CoSy logo Cognitive Systems for Cognitive Assistants
 
 
 

cosyBib2006.bib

@INPROCEEDINGS{Bertolli06a,
  AUTHOR = {Federico Bertolli and Patric Jensfelt and Henrik I. Christensen},
  TITLE = {SLAM using Visual Scan-Matching with Distinguishable 3D Points},
  BOOKTITLE = {Proc.~of the IEEE/RSJ International Conference on Intelligent Robots
	and Systems (IROS'05)},
  YEAR = {2006},
  URL = {http://www.cas.kth.se/~patric/publications/fedepaper.pdf}
}

@ARTICLE{fidlerPAMI06,
  AUTHOR = {Sanja Fidler and Danijel Sko\v{c}aj and Ale\v{s} Leonardis},
  TITLE = {Combining Reconstructive and Discriminative Subspace Methods for
	Robust Classification and Regression by Subsampling},
  JOURNAL = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  YEAR = {2006},
  VOLUME = {28},
  PAGES = {337-350},
  NUMBER = {3},
  MONTH = {March},
  ABSTRACT = {Linear subspace methods that provide sufficient reconstruction of
	the data such as PCA offer an efficient way of dealing with missing
	pixels, outliers, and occlusions that often appear in the visual
	data. Discriminative methods, such as LDA and CCA, which on the other
	hand, are better suited for classification and regression tasks,
	are highly sensitive to corrupted data. We present a theoretical
	framework for achieving best of both types of methods: an approach
	that combines the discrimination power of discriminative methods
	with the reconstruction property of reconstructive methods which
	enables one to work on subsets of pixels in images, to efficiently
	detect and reject the outliers. The proposed approach is therefore
	capable of robust classification/regression with a high-breakdown
	point. The theoretical results are demonstrated on several computer
	vision tasks showing that the proposed approach significantly outperforms
	the standard discriminative methods in the case of missing pixels
	and images containing occlusions and outliers.},
  OWNER = {danijels fidler vicos rpcv cosy mobvis DSSP1},
  TIMESTAMP = {2006.03.03},
  URL = {http://vicos.fri.uni-lj.si/data/publications/fidlerPAMI06.pdf}
}

@INPROCEEDINGS{Fritz06a,
  AUTHOR = {M. Fritz and B. Schiele},
  TITLE = {Towards Unsupervised Discovery of Visual Categories},
  BOOKTITLE = {Proceedings of 28th Annual Symposium of the German Association for
	Pattern Recognition (DAGM), Berlin, Germany},
  YEAR = {2006},
  MONTH = {September},
  ABSTRACT = {Recently, many approaches have been proposed for visual object category
	detection. They vary greatly in terms of how much supervision is
	needed. High performance ob ject detection methods tend to be trained
	in a supervised manner from relatively clean data. In order to deal
	with a large number of ob ject classes and large amounts of training
	data, there is a clear desire to use as little supervision as possible.
	This paper proposes a new approach for unsupervised learning of visual
	categories based on a scheme to detect reoccurring structure in sets
	of images. The approach finds the locations as well as the scales
	of such reoccurring structures in an unsupervised manner. In the
	experiments those reoccurring structures correspond to ob ject categories
	which can be used to directly learn object category models. Experimental
	results show the effectiveness of the new approach and compare the
	performance to previous fully-supervised methods.},
  URL = {http://www.mis.informatik.tu-darmstadt.de/People/mfritz/fritz06dagm.pdf}
}

@INPROCEEDINGS{hawesetal06gc5,
  AUTHOR = {Nick Hawes and Aaron Sloman and Jeremy Wyatt},
  TITLE = {Requirements \& Designs: Asking Scientific Questions About Architectures},
  BOOKTITLE = {Proceedings of the AISB '06 Symposium on GC5: Architecture of Brain
	and Mind: Integrating high level cognitive processes with brain mechanisms
	and functions in a working robot},
  YEAR = {2006},
  ADDRESS = {Bristol},
  MONTH = {April},
  ABSTRACT = {This paper discusses our views on the future of the field of cognitive
	architectures, and how the scientific questions that define it should
	be addressed. We also report on a set of requirements, and a related
	architecture design, that we are currently investigating as part
	of the CoSy project.},
  URL = {http://www.cs.bham.ac.uk/~nah/bibtex/papers/hawesetal06gc5.pdf}
}

@INPROCEEDINGS{haweswyatt06towards,
  AUTHOR = {Nick Hawes and Jeremy Wyatt},
  TITLE = {Towards Context-Sensitive Visual Attention},
  BOOKTITLE = {Proceedings of the Second International Cognitive Vision Workshop
	(ICVW06)},
  YEAR = {2006},
  ADDRESS = {Graz, Austria},
  MONTH = {May},
  ABSTRACT = {In this paper we present a discussion of information processing context
	and how we believe a visual attention system should be influenced
	by contextual information. We support this argument with a proof-of-concept
	design and implementation of a context-sensitive extension to the
	Itti & Koch model of visual attention as part of an architecture
	for a cognitive system. Our model demonstrates improved performance
	in terms of both fixations and processing time on visual search tasks
	compared to the non-extended model.},
  URL = {http://www.cs.bham.ac.uk/research/projects/cosy/bib-db/papers/haweswyatt06.pdf}
}

@INPROCEEDINGS{hongengwyatt06humanoids,
  AUTHOR = {S. Hongeng and J. L. Wyatt},
  TITLE = {Learning Causality and Intention in Human Actions},
  BOOKTITLE = {Proceedings of the 6th IEEE-RAS International Conference on Humanoid
	Robots},
  YEAR = {2006},
  ADDRESS = {Genoa{,} Italy},
  MONTH = {December},
  ABSTRACT = {Previous research has shown that human actions can be detected by
	motion patterns. However, labeling motion patterns is not sufficient
	in a cognitive system that requires reasoning about the agentā??s
	intentions, and how the environmental context affects the way an
	action is performed. In this paper, we develop a graphical model
	that captures how the movements that realize the action vary depending
	on the situations, and present statistical learning algorithms. Using
	object manipulation tasks, we illustrate how a system infers the
	agentā??s goals from visual observation and compare results with
	findings in psychological experiments.},
  URL = {http://www.cs.bham.ac.uk/~sxh/bibtex/papers/hongeng_humanoids06.pdf}
}

@INPROCEEDINGS{kruijffetal06pit,
  AUTHOR = {Geert-Jan M. Kruijff and John D. Kelleher and Nick Hawes},
  TITLE = {Information Fusion For Visual Reference Resolution In Dynamic Situated
	Dialogue},
  BOOKTITLE = {Perception and Interactive Technologies: International Tutorial and
	Research Workshop, PIT 2006},
  YEAR = {2006},
  EDITOR = {Elisabeth Andre and Laila Dybkjaer and Wolfgang Minker and Heiko
	Neumann and Michael Weber},
  VOLUME = {4021},
  SERIES = {Lecture Notes in Computer Science},
  PAGES = {117 -- 128},
  ADDRESS = {Kloster Irsee, Germany},
  MONTH = {June},
  PUBLISHER = {Springer Berlin / Heidelberg},
  ABSTRACT = {Human-Robot Interaction (HRI) invariably involves dialogue about objects
	in the environment in which the agents are situated. The paper focuses
	on the issue of resolving discourse references to such visual objects.
	The paper addresses the problem using strategies for intra-modal
	fusion (identifying that different occurrences concern the same object),
	and inter-modal fusion, (relating object references across different
	modalities). Core to these strategies are sensorimotoric coordination,
	and ontology-based mediation between content in different modalities.
	The approach has been fully implemented, and is illustrated with
	several working examples.},
  EE = {http://dx.doi.org/10.1007/11768029_12},
  URL = {http://www.cs.bham.ac.uk/~nah/bibtex/papers/kruijffetal06pit.pdf}
}

@INPROCEEDINGS{Kruijff06a,
  AUTHOR = {Geert-Jan M. Kruijff and Hendrik Zender and Patric Jensfelt and Henrik
	I. Christensen},
  TITLE = {Clarification dialogues in human-augmented mapping},
  BOOKTITLE = {Proc.~of the 1st Annual Conference on Human-Robot Interaction (HRI'06)},
  YEAR = {2006},
  ADDRESS = {Salt Lake City, UT},
  MONTH = MAR,
  URL = {http://www.cas.kth.se/~patric/publications/main.mapping.hri2006.pdf}
}

@INPROCEEDINGS{Kruijff06b,
  AUTHOR = {Geert-Jan M. Kruijff and Hendrik Zender and Patric Jensfelt and Henrik
	I. Christensen},
  TITLE = {Situated dialogue and understanding spatial organization: Knowing
	what is where and what you can do there},
  BOOKTITLE = {Proc.~of IEEE Workshop on Robot and Human Interactive Communication
	{(ROMAN)}},
  YEAR = {2006}
}

@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 = {2006},
  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{Leibe06c,
  AUTHOR = {B. Leibe and K. Mikolajczyk and B. Schiele},
  TITLE = {Efficient Clustering and Matching for Object Class Recognition},
  BOOKTITLE = {Proceedings of the 17th British Machine Vision Conference, Edinburgh,
	England},
  YEAR = {2006},
  ABSTRACT = {In this paper we address the problem of building object class representations
	based on local features and fast matching in a large database. We
	propose an efficient algorithm for hierarchical agglomerative clustering.
	We examine different agglomerative and partitional clustering strategies
	and compare the quality of obtained clusters. Our combination of
	partitional-agglomerative clustering gives significant improvement
	in terms of efficiency while maintaining the same quality of clusters.
	We also propose a method for building data structures for fast matching
	in high dimensional feature spaces. These improvements allow to deal
	with large sets of training data typically used in recognition of
	multiple object classes.},
  URL = {http://www.mis.informatik.tu-darmstadt.de/Publications/leibe-efficientclustering-bmvc06.pdf}
}

@INPROCEEDINGS{Leibe06d,
  AUTHOR = {B. Leibe and K. Mikolajczyk and B. Schiele},
  TITLE = {Segmentation Based Multi-Cue Integration for Object Detection},
  BOOKTITLE = {Proceedings of the 17th British Machine Vision Conference, Edinburgh,
	England},
  YEAR = {2006},
  ABSTRACT = {This paper proposes a novel method for integrating multiple local
	cues, i.e. local region detectors as well as descriptors, in the
	context of object detection. Rather than to fuse the outputs of several
	distinct classifiers in a fixed setup, our approach implements a
	highly flexible combination scheme, where the contributions of all
	individual cues are flexibly recombined depending on their explanatory
	power for each new test image. The key idea behind our approach is
	to integrate the cues over an estimated top-down segmentation, which
	allows to quantify how much each of them contributed to the object
	hypothesis. By combining those contributions on a per-pixel level,
	our approach ensures that each cue only contributes to object regions
	for which it is confident and that potential correlations between
	cues are effectively factored out. Experimental results on several
	benchmark data sets show that the proposed multi-cue combination
	scheme significantly increases detection performance compared to
	any of its constituent cues alone. Moreover, it provides an interesting
	evaluation tool to analyze the complementarity of local feature detectors
	and descriptors.},
  URL = {http://www.mis.informatik.tu-darmstadt.de/Publications/leibe-multicue-bmvc06.pdf}
}

@TECHREPORT{luo06kth_idol2,
  AUTHOR = {Luo, J. and Pronobis, A. and Caputo, B. and Jensfelt, P.},
  TITLE = {The {KTH-IDOL2} Database},
  INSTITUTION = {Kungliga Tekniska Hoegskolan, CVAP/CAS},
  YEAR = {2006},
  NUMBER = {CVAP304},
  MONTH = {October},
  URL = {http://www.csc.kth.se/~pronobis/research/luo06kth_idol2}
}

@INPROCEEDINGS{mozos2006iros,
  AUTHOR = {Mart\'{i}nez Mozos, O. and Burgard, W.},
  TITLE = {Supervised Learning of Topological Maps using Semantic Information
	Extracted from Range Data},
  BOOKTITLE = {Proc.~of the IEEE/RSJ International Conference on Intelligent Robots
	and Systems (IROS)},
  YEAR = {2006},
  PAGES = {2772-2777},
  ADDRESS = {Beijing, China},
  ABSTRACT = { This paper presents an approach to create topological maps from geometric
	maps obtained with a mobile robot in an indoor-environment using
	range data. Our approach uses AdaBoost, a supervised learning algorithm,
	to classify each point of the geometric map into semantic classes.
	We then apply a segmentation procedure based on probabilistic relaxation
	labeling on the resulting classications to eliminate errors. The
	topological graph is then extracted from the individual dierent
	regions and their connections. In this way, we obtain a topological
	map in the form of a graph, in which each node indicates a region
	in the environment with its corresponding semantic class (e.g., corridor,
	or room) and the edges indicate the connections between them. Experimental
	results obtained with data from dierent real-world environments
	demonstrate the effectiveness of our approach.},
  URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/mozos2006iros.pdf}
}

@INPROCEEDINGS{mozos2006iros_w,
  AUTHOR = {Mart\'{i}nez Mozos, O. and Rottmann, A. and Triebel, R. and Jensfelt,
	P. and Burgard, W.},
  TITLE = {Semantic Labeling of Places using Information Extracted from Laser
	and Vision Sensor Data},
  BOOKTITLE = {In Proc.~of the IEEE/RSJ IROS 2006 Workshop: From Sensors to Human
	Spatial Concepts},
  YEAR = {2006},
  ADDRESS = {Beijing, China},
  ABSTRACT = {Indoor environments can typically be divided into places with different
	functionalities like corridors, kitchens, offices, or seminar rooms.
	The ability to learn such semantic categories from sensor data enables
	a mobile robot to extend the representation of the environment facilitating
	the interaction with humans. As an example, natural language terms
	like ``corridor" or ``room" can be used to communicate the position
	of the robot in a map in a more intuitive way. In this work, we first
	propose an approach based on supervised learning to classify the
	pose of a mobile robot into semantic classes. Our method uses AdaBoost
	to boost simple features extracted from range data and vision into
	a strong classifier. We present two main applications of this approach.
	Firstly, we show how our approach can be utilized by a moving robot
	for an online classification of the poses traversed along its path
	using a hidden Markov model. Secondly, we introduce an approach to
	learn topological maps from geometric maps by applying our semantic
	classification procedure in combination with a probabilistic relaxation
	procedure. We finally show how to apply associative Markov networks
	(AMNs) together with AdaBoost for classifying complete geometric
	maps. Experimental results obtained in simulation and with real robots
	demonstrate the effectiveness of our approach in various indoor environments.},
  URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/mozos2006iros_w.pdf}
}

@INPROCEEDINGS{Mikolajczyk06c,
  AUTHOR = {K. Mikolajczyk and B. Leibe and B. Schiele},
  TITLE = {Multiple Object Class Detection with a Generative Model},
  BOOKTITLE = {Proceedings of the Conference on Computer Vision and Pattern Recognition,
	New York, USA},
  YEAR = {2006},
  PAGES = { },
  MONTH = {June},
  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.mis.informatik.tu-darmstadt.de/Publications/mikolajczyk-multiclass-cvpr06.pdf}
}

@INPROCEEDINGS{Pacchierotti06a,
  AUTHOR = {E. Pacchierotti and H.I. Christensen and P. Jensfelt},
  TITLE = {Design of an office guide robot for social interaction studies},
  BOOKTITLE = {Proc.~of the IEEE/RSJ International Conference on Intelligent Robots
	and Systems (IROS'06)},
  YEAR = {2006},
  URL = {http://www.cas.kth.se/~patric/publications/iros06_elena.pdf}
}

@INPROCEEDINGS{Pacchierotti06b,
  AUTHOR = {E. Pacchierotti and H.I. Christensen and P. Jensfelt},
  TITLE = {Evaluation of passing distance for social robots},
  BOOKTITLE = {IEEE Workshop on Robot and Human Interactive Communication {(ROMAN)}},
  YEAR = {2006},
  ADDRESS = {Hartfordshire, UK},
  MONTH = SEP,
  URL = {http://www.cas.kth.se/~patric/publications/roman06-elena.pdf}
}

@ARTICLE{Philipona06,
  AUTHOR = { David L Philipona and J Kevin O'Regan},
  TITLE = {Color naming, unique hues, and hue cancellation predicted from singularities
	in reflection properties.},
  JOURNAL = {Vis Neurosci},
  YEAR = {2006},
  VOLUME = {23},
  PAGES = {331-9},
  NUMBER = {3-4},
  ABSTRACT = {Psychophysical studies suggest that different colors have different
	perceptual status: red and blue for example are thought of as elementary
	sensations whereas yellowish green is not. The dominant account for
	such perceptual asymmetries attributes them to specificities of the
	neuronal representation of colors. Alternative accounts involve cultural
	or linguistic arguments. What these accounts have in common is the
	idea that there are no asymmetries in the physics of light and surfaces
	that could underlie the perceptual structure of colors, and this
	is why neuronal or cultural processes must be invoked as the essential
	underlying mechanisms that structure color perception. Here, we suggest
	a biological approach for surface reflection properties that takes
	into account only the information about light that is accessible
	to an organism given the photopigments it possesses, and we show
	that now asymmetries appear in the behavior of surfaces with respect
	to light. These asymmetries provide a classification of surface properties
	that turns out to be identical to the one observed in linguistic
	color categorization across numerous cultures, as pinned down by
	cross cultural studies. Further, we show that data from psychophysical
	studies about unique hues and hue cancellation are consistent with
	the viewpoint that stimuli reported by observers as special are those
	associated with this singularity-based categorization of surfaces
	under a standard illuminant. The approach predicts that unique blue
	and unique yellow should be aligned in chromatic space while unique
	red and unique green should not, a fact usually conjectured to result
	from nonlinearities in chromatic pathways.},
  URL = {http://nivea.psycho.univ-paris5.fr/PhiliponaVisNeurosci/PhiliponaVisNeurosci.pdf}
}

@INPROCEEDINGS{plagemann06euros,
  AUTHOR = {Plagemann, C. and Stachniss, C. and Burgard, W.},
  TITLE = {Efficient Failure Detection for Mobile Robots using Mixed-Abstraction
	Particle Filters},
  BOOKTITLE = {European Robotics Symposium 2006},
  YEAR = {2006},
  EDITOR = {H.I. Christiensen},
  VOLUME = {22},
  SERIES = {STAR Springer tracts in advanced robotics},
  PAGES = {93--107},
  PUBLISHER = {Springer-Verlag Berlin Heidelberg, Germany},
  ABSTRACT = {In this paper, we consider the problem of online failure detection
	and isolation for mobile robots. The goal is to enable a mobile robot
	to determine whether the system is running free of faults or to identify
	the cause for faulty behavior. In general, failures cannot be detected
	by solely monitoring the process model for the error free mode because
	if certain model assumptions are violated the observation likelihood
	might not indicate a defect. Existing approaches therefore use comparably
	complex system models to cover all possible system behaviors. In
	this paper, we propose the mixed-abstraction particle filter as an
	efficient way of dealing with potential failures of mobile robots.
	It uses a hierarchy of process models to actively validate the model
	assumptions and distribute the computational resources between the
	models adaptively. We present an implementation of our algorithm
	and discuss results obtained from simulated and real-robot experiments.},
  ISBN = {3-540-32688-X},
  PDFURL = {http://www.informatik.uni-freiburg.de/~plagem/bib/plagemann06euros.pdf}
}

@INPROCEEDINGS{pronobis06iros,
  AUTHOR = {Pronobis, A. and Caputo, B. and Jensfelt, P. and Christensen, H.
	I.},
  TITLE = {A Discriminative Approach to Robust Visual Place Recognition},
  BOOKTITLE = {Proceedings of the IEEE/RSJ International Conference on Intelligent
	Robots and Systems (IROS06)},
  YEAR = {2006},
  ADDRESS = {Beijing, China},
  MONTH = {October},
  URL = {http://www.csc.kth.se/~pronobis/research/pronobis06iros/pronobis06iros.pdf}
}

@INPROCEEDINGS{seemann06cvpr,
  AUTHOR = {E. Seemann and B. Leibe and B. Schiele},
  TITLE = {Multi-Aspect Detection of Articulated Objects},
  BOOKTITLE = {Proceedings of the Conference on Computer Vision and Pattern Recognition,
	New York, USA},
  YEAR = {2006},
  PAGES = { },
  MONTH = {June},
  ABSTRACT = {A wide range of methods have been proposed to detect and recognize
	objects. However, effective and efficient multiviewpoint detection
	of objects is still in its infancy, since most current approaches
	can only handle single viewpoints or aspects. This paper proposes
	a general approach for multi-aspect detection of objects. As the
	running example for detection we use pedestrians, which add another
	difficulty to the problem, namely human body articulations. Global
	appearance changes caused by different articulations and viewpoints
	of pedestrians are handled in a unified manner by a generalization
	of the Implicit Shape Model. An important property of this new approach
	is to share local appearance across different articulations and viewpoints,
	therefore requiring relatively few training samples. The effectiveness
	of the approach is shown and compared to previous approaches on two
	datasets containing pedestrians with different articulations and
	from multiple viewpoints.},
  URL = {http://www.mis.informatik.tu-darmstadt.de/seemann/seemann06cvpr.pdf}
}

@INPROCEEDINGS{Seemann06b,
  AUTHOR = {E. Seemann and B. Schiele},
  TITLE = {Cross-Articulation Learning for Robust Detection of Pedestrians},
  BOOKTITLE = {Proceedings of 28th Annual Symposium of the German Association for
	Pattern Recognition (DAGM), Berlin, Germany},
  YEAR = {2006},
  ADDRESS = {Berlin, Germany},
  MONTH = {September},
  ABSTRACT = {Recognizing categories of articulated ob jects in real-world scenarios
	is a challenging problem for today's vision algorithms. Due to the
	large appearance changes and intra-class variability of these objects,
	it is hard to define a model, which is both general and discriminative
	enough to capture the properties of the category. In this work, we
	propose an approach, which aims for a suitable trade-off for this
	problem. On the one hand, the approach is made more discriminant
	by explicitly distinguishing typical ob ject shapes. On the other
	hand, the method generalizes well and requires relatively few training
	samples by cross-articulation learning. The effectiveness of the
	approach is shown and compared to previous approaches on two datasets
	containing pedestrians with different articulations.},
  URL = {http://www.mis.informatik.tu-darmstadt.de/seemann/seemann06dagm.pdf}
}

@ARTICLE{dsPR06,
  AUTHOR = {D. Sko\v{c}aj and A. Leonardis and H. Bischof},
  TITLE = {Weighted and robust learning of subspace representations},
  JOURNAL = {Pattern recognition},
  YEAR = {2006},
  VOLUME = {40},
  PAGES = {1556-1569},
  NUMBER = {5},
  ABSTRACT = {A reliable system for visual learning and recognition should enable
	a selective treatment of individual parts of input data and should
	successfully deal with noise and occlusions. These requirements are
	not satisfactorily met when visual learning is approached by appearance-based
	modeling of objects and scenes using the traditional PCA approach.
	In this paper we extend standard PCA approach to overcome these shortcomings.
	We first present a weighted version of PCA, which, unlike the standard
	approach, considers individual pixels and images selectively, depending
	on the corresponding weights. Then we propose a robust PCA method
	for obtaining a consistent subspace representation in the presence
	of outlying pixels in the training images. The method is based on
	the EM algorithm for estimation of principal subspaces in the presence
	of missing data. We demonstrate the efficiency of the proposed methods
	in a number of experiments.},
  URL = {http://www.cognitivesystems.org/publications/uol_ds_pr06.pdf}
}

@INPROCEEDINGS{skocajCVWW06,
  AUTHOR = {D. Sko\v{c}aj and M. Uray and A. Leonardis and H. Bischof},
  TITLE = {Why to Combine Reconstructive and Discriminative Information for
	Incremental Subspace Learning},
  BOOKTITLE = {CVWW 2006 : proceedings of the 11th Computer Vision Winter Workshop},
  YEAR = {2006},
  PAGES = {52-57},
  ADDRESS = {Tel\v{c}, Czech Republic},
  MONTH = {February 6-8},
  ABSTRACT = {In the paper we propose a novel method for incremental visual learning
	by combining reconstructive and discriminative subspace methods.
	This is achieved by embedding LDA learning and classification into
	the incremental PCA framework. The combined subspace consists of
	a truncated PCA subspace and a few additional basis vectors that
	encompass the discriminative information, which would be lost by
	the discarded principal vectors. As such it contains both sufficient
	reconstructive information to enable incremental learning, and the
	previously extracted discriminative information to enable efficient
	classification as well. We demonstrate that we are able to efficiently
	update the current model with new instances of the already learned
	classes as well as to introduce new classes.},
  OWNER = {danijels vicos rpcv cosy mobvis DSSP3},
  TIMESTAMP = {2006.02.06},
  URL = {http://vicos.fri.uni-lj.si/data/publications/skocajCVWW06.pdf}
}

@INPROCEEDINGS{sloman2006pieces,
  AUTHOR = {Aaron Sloman},
  TITLE = {How to Put the Pieces of AI Together Again},
  BOOKTITLE = {Proceedings AAAI'06},
  YEAR = {2006},
  ADDRESS = {Boston},
  MONTH = {July},
  ABSTRACT = {Since the 1970s AI as a science has progressively fragmented into
	many activities that are very narrowly focused. It is not clear that
	work done within these fragments can be combined in the design of
	a human-like integrated system -- long held as one of the goals of
	AI as science. A strategy is proposed for reintegrating AI based
	around a backward-chaining analysis to produce a roadmap with partially
	ordered milestones, based on detailed scenarios, that everyone can
	agree are worth achieving, even when they disagree about means. This
	is a summary of ideas being developed within the CoSy project about
	how to plan long term research using a partially ordered network
	of scenarios and a grid of requirements for competences.},
  URL = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/aaai06-member.pdf}
}

@INPROCEEDINGS{slomanetal06cogrob,
  AUTHOR = {Aaron Sloman and Jeremy Wyatt and Nick Hawes and Jackie Chappell
	and Geert-Jan M. Kruijff},
  TITLE = {Long Term Requirements for Cognitive Robotics},
  BOOKTITLE = {Proceedings CogRob2006, The Fifth International Cognitive Robotics
	Workshop. The AAAI-06 Workshop on Cognitive Robotics},
  YEAR = {2006},
  ADDRESS = {Boston, Massachusetts, USA},
  MONTH = {July},
  ABSTRACT = {This paper discusses some of the long term objectives of cognitive
	robotics and some of the requirements for meeting those objectives
	that are still a very long way off. These include requirements for
	visual perception, for architectures, for kinds of learning, and
	for innate competences needed to drive learning and development in
	a variety of different environments. The work arises mainly out of
	research on requirements for forms of representation and architectures
	within the PlayMate scenario, which is a scenario concerned with
	a robot that perceives, interacts with and talks about 3-D objects
	on a tabletop, one of the scenarios in the EC-funded CoSy Robotics
	project.},
  URL = {http://www.cs.bham.ac.uk/~nah/bibtex/papers/slomanetal06cogrob.pdf}
}

@INPROCEEDINGS{stachniss2006icra,
  AUTHOR = {Stachniss, C. and Mart\'{i}nez Mozos, O. and Burgard, W.},
  TITLE = {Speeding-Up Multi-Robot Exploration by Considering Semantic Place
	Information},
  BOOKTITLE = {Proc.~of the IEEE Int.~Conf.~on Robotics \& Automation (ICRA)},
  YEAR = {2006},
  ADDRESS = {Orlando, FL, USA},
  ABSTRACT = {In this paper, we consider the problem of exploring an unknown environment
	with a team of mobile robots. One of the key issues in multi-robot
	exploration is how to assign target locations to the individual robots.
	To better distribute the robots over the environment and to avoid
	redundant work, we take into account the type of place a potential
	target is located in (e.g., a corridor or a room). To determine the
	type of a place, we apply a classifier learned with AdaBoost which
	additionally considers spatial dependencies between nearby locations.
	Our approach to incorporate the type of places in the coordination
	of the robots has been implemented and tested in different environments.
	The experiments demonstrate that our system effectively distributes
	the robots over the environment and allows them to accomplish their
	mission faster compared to approaches that ignore the semantic place
	labels.},
  URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/stachniss2006icra.pdf}
}


This file has been generated by bibtex2html 1.79

Print this page

 

Last modified: 31.8.2008 0:46:49