---
OA_type: closed access
_id: '2971'
abstract:
- lang: eng
text: 'We study the task of interactive semantic labeling of a segmentation hierarchy.
To this end we propose a framework interleaving two components: an automatic labeling
step, based on a Conditional Random Field whose dependencies are defined by the
inclusion tree of the segmentation hierarchy, and an interaction step that integrates
incremental input from a human user. Evaluated on two distinct datasets, the proposed
interactive approach efficiently integrates human interventions and illustrates
the advantages of structured prediction in an interactive framework. '
alternative_title:
- LNCS
article_processing_charge: No
author:
- first_name: Georg
full_name: Zankl, Georg
last_name: Zankl
- first_name: Yll
full_name: Haxhimusa, Yll
last_name: Haxhimusa
- first_name: Adrian
full_name: Ion, Adrian
id: 29F89302-F248-11E8-B48F-1D18A9856A87
last_name: Ion
citation:
ama: 'Zankl G, Haxhimusa Y, Ion A. Interactive labeling of image segmentation hierarchies.
In: 34th DAGM and 36th OAGM Symposium. Vol 7476. Springer; 2012:11-20.
doi:10.1007/978-3-642-32717-9_2'
apa: 'Zankl, G., Haxhimusa, Y., & Ion, A. (2012). Interactive labeling of image
segmentation hierarchies. In 34th DAGM and 36th OAGM Symposium (Vol. 7476,
pp. 11–20). Graz, Austria: Springer. https://doi.org/10.1007/978-3-642-32717-9_2'
chicago: Zankl, Georg, Yll Haxhimusa, and Adrian Ion. “Interactive Labeling of Image
Segmentation Hierarchies.” In 34th DAGM and 36th OAGM Symposium, 7476:11–20.
Springer, 2012. https://doi.org/10.1007/978-3-642-32717-9_2.
ieee: G. Zankl, Y. Haxhimusa, and A. Ion, “Interactive labeling of image segmentation
hierarchies,” in 34th DAGM and 36th OAGM Symposium, Graz, Austria, 2012,
vol. 7476, pp. 11–20.
ista: Zankl G, Haxhimusa Y, Ion A. 2012. Interactive labeling of image segmentation
hierarchies. 34th DAGM and 36th OAGM Symposium. Pattern Recognition, LNCS, vol.
7476, 11–20.
mla: Zankl, Georg, et al. “Interactive Labeling of Image Segmentation Hierarchies.”
34th DAGM and 36th OAGM Symposium, vol. 7476, Springer, 2012, pp. 11–20,
doi:10.1007/978-3-642-32717-9_2.
short: G. Zankl, Y. Haxhimusa, A. Ion, in:, 34th DAGM and 36th OAGM Symposium, Springer,
2012, pp. 11–20.
conference:
end_date: 2012-08-31
location: Graz, Austria
name: Pattern Recognition
start_date: 2012-08-28
date_created: 2018-12-11T12:00:37Z
date_published: 2012-08-01T00:00:00Z
date_updated: 2025-05-20T07:21:42Z
day: '01'
department:
- _id: HeEd
doi: 10.1007/978-3-642-32717-9_2
intvolume: ' 7476'
language:
- iso: eng
month: '08'
oa_version: None
page: 11 - 20
publication: 34th DAGM and 36th OAGM Symposium
publication_identifier:
eisbn:
- '9783642327179'
eissn:
- 1611-3349
publication_status: published
publisher: Springer
publist_id: '3737'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Interactive labeling of image segmentation hierarchies
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 7476
year: '2012'
...
---
_id: '3265'
abstract:
- lang: eng
text: We propose a mid-level statistical model for image segmentation that composes
multiple figure-ground hypotheses (FG) obtained by applying constraints at different
locations and scales, into larger interpretations (tilings) of the entire image.
Inference is cast as optimization over sets of maximal cliques sampled from a
graph connecting all non-overlapping figure-ground segment hypotheses. Potential
functions over cliques combine unary, Gestalt-based figure qualities, and pairwise
compatibilities among spatially neighboring segments, constrained by T-junctions
and the boundary interface statistics of real scenes. Learning the model parameters
is based on maximum likelihood, alternating between sampling image tilings and
optimizing their potential function parameters. State of the art results are reported
on the Berkeley and Stanford segmentation datasets, as well as VOC2009, where
a 28% improvement was achieved.
article_number: '6126486'
author:
- first_name: Adrian
full_name: Ion, Adrian
id: 29F89302-F248-11E8-B48F-1D18A9856A87
last_name: Ion
- first_name: Joao
full_name: Carreira, Joao
last_name: Carreira
- first_name: Cristian
full_name: Sminchisescu, Cristian
last_name: Sminchisescu
citation:
ama: 'Ion A, Carreira J, Sminchisescu C. Image segmentation by figure-ground composition
into maximal cliques. In: IEEE; 2012. doi:10.1109/ICCV.2011.6126486'
apa: 'Ion, A., Carreira, J., & Sminchisescu, C. (2012). Image segmentation by
figure-ground composition into maximal cliques. Presented at the ICCV: International
Conference on Computer Vision, Barcelona, Spain: IEEE. https://doi.org/10.1109/ICCV.2011.6126486'
chicago: Ion, Adrian, Joao Carreira, and Cristian Sminchisescu. “Image Segmentation
by Figure-Ground Composition into Maximal Cliques.” IEEE, 2012. https://doi.org/10.1109/ICCV.2011.6126486.
ieee: 'A. Ion, J. Carreira, and C. Sminchisescu, “Image segmentation by figure-ground
composition into maximal cliques,” presented at the ICCV: International Conference
on Computer Vision, Barcelona, Spain, 2012.'
ista: 'Ion A, Carreira J, Sminchisescu C. 2012. Image segmentation by figure-ground
composition into maximal cliques. ICCV: International Conference on Computer Vision,
6126486.'
mla: Ion, Adrian, et al. Image Segmentation by Figure-Ground Composition into
Maximal Cliques. 6126486, IEEE, 2012, doi:10.1109/ICCV.2011.6126486.
short: A. Ion, J. Carreira, C. Sminchisescu, in:, IEEE, 2012.
conference:
end_date: 2011-11-13
location: Barcelona, Spain
name: 'ICCV: International Conference on Computer Vision'
start_date: 2011-11-06
date_created: 2018-12-11T12:02:21Z
date_published: 2012-01-12T00:00:00Z
date_updated: 2021-01-12T07:42:15Z
day: '12'
department:
- _id: HeEd
doi: 10.1109/ICCV.2011.6126486
language:
- iso: eng
month: '01'
oa_version: None
publication_status: published
publisher: IEEE
publist_id: '3382'
quality_controlled: '1'
status: public
title: Image segmentation by figure-ground composition into maximal cliques
type: conference
user_id: 4435EBFC-F248-11E8-B48F-1D18A9856A87
year: '2012'
...
---
_id: '3266'
abstract:
- lang: eng
text: We present a joint image segmentation and labeling model (JSL) which, given
a bag of figure-ground segment hypotheses extracted at multiple image locations
and scales, constructs a joint probability distribution over both the compatible
image interpretations (tilings or image segmentations) composed from those segments,
and over their labeling into categories. The process of drawing samples from the
joint distribution can be interpreted as first sampling tilings, modeled as maximal
cliques, from a graph connecting spatially non-overlapping segments in the bag
[1], followed by sampling labels for those segments, conditioned on the choice
of a particular tiling. We learn the segmentation and labeling parameters jointly,
based on Maximum Likelihood with a novel Incremental Saddle Point estimation procedure.
The partition function over tilings and labelings is increasingly more accurately
approximated by including incorrect configurations that a not-yet-competent model
rates probable during learning. We show that the proposed methodologymatches the
current state of the art in the Stanford dataset [2], as well as in VOC2010, where
41.7% accuracy on the test set is achieved.
author:
- first_name: Adrian
full_name: Ion, Adrian
id: 29F89302-F248-11E8-B48F-1D18A9856A87
last_name: Ion
- first_name: Joao
full_name: Carreira, Joao
last_name: Carreira
- first_name: Cristian
full_name: Sminchisescu, Cristian
last_name: Sminchisescu
citation:
ama: 'Ion A, Carreira J, Sminchisescu C. Probabilistic joint image segmentation
and labeling. In: NIPS Proceedings. Vol 24. Neural Information Processing
Systems Foundation; 2011:1827-1835.'
apa: 'Ion, A., Carreira, J., & Sminchisescu, C. (2011). Probabilistic joint
image segmentation and labeling. In NIPS Proceedings (Vol. 24, pp. 1827–1835).
Granada, Spain: Neural Information Processing Systems Foundation.'
chicago: Ion, Adrian, Joao Carreira, and Cristian Sminchisescu. “Probabilistic Joint
Image Segmentation and Labeling.” In NIPS Proceedings, 24:1827–35. Neural
Information Processing Systems Foundation, 2011.
ieee: A. Ion, J. Carreira, and C. Sminchisescu, “Probabilistic joint image segmentation
and labeling,” in NIPS Proceedings, Granada, Spain, 2011, vol. 24, pp.
1827–1835.
ista: 'Ion A, Carreira J, Sminchisescu C. 2011. Probabilistic joint image segmentation
and labeling. NIPS Proceedings. NIPS: Neural Information Processing Systems vol.
24, 1827–1835.'
mla: Ion, Adrian, et al. “Probabilistic Joint Image Segmentation and Labeling.”
NIPS Proceedings, vol. 24, Neural Information Processing Systems Foundation,
2011, pp. 1827–35.
short: A. Ion, J. Carreira, C. Sminchisescu, in:, NIPS Proceedings, Neural Information
Processing Systems Foundation, 2011, pp. 1827–1835.
conference:
end_date: 2011-12-14
location: Granada, Spain
name: 'NIPS: Neural Information Processing Systems'
start_date: 2011-12-12
date_created: 2018-12-11T12:02:21Z
date_published: 2011-12-01T00:00:00Z
date_updated: 2021-01-12T07:42:15Z
day: '01'
department:
- _id: HeEd
intvolume: ' 24'
language:
- iso: eng
month: '12'
oa_version: None
page: 1827 - 1835
publication: NIPS Proceedings
publication_status: published
publisher: Neural Information Processing Systems Foundation
publist_id: '3381'
quality_controlled: '1'
scopus_import: 1
status: public
title: Probabilistic joint image segmentation and labeling
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 24
year: '2011'
...
---
_id: '10907'
abstract:
- lang: eng
text: This paper presents a method to create a model of an articulated object using
the planar motion in an initialization video. The model consists of rigid parts
connected by points of articulation. The rigid parts are described by the positions
of salient feature-points tracked throughout the video. Following a filtering
step that identifies points that belong to different objects, rigid parts are
found by a grouping process in a graph pyramid. Valid articulation points are
selected by verifying multiple hypotheses for each pair of parts.
acknowledgement: This work has been partially supported by the Austrian Science Fund
under grants S9103-N13 and P18716-N13.
alternative_title:
- LNCS
article_processing_charge: No
author:
- first_name: Nicole M.
full_name: Artner, Nicole M.
last_name: Artner
- first_name: Adrian
full_name: Ion, Adrian
id: 29F89302-F248-11E8-B48F-1D18A9856A87
last_name: Ion
- first_name: Walter G.
full_name: Kropatsch, Walter G.
last_name: Kropatsch
citation:
ama: 'Artner NM, Ion A, Kropatsch WG. Spatio-temporal extraction of articulated
models in a graph pyramid. In: Jiang X, Ferrer M, Torsello A, eds. Graph-Based
Representations in Pattern Recognition. Vol 6658. LNIP. Berlin, Heidelberg:
Springer; 2011:215-224. doi:10.1007/978-3-642-20844-7_22'
apa: 'Artner, N. M., Ion, A., & Kropatsch, W. G. (2011). Spatio-temporal extraction
of articulated models in a graph pyramid. In X. Jiang, M. Ferrer, & A. Torsello
(Eds.), Graph-Based Representations in Pattern Recognition (Vol. 6658,
pp. 215–224). Berlin, Heidelberg: Springer. https://doi.org/10.1007/978-3-642-20844-7_22'
chicago: 'Artner, Nicole M., Adrian Ion, and Walter G. Kropatsch. “Spatio-Temporal
Extraction of Articulated Models in a Graph Pyramid.” In Graph-Based Representations
in Pattern Recognition, edited by Xiaoyi Jiang, Miquel Ferrer, and Andrea
Torsello, 6658:215–24. LNIP. Berlin, Heidelberg: Springer, 2011. https://doi.org/10.1007/978-3-642-20844-7_22.'
ieee: N. M. Artner, A. Ion, and W. G. Kropatsch, “Spatio-temporal extraction of
articulated models in a graph pyramid,” in Graph-Based Representations in Pattern
Recognition, Münster, Germany, 2011, vol. 6658, pp. 215–224.
ista: 'Artner NM, Ion A, Kropatsch WG. 2011. Spatio-temporal extraction of articulated
models in a graph pyramid. Graph-Based Representations in Pattern Recognition.
GbRPR: Graph-based Representations in Pattern RecognitionLNIP, LNCS, vol. 6658,
215–224.'
mla: Artner, Nicole M., et al. “Spatio-Temporal Extraction of Articulated Models
in a Graph Pyramid.” Graph-Based Representations in Pattern Recognition,
edited by Xiaoyi Jiang et al., vol. 6658, Springer, 2011, pp. 215–24, doi:10.1007/978-3-642-20844-7_22.
short: N.M. Artner, A. Ion, W.G. Kropatsch, in:, X. Jiang, M. Ferrer, A. Torsello
(Eds.), Graph-Based Representations in Pattern Recognition, Springer, Berlin,
Heidelberg, 2011, pp. 215–224.
conference:
end_date: 2011-05-20
location: Münster, Germany
name: 'GbRPR: Graph-based Representations in Pattern Recognition'
start_date: 2011-05-18
corr_author: '1'
date_created: 2022-03-21T08:08:35Z
date_published: 2011-06-01T00:00:00Z
date_updated: 2024-10-09T21:02:32Z
day: '01'
department:
- _id: HeEd
doi: 10.1007/978-3-642-20844-7_22
editor:
- first_name: Xiaoyi
full_name: Jiang, Xiaoyi
last_name: Jiang
- first_name: Miquel
full_name: Ferrer, Miquel
last_name: Ferrer
- first_name: Andrea
full_name: Torsello, Andrea
last_name: Torsello
intvolume: ' 6658'
language:
- iso: eng
month: '06'
oa_version: None
page: 215-224
place: Berlin, Heidelberg
publication: Graph-Based Representations in Pattern Recognition
publication_identifier:
eisbn:
- '9783642208447'
eissn:
- 1611-3349
isbn:
- '9783642208430'
issn:
- 0302-9743
publication_status: published
publisher: Springer
quality_controlled: '1'
scopus_import: '1'
series_title: LNIP
status: public
title: Spatio-temporal extraction of articulated models in a graph pyramid
type: conference
user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1
volume: 6658
year: '2011'
...
---
_id: '9648'
abstract:
- lang: eng
text: In this paper, we establish a correspondence between the incremental algorithm
for computing AT-models [8,9] and the one for computing persistent homology [6,14,15].
We also present a decremental algorithm for computing AT-models that allows to
extend the persistence computation to a wider setting. Finally, we show how to
combine incremental and decremental techniques for persistent homology computation.
alternative_title:
- LNCS
article_processing_charge: No
author:
- first_name: Rocio
full_name: Gonzalez-Diaz, Rocio
last_name: Gonzalez-Diaz
- first_name: Adrian
full_name: Ion, Adrian
id: 29F89302-F248-11E8-B48F-1D18A9856A87
last_name: Ion
- first_name: Maria Jose
full_name: Jimenez, Maria Jose
last_name: Jimenez
- first_name: Regina
full_name: Poyatos, Regina
last_name: Poyatos
citation:
ama: 'Gonzalez-Diaz R, Ion A, Jimenez MJ, Poyatos R. Incremental-decremental algorithm
for computing AT-models and persistent homology. In: Computer Analysis of Images
and Patterns. Vol 6854. Springer Nature; 2011:286-293. doi:10.1007/978-3-642-23672-3_35'
apa: 'Gonzalez-Diaz, R., Ion, A., Jimenez, M. J., & Poyatos, R. (2011). Incremental-decremental
algorithm for computing AT-models and persistent homology. In Computer Analysis
of Images and Patterns (Vol. 6854, pp. 286–293). Seville, Spain: Springer
Nature. https://doi.org/10.1007/978-3-642-23672-3_35'
chicago: Gonzalez-Diaz, Rocio, Adrian Ion, Maria Jose Jimenez, and Regina Poyatos.
“Incremental-Decremental Algorithm for Computing AT-Models and Persistent Homology.”
In Computer Analysis of Images and Patterns, 6854:286–93. Springer Nature,
2011. https://doi.org/10.1007/978-3-642-23672-3_35.
ieee: R. Gonzalez-Diaz, A. Ion, M. J. Jimenez, and R. Poyatos, “Incremental-decremental
algorithm for computing AT-models and persistent homology,” in Computer Analysis
of Images and Patterns, Seville, Spain, 2011, vol. 6854, pp. 286–293.
ista: 'Gonzalez-Diaz R, Ion A, Jimenez MJ, Poyatos R. 2011. Incremental-decremental
algorithm for computing AT-models and persistent homology. Computer Analysis of
Images and Patterns. CAIP: International Conference on Computer Analysis of Images
and Patterns, LNCS, vol. 6854, 286–293.'
mla: Gonzalez-Diaz, Rocio, et al. “Incremental-Decremental Algorithm for Computing
AT-Models and Persistent Homology.” Computer Analysis of Images and Patterns,
vol. 6854, Springer Nature, 2011, pp. 286–93, doi:10.1007/978-3-642-23672-3_35.
short: R. Gonzalez-Diaz, A. Ion, M.J. Jimenez, R. Poyatos, in:, Computer Analysis
of Images and Patterns, Springer Nature, 2011, pp. 286–293.
conference:
end_date: 2011-08-31
location: Seville, Spain
name: 'CAIP: International Conference on Computer Analysis of Images and Patterns'
start_date: 2011-08-29
date_created: 2021-07-11T22:01:19Z
date_published: 2011-08-01T00:00:00Z
date_updated: 2026-04-16T10:09:19Z
day: '01'
department:
- _id: HeEd
doi: 10.1007/978-3-642-23672-3_35
intvolume: ' 6854'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://hdl.handle.net/11441/30766
month: '08'
oa: 1
oa_version: Published Version
page: 286-293
publication: Computer Analysis of Images and Patterns
publication_identifier:
eissn:
- 1611-3349
isbn:
- '9783642236716'
issn:
- 0302-9743
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
scopus_import: '1'
status: public
title: Incremental-decremental algorithm for computing AT-models and persistent homology
type: conference
user_id: ba8df636-2132-11f1-aed0-ed93e2281fdd
volume: 6854
year: '2011'
...