|
|
cosyBib2005.bib
@INPROCEEDINGS{stimecCVWW05,
AUTHOR = {Ale\v{s} \v{S}timec and Matja\v{z} Jogan and Ale\v{s} Leonardis},
TITLE = {A hierarchy of cognitive maps from panoramic images},
BOOKTITLE = {CVWW 2005},
YEAR = {2005},
PAGES = {185--194},
ADDRESS = {Zell an der Pram, Austria},
MONTH = {February},
ABSTRACT = {This paper presents a computational model which implements a hierarchy
of cognitive maps based on panoramic images of the environment. The
resulting map consists of place cells placed in a topologically consistent
metric space. The formation of the cognitive map is achieved by passing
subspace representations of panoramic images to a computational model
inspired by Hafner. A physical force model is applied to translate
the non-metric map to a sparse topological map with metric information
using local relative orientations only. Finally, a hierarchy of maps
is formed in order to implement different levels of representations.},
URL = {http://www.cognitivesystems.org/publications/uol_as_cvww05.pdf}
}
@INPROCEEDINGS{artacIROS05,
AUTHOR = {Matej Arta\v{c} and Matja\v{z} Jogan and Hynek Bakstein and Ale\v{s}
Leonardis},
TITLE = {Panoramic Volumes for Robot Localization},
BOOKTITLE = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
YEAR = {2005},
PAGES = {3776--3782},
ADDRESS = {Edmonton, Alberta, Canada},
MONTH = {August},
ABSTRACT = {We propose a method for visual robot localization using a panoramic
image volume as the representation from which we can generate views
from virtual viewpoints and match them to the current view. We use
a geometric image-based rendering formalism in combination with a
subspace representation of images, which allows us to synthesize
views at arbitrary virtual viewpoints from a compact low-dimensional
representation.},
URL = {http://www.cognitivesystems.org/publications/uol_ma_iros05.pdf}
}
@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.}
}
@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.}
}
@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.mis.informatik.tu-darmstadt.de/Publications/index.html#cvpr05_leibe}
}
@INPROCEEDINGS{martinez2005icra,
AUTHOR = {Mart\'{i}nez Mozos, O. and Stachniss, C. and Burgard, W.},
TITLE = {Supervised Learning of Places from Range Data using AdaBoost},
BOOKTITLE = {Proc.~of the IEEE Int.~Conf.~on Robotics \& Automation (ICRA)},
YEAR = {2005},
PAGES = {1742-1747},
ADDRESS = {Barcelona, Spain},
MONTH = {April},
ABSTRACT = {This paper addresses the problem of classifying places in the environment
of a mobile robot into semantic categories. We believe that semantic
information about the type of place improves the capabilities of
a mobile robot in various domains including localization, path-planning,
or human-robot interaction. Our approach uses AdaBoost, a supervised
learning algorithm, to train a set of classifiers for place recognition
based on laser range data. In this paper we describe how this approach
can be applied to distinguish between rooms, corridors, doorways,
and hallways. Experimental results obtained in simulation and with
real robots demonstrate the effectiveness of our approach in various
environments.},
URL = {http://www.cognitivesystems.org/publications/martinez2005icra.pdf},
VIDEO = {http://www.informatik.uni-freiburg.de/~omartine/multimedia/fr079-online-classification.anim.avi}
}
@INPROCEEDINGS{Mikolajczyk05c,
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.}
}
@INPROCEEDINGS{peternelHAREM05,
AUTHOR = {Miha Peternel and Ale\v{s} Leonardis},
TITLE = {Activity Recognition via Autoregressive Prediction of Velocity Distribution},
BOOKTITLE = {Workshop on Human Activity Recognition and Modelling - HAREM 2005},
YEAR = {2005},
PAGES = {71--78},
MONTH = {September},
ABSTRACT = {We present a novel approach for view-based learning and recognition
of motion patterns of articulated objects. We formulate the intervals
of motion as a predictive model of local spatio-temporal receptive
field activation. We compute local velocity distribution using a
Bayesian approach, and then approximate the local velocity distribution
in space and time using a set of Gaussian receptive fields. The activation
sequence of receptive fields over time is modeled in a PCA subspace
using linear auto-regression to arrive at a model of the motion pattern.
Recognition is performed using the MDL principle. We test the approach
on a number of human motion patterns to demonstrate the applicability
of the proposed approach to simple action recognition and identification.},
LOCATION = {Oxford, UK},
URL = {http://www.cognitivesystems.org/publications/uol_mp_harem2005.pdf}
}
@INPROCEEDINGS{rothDAGM05,
AUTHOR = {P. Roth and H. Grabner and D. Sko\v{c}aj and H. Bischof and A. Leonardis},
TITLE = {Conservative visual learning for object detection with minimal hand
labeling effort},
BOOKTITLE = {DAGM 2005, Lect. notes comput. sci.},
YEAR = {2005},
PAGES = {761-775},
ADDRESS = {Vienna, Austria},
ABSTRACT = {We present a novel framework for unsupervised training of an object
detection system. The basic idea is to (1) exploit a huge amount
of unlabeled video data by being very conservative in selecting training
examples; and (2) to start with a very simple object detection system
and using generative and discriminative classifiers in an iterative
co- training fashion arriving at a better object detector. We demonstrate
the framework on a surveillance task where we learn a person detector.
We start with a simple moving object classiffier and proceed with
a robust PCA (on shape and appearance) as a generative classiffier
which in turn generates a training set for a discriminative AdaBoost
classiffier. The results obtained by AdaBoost are again filtered
by PCA which produces an even better training set. We demonstrate
that by using this approach we avoid hand labeling training data
and still achieve a state of the art detection rate.},
URL = {http://www.cognitivesystems.org/publications/rothDAGM05.pdf}
}
@INPROCEEDINGS{rothVSPETS05,
AUTHOR = {P. Roth and H. Grabner and D. Sko\v{c}aj and H. Bischof and A. Leonardis},
TITLE = {On-line conservative learning for person detection},
BOOKTITLE = {2nd Joint IEEE International Workshop on Visual Surveillance and
Performance Evaluation of Tracking and Surveillance (VS-PETS)},
YEAR = {2005},
PAGES = {223-230},
ADDRESS = {Beijing, China},
MONTH = {October 15-16},
ABSTRACT = {We present a novel on-line conservative learning framework for an
object detection system. All algorithms operate in an on-line mode,
in particular we also present a novel on-line AdaBoost method. The
basic idea is to exploit a huge amount of unlabeled video data by
being very conservative in selecting training examples and to start
with a very simple object detection system and using reconstructive
and discriminative classifiers in an iterative co-training fashion
to arrive at increasingly better object detectors. We demonstrate
the framework on a surveillance task where we learn person detectors
that are tested on two surveillance video sequences. We start with
a simple moving object classifier and proceed with incremental PCA
(on shape and appearance) as a reconstructive classifier which in
turn generates a training set for a discriminative on-line AdaBoost
classifier.},
URL = {http://www.cognitivesystems.org/publications/rothVSPETS05.pdf}
}
@INPROCEEDINGS{rottmann05aaai,
AUTHOR = {Rottmann, A. and Mart\'{i}nez Mozos, O. and Stachniss, C. and Burgard,
W.},
TITLE = {Place Classification of Indoor Environments with Mobile Robots using
Boosting},
BOOKTITLE = {Proc.~of the National Conference on Artificial Intelligence (AAAI)},
YEAR = {2005},
PAGES = {1306-1311},
ADDRESS = {Pittsburgh, PA, USA},
ABSTRACT = {Indoor environments can typically be divided into places with different
functionalities like kitchens, offices, or seminar rooms. We believe
that such semantic information enables a mobile robot to more efficiently
accomplish a variety of tasks such as human-robot interaction, path-planning,
or localization. This paper presents a supervised learning approach
to label different locations using boosting. We train a classifier
using features extracted from vision and laser range data. Furthermore,
we apply a Hidden Markov Model to increase the robustness of the
final classification. Our technique has been implemented and tested
on real robots as well as in simulation. The experiments demonstrate
that our approach can be utilized to robustly classify places into
semantic categories. We also present an example of localization using
semantic labeling.},
URL = {http://www.cognitivesystems.org/publications/rottmann2005aaai.pdf},
VIDEO = {http://www.informatik.uni-freiburg.de/~omartine/multimedia/fr079-6classes-hmm2.anim.avi}
}
@INPROCEEDINGS{Seemann05,
AUTHOR = {E. Seemann and B. Leibe and K. Mikolajczyk and B. Schiele},
TITLE = {An Evaluation of Local Shape-Based Features for Pedestrian Detection},
BOOKTITLE = {British Machine Vision Conference},
YEAR = {2005},
ADDRESS = {Oxford, UK},
ABSTRACT = {Pedestrian detection in real world scenes is a challenging problem.
In recent years a variety of apprgoaches have been proposed, and
impressive results have been reported on a variety of databases.
This paper systematically evaluates (1) various local shape descriptors,
namely Shape Context and Local Chamfer descriptor and (2) four different
interest point detectors for the detection of pedestrians. Those
results are compared to the standard global Chamfer matching approach.
A main result of the paper is that Shape Context trained on real
edge images rather than on clean pedestrian silhouettes combined
with the Hessian-Laplace detector outperforms all other tested approaches.}
}
@INPROCEEDINGS{Sloman/etal:2005,
AUTHOR = {A. Sloman and J. Chappell},
TITLE = {{The Altricial-Precocial Spectrum for Robots}},
BOOKTITLE = {{Proceedings IJCAI'05}},
YEAR = {2005},
PAGES = {1187--1192},
ADDRESS = {Edinburgh},
PUBLISHER = {IJCAI},
NOTE = {http://www.cs.bham.ac.uk/research/cogaff/05.html\#200502},
ABSTRACT = {Several high level methodological debates among AI researchers, linguists,
psychologists and philosophers, appear to be endless, e.g. about
the need for and nature of representations, about the role of symbolic
processes, about embodiment, about situatedness, about whether symbol-grounding
is needed, and about whether a robot needs any knowledge at birth
or can start simply with a powerful learning mechanism. Consideration
of the variety of capabilities and development patterns on the precocial-altricial
spectrum in biological organisms will help us to see these debates
in a new light.
It seems that after evolution discovered how to make physical bodies
that grow themselves, it discovered how to make virtual machines
that grow themselves. Researchers attempting to design human-like,
chimp-like or crow-like intelligent robots will need to understand
how. Whether computers as we know them can provide the infrastructure
for such systems is a separate question.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/alt-prec-ijcai05.pdf}
}
@ARTICLE{Sloman/etal:2005a,
AUTHOR = {Aaron Sloman and Jackie Chappell},
TITLE = {{Altricial self-organising information-processing systems}},
JOURNAL = {AISB Quarterly},
YEAR = {2005},
PAGES = {5--7},
NUMBER = {121},
MONTH = {Summer 2005},
NOTE = {http://www.cs.bham.ac.uk/research/cogaff/05.html\#200503},
ABSTRACT = {It is often thought that there is one key design principle or at best
a small set of design principles, underlying the success of biological
organisms. Candidates include neural nets, `swarm intelligence',
evolutionary computation, dynamical systems, particular types of
architecture or use of a powerful uniform learning mechanism, e.g.
reinforcement learning. All of those support types of self-organising,
self-modifying behaviours. But we are nowhere near understanding
the full variety of powerful information-processing principles `discovered'
by evolution. By attending closely to the diversity of biological
phenomena we may gain key insights into (a) how evolution happens,
(b) what sorts of mechanisms, forms of representation, types of learning
and development and types of architectures have evolved, (c) how
to explain ill-understood aspects of human and animal intelligence,
and (d) new useful mechanisms for artificial systems. },
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/summary-gc7.pdf}
}
@BOOK{Sloman/etal:2005c,
TITLE = {{Tutorial on Learning and Representation in Animals and Robots}},
PUBLISHER = {IJCAI'05},
YEAR = {2005},
EDITOR = {A. Sloman and B. Schiele},
AUTHOR = {A. Sloman and B. Schiele},
ADDRESS = {Edinburgh},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/conferences},
ABSTRACT = {A two-day tutorial was held in The University of Edinburgh on 30th
and 31st July 2005 at IJCAI 2005 on REPRESENTATION AND LEARNING IN
ROBOTS AND ANIMALS.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/research/projects/cosy/conferences/}
}
@INPROCEEDINGS{stachniss2005isrr,
AUTHOR = {Stachniss, C. and Mart\'{i}nez-Mozos, O. and Rottmann, A. and Burgard,
W.},
TITLE = {Semantic Labeling of Places},
BOOKTITLE = {International Symposium of Robotics Research (ISRR)},
YEAR = {2005},
ADDRESS = {San Francisco, CA, USA},
MONTH = {October},
ABSTRACT = {Indoor environments can typically be divided into places with different
functionalities like corridors, kitchens, offices, or seminar rooms.
We believe that such semantic information enables a mobile robot
to more efficiently accomplish a variety of tasks such as human-robot
interaction, path-planning, or localization. In this paper, we propose
an approach to classify places in indoor environments into different
categories. Our approach uses AdaBoost to boost simple features extracted
from vision and laser range data. Furthermore, we apply a Hidden
Markov Model to take spatial dependencies between robot poses into
account and to increase the robustness of the classification. Our
technique has been implemented and tested on real robots as well
as in simulation. Experiments presented in this paper demonstrate
that our approach can be utilized to robustly classify places into
semantic categories.},
URL = {http://www.cognitivesystems.org/publications/stachniss2005isrr.pdf}
}
@INPROCEEDINGS{Wyatt:2005,
AUTHOR = {Jeremy Wyatt},
TITLE = {Planning clarification questions to resolve ambiguous references
to objects},
BOOKTITLE = {Proceedings of the 4th Workshop on Knowledge and Reasoning in Practical
Dialogue Systems, held at IJCAI 05},
YEAR = {2005},
ABSTRACT = {Our aim is to design robots that can have task directed conversations
with humans about objects in a table top scene. One of the pre-requisites
is that the robot is able to correctly identify the object to which
another speaker refers. This is not trivial as human references to
objects are often ambiguous, and rely on contextual information from
the scene, the task, or the dialogue to resolve the reference. This
paper describes work in progress on building a robot system able
to plan the content of clarifying questions that when answered provide
the robot with enough information to resolve ambiguous references.
It describes an algorithm that models the degree of uncertainty about
the binding of a referent using a probability distribution. We use
the visual salience of the object as a way to generate the prior
distribution over candidate objects, which we call the belief state.
Then we generate action models, for the effects of various clarifying
questions, on the fly. Finally we evaluate the mean reduction in
the entropy of the resulting belief states. The method can be seen
as a form of prior-posterior analysis, or as one step look ahead
in an information state Markov decision process. We are currently
implementing the algorithm in a robot and discuss the issues we have
encountered to date.},
DATE-ADDED = {2009-01-05 11:44:47 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/wyatt05ijcai.pdf}
}
This file has been generated by
bibtex2html 1.79
Print this page
|
