|
|
chap4.bib
@INPROCEEDINGS{s:fidler06,
AUTHOR = {S. Fidler and G. Berginc and A. Leonardis},
TITLE = {Hierarchical Statistical Learning of Generic Parts of Object Structure.},
BOOKTITLE = {CVPR},
YEAR = {2006},
PAGES = {182--189},
ABSTRACT = {With the growing interest in object categorization various methods
have emerged that perform well in this challenging task, yet are
inherently limited to only a moderate number of object classes. In
pursuit of a more general categorization system this paper proposes
a way to overcome the computational complexity encompassing the enormous
number of different object categories by exploiting the statistical
properties of the highly structured visual world. Our approach proposes
a hierarchical acquisition of generic parts of object structure,
varying from simple to more complex ones, which stem from the favorable
statistics of natural images. The parts recovered in the individual
layers of the hierarchy can be used in a top-down manner resulting
in a robust statistical engine that could be efficiently used within
many of the current categorization systems. The proposed approach
has been applied to large image datasets yielding important statistical
insights into the generic parts of object structure.}
}
@INPROCEEDINGS{s:fidler07,
AUTHOR = {S. Fidler and A. Leonardis},
TITLE = {Towards Scalable Representations of Visual Categories: Learning a
Hierarchy of parts.},
BOOKTITLE = {CVPR'07},
YEAR = {2007},
ABSTRACT = {This paper proposes a novel approach to constructing a hierarchical
representation of visual input that aims to enable recognition and
detection of a large number of object categories. Inspired by the
principles of efficient indexing (bottom-up,), robust matching (top-down,),
and ideas of compositionality, our approach learns a hierarchy of
spatially flexible compositions, i.e. parts, in an unsupervised,
statistics-driven manner. Starting with simple, frequent features,
we learn the statistically most significant compositions (parts composed
of parts), which consequently define the next layer. Parts are learned
sequentially, layer after layer, optimally adjusting to the visual
data. Lower layers are learned in a category-independent way to obtain
complex, yet sharable visual building blocks, which is a crucial
step towards a scalable representation. Higher layers of the hierarchy,
on the other hand, are constructed by using specific categories,
achieving a category representation with a small number of highly
generalizable parts that gained their structural flexibility through
composition within the hierarchy. Built in this way, new categories
can be efficiently and continuously added to the system by adding
a small number of parts only in the higher layers. The approach is
demonstrated on a large collection of images and a variety of object
categories. Detection results confirm the effectiveness and robustness
of the learned parts.}
}
@INPROCEEDINGS{Fritz05,
AUTHOR = {M. Fritz and B. Leibe and B. Caputo and B. Schiele},
TITLE = {Integrating Representative and Discriminant Models for Object Category
Detection},
BOOKTITLE = {Proceedings of International Conference on Computer Vision 2005},
YEAR = {2005},
ADDRESS = {Beijing, China},
MONTH = OCT,
ABSTRACT = {Category detection is a lively area of research. While categorization
algorithms tend to agree in using local descriptors, they differ
in the choice of the classifier, with some using generative models
and others discriminative approaches. This paper presents a method
for object category detection which integrates a generative model
with a discriminative classifier. For each object category, we generate
an appearance codebook, which becomes a common vocabulary for the
generative and discriminative methods. Given a query image, the generative
part of the algorithm finds a set of hypotheses and estimates their
support in location and scale. Then, the discriminative part verifies
each hypothesis on the same codebook activations. The new algorithm
exploits the strengths of both original methods, minimizing their
weaknesses. Experiments on several databases show that our new approach
performs better than its building blocks taken separately. Moreover,
experiments on two challenging multi-scale databases show that our
new algorithm outperforms previously reported results.},
URL = {http://www.cognitivesystems.org/publications/fritz-represdiscrim-iccv05.pdf}
}
@INPROCEEDINGS{fritz08cvpr,
AUTHOR = {Mario Fritz and Bernt Schiele},
TITLE = {Decomposition, Discovery and Detection of Visual Categories Using
Topic Models},
BOOKTITLE = {Proceedings of CVPR},
YEAR = {2008},
MONTH = JUN,
ABSTRACT = {We present a novel method for the discovery and detection of visual
object categories based on decompositions using topic models. The
approach is capable of learning a compact and low dimensional representation
for multiple visual categories from multiple view points without
labeling of the training instances. The learnt object components
range from local structures over line segments to global silhouette-like
descriptions. This representation can be used to discover object
categories in a totally unsupervised fashion. Furthermore we employ
the representation as the basis for building a supervised multi-category
detection system making efficient use of training examples and outperforming
pure features-based representations. The proposed speed-ups make
the system scale to large databases. Experiments on three databases
show that the approach improves the state-of-the-art in unsupervised
learning as well as supervised detection. In particular we improve
the state-of-the-art on the challenging PASCAL'06 multi-class detection
tasks for several categories.},
URL = {http://www.cognitivesystems.org/publications/fritz08cvpr.pdf}
}
@ARTICLE{Leibe05c,
AUTHOR = {B. Leibe and A. Leonardis and B. Schiele},
TITLE = {Robust Object Detection by Interleaving Categorization and Segmentation},
JOURNAL = {International Journal of Computer Vision},
YEAR = {2005},
ABSTRACT = {This paper presents a new method for visual object categorization,
i.e.~for recognizing previously unseen objects, localizing them in
cluttered images, and assigning the correct category label. It considers
object categorization and figure-ground segmentation as two interleaved
processes that closely collaborate towards a common goal. As shown
in our work, the tight coupling between those two processes allows
them to profit from each other and improve the combined performance.
The core part of our work is a highly flexible learned representation
for object shape that can combine the information observed on different
training examples in a probabilistic extension of the Generalized
Hough Transform. The resulting approach can detect categorical objects
in novel images and automatically infer a probabilistic segmentation
from the recognition result. This segmentation is then used to again
improve recognition by allowing the system to focus its efforts on
object pixels and discard misleading influences from the background.
Moreover, the information from where in the image a hypothesis draws
its support is used in an MDL based hypothesis verification stage
to resolve ambiguities between overlapping hypotheses and factor
out the effects of partial occlusion. An extensive evaluation on
several large data sets shows that the proposed system is applicable
to a range of different object categories, including both rigid and
articulated objects. In addition, its flexible representation allows
it to achieve competitive object detection performance already from
training sets that are between one and two orders of magnitude smaller
than those used in comparable systems.},
URL = {http://www.cognitivesystems.org/publications/leibe-interleaved-ijcv07final.pdf}
}
@INPROCEEDINGS{leibe05cvpr,
AUTHOR = {Bastian Leibe and Edgar Seemann and Bernt Schiele},
TITLE = {Pedestrian Detection in Crowded Scenes},
BOOKTITLE = {CVPR '05: Proceedings of the 2005 IEEE Computer Society Conference
on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1},
YEAR = {2005},
PAGES = {878--885},
ADDRESS = {Washington, DC, USA},
PUBLISHER = {IEEE Computer Society},
ABSTRACT = {In this paper, we address the problem of detecting pedestrians in
crowded real-world scenes with severe overlaps. Our basic premise
is that this problem is too difficult for any type of model or feature
alone. Instead, we present a novel algorithm that integrates evidence
in multiple iterations and from different sources. The core part
of our method is the combination of local and global cues via a probabilistic
top-down segmentation. Altogether, this approach allows to examine
and compare object hypotheses with high precision down to the pixel
level. Qualitative and quantitative results on a large data set confirm
that our method is able to reliably detect pedestrians in crowded
scenes, even when they overlap and partially occlude each other.
In addition, the flexible nature of our approach allows it to operate
on very small training sets.},
ISBN = {0-7695-2372-2},
URL = {http://www.cognitivesystems.org/publications/leibe-crowdedscenes-cvpr05.pdf}
}
@INPROCEEDINGS{Mikolajczyk06c,
AUTHOR = {K. Mikolajczyk and B. Leibe and B. Schiele},
TITLE = {Multiple object class detection with a generative mode},
BOOKTITLE = {Proceedings of International Conference on Computer Vision and Pattern
Recognition 2006},
YEAR = {2006},
ADDRESS = {New York, USA},
MONTH = JUN,
ABSTRACT = {In this paper we propose an approach capable of simultaneous recognition
and localization of multiple object classes using a generative model.
We propose a novel hierarchical representation which allows to represent
individual images as well as various objects classes in a single
similarity invariant model. The recognition method is based on a
codebook representation where appearance clusters built from edge
based features are shared among several object classes. A probabilistic
model based on Bayesian rules allows for reliable detection of various
objects in the same image. The approach is very efficient due to
applied fast clustering and matching method capable of dealing with
millions of high dimensional features. The system shows an excellent
performance on several object categories in wide range of scales,
in-plane rotations, background clutter, and occlusion. The performance
is comparable with state of the art approaches dedicated to single
object classes.},
URL = {http://www.cognitivesystems.org/publications/mikolajczyk-multiclass-cvpr06.pdf}
}
@INPROCEEDINGS{conf/iccv/MikolajczykLS05,
AUTHOR = {K. Mikolajczyk and B. Leibe and B. Schiele},
TITLE = {Local Features for Object Class Recognition},
BOOKTITLE = {Proceedings of International Conference on Computer Vision 2005},
YEAR = {2005},
ADDRESS = {Beijing, China},
MONTH = OCT,
ABSTRACT = {In this paper we compare the performance of local detectors and descriptors
in the context of object class recognition. Recently, many detectors
/ descriptors have been evaluated in the context of matching as well
as invariance to viewpoint changes [Mikolajczyk,IJCV04]. However,
it is unclear if these results can be generalized to categorization
problems, which require different properties of features. We evaluate
5 state-of-the-art scale invariant region detectors and 5 descriptors.
Local features are computed for 20 object classes and clustered using
hierarchical agglomerative clustering. We measure the quality of
appearance clusters and location distributions using entropy as well
as precision. We also measure how the clusters generalize from training
set to novel test data. Our results indicate that extended SIFT descriptors
[Mikolajczyk,TR04a] computed on Hessian-Laplace [Mikolajczyk,IJCV04]
regions perform best. Second score is obtained by Salient regions
[Kadir,IJCV01]. The results also show that these two detectors provide
complementary features. The evaluation is validated with a recognition
approach on pedestrian database.},
URL = {http://www.cognitivesystems.org/publications/mikolajczyk-features-iccv05.pdf}
}
@INPROCEEDINGS{stark07iccv,
AUTHOR = {Michael Stark and Bernt Schiele},
TITLE = {How Good are Local Features for Classes of Geometric Objects},
BOOKTITLE = {Eleventh IEEE International Conference on Computer Vision (ICCV)},
YEAR = {2007},
MONTH = OCT,
NOTE = {Accepted},
ABSTRACT = {Recent work in object categorization often uses local image descriptors
such as SIFT to learn and detect object categories. As such descriptors
explicitly code local appearance they have shown impressive results
on objects with sufficient local appearance statistics. However,
many important object classes such as tools, cups and other man-made
artifacts seem to require features that capture the respective shape
and geometric layout of those object classes. Therefore this paper
compares, on a novel data collection of 10 geometric object classes,
various shape-based features with more appearance based descriptors
such as SIFT. The analysis includes a direct comparison of feature
statistics as well as the results within standard recognition frameworks.
The results suggest that there are indeed differences between shape-
based and more appearance-based features but that those differences
do not always conform with what one might expect.},
LOCATION = {Rio de Janeiro, Brazil},
URL = {http://www.cognitivesystems.org/publications/iccv07.pdf}
}
This file has been generated by
bibtex2html 1.79
Print this page
|
