML Research Press; 2012:211-218.'
apa: 'Quadrianto, N., Lampert, C., & Chen, C. (2012). The most persistent soft-clique
in a set of sampled graphs. In Proceedings of the 29th International Conference
on Machine Learning (pp. 211–218). Edinburgh, United Kingdom: ML Research
Press.'
chicago: Quadrianto, Novi, Christoph Lampert, and Chao Chen. “The Most Persistent
Soft-Clique in a Set of Sampled Graphs.” In Proceedings of the 29th International
Conference on Machine Learning, 211–18. ML Research Press, 2012.
ieee: N. Quadrianto, C. Lampert, and C. Chen, “The most persistent soft-clique in
a set of sampled graphs,” in Proceedings of the 29th International Conference
on Machine Learning, Edinburgh, United Kingdom, 2012, pp. 211–218.
ista: 'Quadrianto N, Lampert C, Chen C. 2012. The most persistent soft-clique in
a set of sampled graphs. Proceedings of the 29th International Conference on Machine
Learning. ICML: International Conference on Machine Learning, 211–218.'
mla: Quadrianto, Novi, et al. “The Most Persistent Soft-Clique in a Set of Sampled
Graphs.” Proceedings of the 29th International Conference on Machine Learning,
ML Research Press, 2012, pp. 211–18.
short: N. Quadrianto, C. Lampert, C. Chen, in:, Proceedings of the 29th International
Conference on Machine Learning, ML Research Press, 2012, pp. 211–218.
conference:
end_date: 2012-07-01
location: Edinburgh, United Kingdom
name: 'ICML: International Conference on Machine Learning'
start_date: 2012-06-26
date_created: 2018-12-11T12:01:33Z
date_published: 2012-06-01T00:00:00Z
date_updated: 2025-06-11T08:09:42Z
day: '01'
department:
- _id: ChLa
- _id: HeEd
external_id:
arxiv:
- '1206.4652'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://arxiv.org/abs/1206.4652
month: '06'
oa: 1
oa_version: Preprint
page: 211-218
publication: Proceedings of the 29th International Conference on Machine Learning
publication_status: published
publisher: ML Research Press
publist_id: '3572'
quality_controlled: '1'
scopus_import: '1'
status: public
title: The most persistent soft-clique in a set of sampled graphs
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2012'
...
---
_id: '3164'
abstract:
- lang: eng
text: Overview of the Special Issue on structured prediction and inference.
article_processing_charge: No
author:
- first_name: Matthew
full_name: Blaschko, Matthew
last_name: Blaschko
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Blaschko M, Lampert C. Guest editorial: Special issue on structured prediction
and inference. International Journal of Computer Vision. 2012;99(3):257-258.
doi:10.1007/s11263-012-0530-y'
apa: 'Blaschko, M., & Lampert, C. (2012). Guest editorial: Special issue on
structured prediction and inference. International Journal of Computer Vision.
Springer. https://doi.org/10.1007/s11263-012-0530-y'
chicago: 'Blaschko, Matthew, and Christoph Lampert. “Guest Editorial: Special Issue
on Structured Prediction and Inference.” International Journal of Computer
Vision. Springer, 2012. https://doi.org/10.1007/s11263-012-0530-y.'
ieee: 'M. Blaschko and C. Lampert, “Guest editorial: Special issue on structured
prediction and inference,” International Journal of Computer Vision, vol.
99, no. 3. Springer, pp. 257–258, 2012.'
ista: 'Blaschko M, Lampert C. 2012. Guest editorial: Special issue on structured
prediction and inference. International Journal of Computer Vision. 99(3), 257–258.'
mla: 'Blaschko, Matthew, and Christoph Lampert. “Guest Editorial: Special Issue
on Structured Prediction and Inference.” International Journal of Computer
Vision, vol. 99, no. 3, Springer, 2012, pp. 257–58, doi:10.1007/s11263-012-0530-y.'
short: M. Blaschko, C. Lampert, International Journal of Computer Vision 99 (2012)
257–258.
date_created: 2018-12-11T12:01:46Z
date_published: 2012-09-01T00:00:00Z
date_updated: 2025-09-30T07:52:02Z
day: '01'
department:
- _id: ChLa
doi: 10.1007/s11263-012-0530-y
external_id:
isi:
- '000304655600001'
intvolume: ' 99'
isi: 1
issue: '3'
language:
- iso: eng
month: '09'
oa_version: None
page: 257 - 258
publication: International Journal of Computer Vision
publication_status: published
publisher: Springer
publist_id: '3521'
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Guest editorial: Special issue on structured prediction and inference'
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 99
year: '2012'
...
---
_id: '3248'
abstract:
- lang: eng
text: We describe RTblob, a high speed vision system that detects objects in cluttered
scenes based on their color and shape at a speed of over 800 frames/s. Because
the system is available as open-source software and relies only on off-the-shelf
PC hardware components, it can provide the basis for multiple application scenarios.
As an illustrative example, we show how RTblob can be used in a robotic table
tennis scenario to estimate ball trajectories through 3D space simultaneously
from four cameras images at a speed of 200 Hz.
article_processing_charge: No
article_type: original
author:
- first_name: Christoph
full_name: Lampert, Christoph
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. Real-time detection of colored objects in multiple camera
streams with off-the-shelf hardware components. Journal of Real-Time Image
Processing. 2012;7(1):31-41. doi:10.1007/s11554-010-0168-3
apa: Lampert, C., & Peters, J. (2012). Real-time detection of colored objects
in multiple camera streams with off-the-shelf hardware components. Journal
of Real-Time Image Processing. Springer. https://doi.org/10.1007/s11554-010-0168-3
chicago: Lampert, Christoph, and Jan Peters. “Real-Time Detection of Colored Objects
in Multiple Camera Streams with off-the-Shelf Hardware Components.” Journal
of Real-Time Image Processing. Springer, 2012. https://doi.org/10.1007/s11554-010-0168-3.
ieee: C. Lampert and J. Peters, “Real-time detection of colored objects in multiple
camera streams with off-the-shelf hardware components,” Journal of Real-Time
Image Processing, vol. 7, no. 1. Springer, pp. 31–41, 2012.
ista: Lampert C, Peters J. 2012. Real-time detection of colored objects in multiple
camera streams with off-the-shelf hardware components. Journal of Real-Time Image
Processing. 7(1), 31–41.
mla: Lampert, Christoph, and Jan Peters. “Real-Time Detection of Colored Objects
in Multiple Camera Streams with off-the-Shelf Hardware Components.” Journal
of Real-Time Image Processing, vol. 7, no. 1, Springer, 2012, pp. 31–41, doi:10.1007/s11554-010-0168-3.
short: C. Lampert, J. Peters, Journal of Real-Time Image Processing 7 (2012) 31–41.
corr_author: '1'
date_created: 2018-12-11T12:02:15Z
date_published: 2012-03-01T00:00:00Z
date_updated: 2025-09-30T07:46:36Z
day: '01'
ddc:
- '000'
department:
- _id: ChLa
doi: 10.1007/s11554-010-0168-3
external_id:
isi:
- '000303242600004'
file:
- access_level: open_access
checksum: 241be47ea50e81a283bcf4c45b07e8cc
content_type: application/pdf
creator: kschuh
date_created: 2019-02-12T10:52:25Z
date_updated: 2020-07-14T12:46:04Z
file_id: '5958'
file_name: 2012_Springer_Lampert.pdf
file_size: 2933187
relation: main_file
file_date_updated: 2020-07-14T12:46:04Z
has_accepted_license: '1'
intvolume: ' 7'
isi: 1
issue: '1'
language:
- iso: eng
month: '03'
oa: 1
oa_version: Submitted Version
page: 31 - 41
publication: Journal of Real-Time Image Processing
publication_identifier:
eissn:
- 1861-8219
issn:
- 1861-8200
publication_status: published
publisher: Springer
publist_id: '3417'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Real-time detection of colored objects in multiple camera streams with off-the-shelf
hardware components
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 7
year: '2012'
...
---
_id: '5396'
abstract:
- lang: eng
text: We consider the problem of inference in agraphical model with binary variables.
While in theory it is arguably preferable to compute marginal probabilities, in
practice researchers often use MAP inference due to the availability of efficient
discrete optimization algorithms. We bridge the gap between the two approaches
by introducing the Discrete Marginals technique in which approximate marginals
are obtained by minimizing an objective function with unary and pair-wise terms
over a discretized domain. This allows the use of techniques originally devel-oped
for MAP-MRF inference and learning. We explore two ways to set up the objective
function - by discretizing the Bethe free energy and by learning it from training
data. Experimental results show that for certain types of graphs a learned function
can out-perform the Bethe approximation. We also establish a link between the
Bethe free energy and submodular functions.
alternative_title:
- IST Austria Technical Report
author:
- first_name: Filip
full_name: Korc, Filip
id: 476A2FD6-F248-11E8-B48F-1D18A9856A87
last_name: Korc
- first_name: Vladimir
full_name: Kolmogorov, Vladimir
id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
last_name: Kolmogorov
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: Korc F, Kolmogorov V, Lampert C. Approximating Marginals Using Discrete
Energy Minimization. IST Austria; 2012. doi:10.15479/AT:IST-2012-0003
apa: Korc, F., Kolmogorov, V., & Lampert, C. (2012). Approximating marginals
using discrete energy minimization. IST Austria. https://doi.org/10.15479/AT:IST-2012-0003
chicago: Korc, Filip, Vladimir Kolmogorov, and Christoph Lampert. Approximating
Marginals Using Discrete Energy Minimization. IST Austria, 2012. https://doi.org/10.15479/AT:IST-2012-0003.
ieee: F. Korc, V. Kolmogorov, and C. Lampert, Approximating marginals using discrete
energy minimization. IST Austria, 2012.
ista: Korc F, Kolmogorov V, Lampert C. 2012. Approximating marginals using discrete
energy minimization, IST Austria, 13p.
mla: Korc, Filip, et al. Approximating Marginals Using Discrete Energy Minimization.
IST Austria, 2012, doi:10.15479/AT:IST-2012-0003.
short: F. Korc, V. Kolmogorov, C. Lampert, Approximating Marginals Using Discrete
Energy Minimization, IST Austria, 2012.
date_created: 2018-12-12T11:39:06Z
date_published: 2012-07-23T00:00:00Z
date_updated: 2024-10-09T20:54:48Z
day: '23'
ddc:
- '000'
department:
- _id: VlKo
- _id: ChLa
doi: 10.15479/AT:IST-2012-0003
file:
- access_level: open_access
checksum: 7e0ba85ad123b13223aaf6cdde2d288c
content_type: application/pdf
creator: system
date_created: 2018-12-12T11:53:29Z
date_updated: 2020-07-14T12:46:44Z
file_id: '5490'
file_name: IST-2012-0003_IST-2012-0003.pdf
file_size: 618744
relation: main_file
file_date_updated: 2020-07-14T12:46:44Z
has_accepted_license: '1'
language:
- iso: eng
month: '07'
oa: 1
oa_version: Published Version
page: '13'
publication_identifier:
issn:
- 2664-1690
publication_status: published
publisher: IST Austria
pubrep_id: '36'
related_material:
record:
- id: '3124'
relation: earlier_version
status: public
status: public
title: Approximating marginals using discrete energy minimization
type: technical_report
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2012'
...
---
_id: '3163'
abstract:
- lang: eng
text: We study multi-label prediction for structured output sets, a problem that
occurs, for example, in object detection in images, secondary structure prediction
in computational biology, and graph matching with symmetries. Conventional multilabel
classification techniques are typically not applicable in this situation, because
they require explicit enumeration of the label set, which is infeasible in case
of structured outputs. Relying on techniques originally designed for single-label
structured prediction, in particular structured support vector machines, results
in reduced prediction accuracy, or leads to infeasible optimization problems.
In this work we derive a maximum-margin training formulation for multi-label structured
prediction that remains computationally tractable while achieving high prediction
accuracy. It also shares most beneficial properties with single-label maximum-margin
approaches, in particular formulation as a convex optimization problem, efficient
working set training, and PAC-Bayesian generalization bounds.
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. Maximum margin multi-label structured prediction. In: Neural Information
Processing Systems Foundation; 2011.'
apa: 'Lampert, C. (2011). Maximum margin multi-label structured prediction. Presented
at the NIPS: Neural Information Processing Systems, Granada, Spain: Neural Information
Processing Systems Foundation.'
chicago: Lampert, Christoph. “Maximum Margin Multi-Label Structured Prediction.”
Neural Information Processing Systems Foundation, 2011.
ieee: 'C. Lampert, “Maximum margin multi-label structured prediction,” presented
at the NIPS: Neural Information Processing Systems, Granada, Spain, 2011.'
ista: 'Lampert C. 2011. Maximum margin multi-label structured prediction. NIPS:
Neural Information Processing Systems.'
mla: Lampert, Christoph. Maximum Margin Multi-Label Structured Prediction.
Neural Information Processing Systems Foundation, 2011.
short: C. Lampert, in:, Neural Information Processing Systems Foundation, 2011.
conference:
end_date: 2011-12-14
location: Granada, Spain
name: 'NIPS: Neural Information Processing Systems'
start_date: 2011-12-12
corr_author: '1'
date_created: 2018-12-11T12:01:45Z
date_published: 2011-12-01T00:00:00Z
date_updated: 2025-06-03T11:47:47Z
day: '01'
department:
- _id: ChLa
language:
- iso: eng
month: '12'
oa_version: None
publication_status: published
publisher: Neural Information Processing Systems Foundation
publist_id: '3522'
quality_controlled: '1'
related_material:
record:
- id: '3322'
relation: later_version
status: public
scopus_import: '1'
status: public
title: Maximum margin multi-label structured prediction
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2011'
...
---
_id: '3319'
abstract:
- lang: eng
text: We address the problem of metric learning for multi-view data, namely the
construction of embedding projections from data in different representations into
a shared feature space, such that the Euclidean distance in this space provides
a meaningful within-view as well as between-view similarity. Our motivation stems
from the problem of cross-media retrieval tasks, where the availability of a joint
Euclidean distance function is a pre-requisite to allow fast, in particular hashing-based,
nearest neighbor queries. We formulate an objective function that expresses the
intuitive concept that matching samples are mapped closely together in the output
space, whereas non-matching samples are pushed apart, no matter in which view
they are available. The resulting optimization problem is not convex, but it can
be decomposed explicitly into a convex and a concave part, thereby allowing efficient
optimization using the convex-concave procedure. Experiments on an image retrieval
task show that nearest-neighbor based cross-view retrieval is indeed possible,
and the proposed technique improves the retrieval accuracy over baseline techniques.
article_processing_charge: No
author:
- first_name: Novi
full_name: Quadrianto, Novi
last_name: Quadrianto
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Quadrianto N, Lampert C. Learning multi-view neighborhood preserving projections.
In: ML Research Press; 2011:425-432.'
apa: 'Quadrianto, N., & Lampert, C. (2011). Learning multi-view neighborhood
preserving projections (pp. 425–432). Presented at the ICML: International Conference
on Machine Learning, Bellevue, United States: ML Research Press.'
chicago: Quadrianto, Novi, and Christoph Lampert. “Learning Multi-View Neighborhood
Preserving Projections,” 425–32. ML Research Press, 2011.
ieee: 'N. Quadrianto and C. Lampert, “Learning multi-view neighborhood preserving
projections,” presented at the ICML: International Conference on Machine Learning,
Bellevue, United States, 2011, pp. 425–432.'
ista: 'Quadrianto N, Lampert C. 2011. Learning multi-view neighborhood preserving
projections. ICML: International Conference on Machine Learning, 425–432.'
mla: Quadrianto, Novi, and Christoph Lampert. Learning Multi-View Neighborhood
Preserving Projections. ML Research Press, 2011, pp. 425–32.
short: N. Quadrianto, C. Lampert, in:, ML Research Press, 2011, pp. 425–432.
conference:
end_date: 2011-07-02
location: Bellevue, United States
name: 'ICML: International Conference on Machine Learning'
start_date: 2011-06-28
corr_author: '1'
date_created: 2018-12-11T12:02:39Z
date_published: 2011-01-01T00:00:00Z
date_updated: 2024-10-09T20:54:32Z
day: '01'
department:
- _id: ChLa
language:
- iso: eng
month: '01'
oa_version: None
page: 425 - 432
publication_status: published
publisher: ML Research Press
publist_id: '3316'
scopus_import: '1'
status: public
title: Learning multi-view neighborhood preserving projections
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2011'
...
---
_id: '3320'
abstract:
- lang: eng
text: Powerful statistical models that can be learned efficiently from large amounts
of data are currently revolutionizing computer vision. These models possess a
rich internal structure reflecting task-specific relations and constraints. This
monograph introduces the reader to the most popular classes of structured models
in computer vision. Our focus is discrete undirected graphical models which we
cover in detail together with a description of algorithms for both probabilistic
inference and maximum a posteriori inference. We discuss separately recently successful
techniques for prediction in general structured models. In the second part of
this monograph we describe methods for parameter learning where we distinguish
the classic maximum likelihood based methods from the more recent prediction-based
parameter learning methods. We highlight developments to enhance current models
and discuss kernelized models and latent variable models. To make the monograph
more practical and to provide links to further study we provide examples of successful
application of many methods in the computer vision literature.
article_processing_charge: No
article_type: original
author:
- first_name: Sebastian
full_name: Nowozin, Sebastian
last_name: Nowozin
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: Nowozin S, Lampert C. Structured learning and prediction in computer vision.
Foundations and Trends in Computer Graphics and Vision. 2011;6(3-4):185-365.
doi:10.1561/0600000033
apa: Nowozin, S., & Lampert, C. (2011). Structured learning and prediction in
computer vision. Foundations and Trends in Computer Graphics and Vision.
Now Publishers. https://doi.org/10.1561/0600000033
chicago: Nowozin, Sebastian, and Christoph Lampert. “Structured Learning and Prediction
in Computer Vision.” Foundations and Trends in Computer Graphics and Vision.
Now Publishers, 2011. https://doi.org/10.1561/0600000033.
ieee: S. Nowozin and C. Lampert, “Structured learning and prediction in computer
vision,” Foundations and Trends in Computer Graphics and Vision, vol. 6,
no. 3–4. Now Publishers, pp. 185–365, 2011.
ista: Nowozin S, Lampert C. 2011. Structured learning and prediction in computer
vision. Foundations and Trends in Computer Graphics and Vision. 6(3–4), 185–365.
mla: Nowozin, Sebastian, and Christoph Lampert. “Structured Learning and Prediction
in Computer Vision.” Foundations and Trends in Computer Graphics and Vision,
vol. 6, no. 3–4, Now Publishers, 2011, pp. 185–365, doi:10.1561/0600000033.
short: S. Nowozin, C. Lampert, Foundations and Trends in Computer Graphics and Vision
6 (2011) 185–365.
corr_author: '1'
date_created: 2018-12-11T12:02:39Z
date_published: 2011-05-23T00:00:00Z
date_updated: 2024-10-09T20:54:32Z
day: '23'
ddc:
- '000'
department:
- _id: ChLa
doi: 10.1561/0600000033
file:
- access_level: open_access
checksum: f1043ef389f1558e2a226bb51568511f
content_type: application/pdf
creator: dernst
date_created: 2020-05-14T14:34:47Z
date_updated: 2020-07-14T12:46:07Z
file_id: '7837'
file_name: 2011_CompGraphicsVision_Nowozin.pdf
file_size: 3745064
relation: main_file
file_date_updated: 2020-07-14T12:46:07Z
has_accepted_license: '1'
intvolume: ' 6'
issue: 3-4
language:
- iso: eng
month: '05'
oa: 1
oa_version: Published Version
page: 185 - 365
publication: Foundations and Trends in Computer Graphics and Vision
publication_status: published
publisher: Now Publishers
publist_id: '3315'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Structured learning and prediction in computer vision
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 6
year: '2011'
...
---
_id: '3322'
abstract:
- lang: eng
text: We study multi-label prediction for structured output spaces, a problem that
occurs, for example, in object detection in images, secondary structure prediction
in computational biology, and graph matching with symmetries. Conventional multi-label
classification techniques are typically not applicable in this situation, because
they require explicit enumeration of the label space, which is infeasible in case
of structured outputs. Relying on techniques originally designed for single- label
structured prediction, in particular structured support vector machines, results
in reduced prediction accuracy, or leads to infeasible optimization problems.
In this work we derive a maximum-margin training formulation for multi-label structured
prediction that remains computationally tractable while achieving high prediction
accuracy. It also shares most beneficial properties with single-label maximum-margin
approaches, in particular a formulation as a convex optimization problem, efficient
working set training, and PAC-Bayesian generalization bounds.
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. Maximum Margin Multi Label Structured Prediction. Neural
Information Processing Systems Foundation; 2011.
apa: 'Lampert, C. (2011). Maximum margin multi label structured prediction.
NIPS: Neural Information Processing Systems. Neural Information Processing
Systems Foundation.'
chicago: 'Lampert, Christoph. Maximum Margin Multi Label Structured Prediction.
NIPS: Neural Information Processing Systems. Neural Information Processing
Systems Foundation, 2011.'
ieee: C. Lampert, Maximum margin multi label structured prediction. Neural
Information Processing Systems Foundation, 2011.
ista: Lampert C. 2011. Maximum margin multi label structured prediction, Neural
Information Processing Systems Foundation,p.
mla: 'Lampert, Christoph. “Maximum Margin Multi Label Structured Prediction.” NIPS:
Neural Information Processing Systems, Neural Information Processing Systems
Foundation, 2011.'
short: C. Lampert, Maximum Margin Multi Label Structured Prediction, Neural Information
Processing Systems Foundation, 2011.
date_created: 2018-12-11T12:02:40Z
date_published: 2011-12-13T00:00:00Z
date_updated: 2025-06-03T11:47:47Z
day: '13'
department:
- _id: ChLa
language:
- iso: eng
month: '12'
oa_version: None
publication: 'NIPS: Neural Information Processing Systems'
publication_status: published
publisher: Neural Information Processing Systems Foundation
publist_id: '3313'
related_material:
record:
- id: '3163'
relation: earlier_version
status: public
status: public
title: Maximum margin multi label structured prediction
type: conference_poster
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2011'
...
---
_id: '3336'
abstract:
- lang: eng
text: 'We introduce TopoCut: a new way to integrate knowledge about topological
properties (TPs) into random field image segmentation model. Instead of including
TPs as additional constraints during minimization of the energy function, we devise
an efficient algorithm for modifying the unary potentials such that the resulting
segmentation is guaranteed with the desired properties. Our method is more flexible
in the sense that it handles more topology constraints than previous methods,
which were only able to enforce pairwise or global connectivity. In particular,
our method is very fast, making it for the first time possible to enforce global
topological properties in practical image segmentation tasks.'
acknowledgement: The first author is supported by the Austrian Science Fund (FWF)
grant No. P20134-N13. The authors would like to thank Sebastian Nowozin for helpful
discussions.
article_processing_charge: No
author:
- first_name: Chao
full_name: Chen, Chao
id: 3E92416E-F248-11E8-B48F-1D18A9856A87
last_name: Chen
- first_name: Daniel
full_name: Freedman, Daniel
last_name: Freedman
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Chen C, Freedman D, Lampert C. Enforcing topological constraints in random
field image segmentation. In: CVPR: Computer Vision and Pattern Recognition.
IEEE; 2011:2089-2096. doi:10.1109/CVPR.2011.5995503'
apa: 'Chen, C., Freedman, D., & Lampert, C. (2011). Enforcing topological constraints
in random field image segmentation. In CVPR: Computer Vision and Pattern Recognition
(pp. 2089–2096). Colorado Springs, CO, United States: IEEE. https://doi.org/10.1109/CVPR.2011.5995503'
chicago: 'Chen, Chao, Daniel Freedman, and Christoph Lampert. “Enforcing Topological
Constraints in Random Field Image Segmentation.” In CVPR: Computer Vision and
Pattern Recognition, 2089–96. IEEE, 2011. https://doi.org/10.1109/CVPR.2011.5995503.'
ieee: 'C. Chen, D. Freedman, and C. Lampert, “Enforcing topological constraints
in random field image segmentation,” in CVPR: Computer Vision and Pattern Recognition,
Colorado Springs, CO, United States, 2011, pp. 2089–2096.'
ista: 'Chen C, Freedman D, Lampert C. 2011. Enforcing topological constraints in
random field image segmentation. CVPR: Computer Vision and Pattern Recognition.
CVPR: Conference on Computer Vision and Pattern Recognition, 2089–2096.'
mla: 'Chen, Chao, et al. “Enforcing Topological Constraints in Random Field Image
Segmentation.” CVPR: Computer Vision and Pattern Recognition, IEEE, 2011,
pp. 2089–96, doi:10.1109/CVPR.2011.5995503.'
short: 'C. Chen, D. Freedman, C. Lampert, in:, CVPR: Computer Vision and Pattern
Recognition, IEEE, 2011, pp. 2089–2096.'
conference:
end_date: 2011-06-25
location: Colorado Springs, CO, United States
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2011-06-20
corr_author: '1'
date_created: 2018-12-11T12:02:45Z
date_published: 2011-07-22T00:00:00Z
date_updated: 2024-10-09T20:54:30Z
day: '22'
department:
- _id: HeEd
- _id: ChLa
doi: 10.1109/CVPR.2011.5995503
language:
- iso: eng
month: '07'
oa_version: None
page: 2089 - 2096
publication: 'CVPR: Computer Vision and Pattern Recognition'
publication_identifier:
eisbn:
- 978-1-4577-0395-9
isbn:
- 978-1-4577-0394-2
publication_status: published
publisher: IEEE
publist_id: '3294'
quality_controlled: '1'
related_material:
record:
- id: '5386'
relation: earlier_version
status: public
scopus_import: '1'
status: public
title: Enforcing topological constraints in random field image segmentation
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2011'
...