Search For:

Displaying 1-50 out of 56 total
Realtime Personal Positioning System for Wearable Computers
Found in: Wearable Computers, IEEE International Symposium
By Hisashi Aoki, Bernt Schiele, Alex Pentland
Issue Date:October 1999
pp. 37
Context awareness is an important functionality for wearable computers. In particular, the computer should know where the person is in the environment. This paper proposes an image sequence matching technique for the recognition of locations and previously...
 
Learning Audio-Visual Associations Using Mutual Information
Found in: Integration of Speech and Image Understanding, ICCV Workshop on
By Deb Roy, Bernt Schiele, Alex Pentland
Issue Date:September 1999
pp. 147
This paper addresses the problem of finding useful associations between audio and visual input signals. The proposed approach is based on the maximization of mutual information of audio-visual clusters. This approach results in segmentation of continuous s...
 
Visual Contextual Awareness in Wearable Computing
Found in: Wearable Computers, IEEE International Symposium
By Thad Starner, Bernt Schiele, Alex Pentland
Issue Date:October 1998
pp. 50
Small, body-mounted video cameras enable a different style of wearable computing interface. As processing power increases, a wearable computer can spend more time observing its user to provide serendipitous information, manage interruptions and tasks, and ...
 
Learning People Detectors for Tracking in Crowded Scenes
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Siyu Tang,Mykhaylo Andriluka,Anton Milan,Konrad Schindler,Stefan Roth,Bernt Schiele
Issue Date:December 2013
pp. 1049-1056
People tracking in crowded real-world scenes is challenging due to frequent and long-term occlusions. Recent tracking methods obtain the image evidence from object (people) detectors, but typically use off-the-shelf detectors and treat them as black box co...
 
Translating Video Content to Natural Language Descriptions
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Marcus Rohrbach,Wei Qiu,Ivan Titov,Stefan Thater,Manfred Pinkal,Bernt Schiele
Issue Date:December 2013
pp. 433-440
Humans use rich natural language to describe and communicate visual perceptions. In order to provide natural language descriptions for visual content, this paper combines two important ingredients. First, we generate a rich semantic representation of the v...
 
Strong Appearance and Expressive Spatial Models for Human Pose Estimation
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Leonid Pishchulin,Mykhaylo Andriluka,Peter Gehler,Bernt Schiele
Issue Date:December 2013
pp. 3487-3494
Typical approaches to articulated pose estimation combine spatial modelling of the human body with appearance modelling of body parts. This paper aims to push the state-of-the-art in articulated pose estimation in two ways. First we explore various types o...
 
A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Fabio Galasso,Naveen Shankar Nagaraja,Tatiana Jimenez Cardenas,Thomas Brox,Bernt Schiele
Issue Date:December 2013
pp. 3527-3534
Video segmentation research is currently limited by the lack of a benchmark dataset that covers the large variety of sub problems appearing in video segmentation and that is large enough to avoid over fitting. Consequently, there is little analysis of vide...
 
South by South-East or Sitting at the Desk: Can Orientation be a Place?
Found in: Wearable Computers, IEEE International Symposium
By Ulf Blanke, Robert Rehner, Bernt Schiele
Issue Date:June 2011
pp. 43-46
Location is a key information for context-aware systems. While coarse-grained indoor location estimates may be obtained quite easily (e.g. based on WiFi or GSM), finer-grained estimates typically require additional infrastructure (e.g. ultrasound). This wo...
 
Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Maja Stikic,Diane Larlus,Sandra Ebert,Bernt Schiele
Issue Date:December 2011
pp. 2521-2537
This paper considers scalable and unobtrusive activity recognition using on-body sensing for context awareness in wearable computing. Common methods for activity recognition rely on supervised learning requiring substantial amounts of labeled training data...
 
Monocular 3D pose estimation and tracking by detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mykhaylo Andriluka, Stefan Roth, Bernt Schiele
Issue Date:June 2010
pp. 623-630
Automatic recovery of 3D human pose from monocular image sequences is a challenging and important research topic with numerous applications. Although current methods are able to recover 3D pose for a single person in controlled environments, they are sever...
 
New features and insights for pedestrian detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stefan Walk, Nikodem Majer, Konrad Schindler, Bernt Schiele
Issue Date:June 2010
pp. 1030-1037
Despite impressive progress in people detection the performance on challenging datasets like Caltech Pedestrians or TUD-Brussels is still unsatisfactory. In this work we show that motion features derived from optic flow yield substantial improvements on im...
 
What helps where – and why? Semantic relatedness for knowledge transfer
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Marcus Rohrbach, Michael Stark, Gyorgy Szarvas, Iryna Gurevych, Bernt Schiele
Issue Date:June 2010
pp. 910-917
Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today's recognition methods. Several authors have promoted knowledge transfer between classes as...
 
Multi-cue pedestrian classification with partial occlusion handling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Markus Enzweiler, Angela Eigenstetter, Bernt Schiele, Dariu M. Gavrila
Issue Date:June 2010
pp. 990-997
This paper presents a novel mixture-of-experts framework for pedestrian classification with partial occlusion handling. The framework involves a set of component-based expert classifiers trained on features derived from intensity, depth and motion. To hand...
 
Automatic discovery of meaningful object parts with latent CRFs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Paul Schnitzspan, Stefan Roth, Bernt Schiele
Issue Date:June 2010
pp. 121-128
Object recognition is challenging due to high intra-class variability caused, e.g., by articulation, viewpoint changes, and partial occlusion. Successful methods need to strike a balance between being flexible enough to model such variation and discriminat...
 
Enabling Efficient Time Series Analysis for Wearable Activity Data
Found in: Machine Learning and Applications, Fourth International Conference on
By Kristof Van Laerhoven, Eugen Berlin, Bernt Schiele
Issue Date:December 2009
pp. 392-397
Long-term activity recognition relies on wearable sensors that log the physical actions of the wearer, so that these can be analyzed afterwards. Recent progress in this field has made it feasible to log high-resolution inertial data, resulting in increasin...
 
An Exploration of Daily Routine Modeling Based on Bluetooth and GSM-Data
Found in: Wearable Computers, IEEE International Symposium
By Ulrich Steinhoff, Bernt Schiele
Issue Date:September 2009
pp. 141-142
We explore GSM & Bluetooth (BT) data to capture daily routines and social environments. With focus on the individual, non-networked user, showing the complementarity of these modalities. We present a realistic real-life dataset over 22 weeks and analyz...
 
An Analysis of Sensor-Oriented vs. Model-Based Activity Recognition
Found in: Wearable Computers, IEEE International Symposium
By Andreas Zinnen, Ulf Blanke, Bernt Schiele
Issue Date:September 2009
pp. 93-100
Model-based activity recognition has been recently proposed as an alternative to signal-oriented recognition. Such model-based approaches seem attractive due to their ability to enable user-independent activity recognition and due to their improved robustn...
 
Multi-graph Based Semi-supervised Learning for Activity Recognition
Found in: Wearable Computers, IEEE International Symposium
By Maja Stikic, Diane Larlus, Bernt Schiele
Issue Date:September 2009
pp. 85-92
On-body sensing has enabled scalable and unobtrusive activity recognition for context-aware wearable computing. Common methods for activity recognition are based on supervised learning requiring substantial amounts of labeled training data. Obtaining accur...
 
Sustained logging and discrimination of sleep postures with low-level, wrist-worn sensors
Found in: Wearable Computers, IEEE International Symposium
By Kristof Van Laerhoven, Marko Borazio, David Kilian, Bernt Schiele
Issue Date:October 2008
pp. 69-76
We present a study which evaluates the use of simple low-power sensors for a long-term, coarse-grained detection of sleep postures. In contrast to the information-rich but complex recording methods used in sleep studies, we follow a paradigm closer to that...
 
Exploring semi-supervised and active learning for activity recognition
Found in: Wearable Computers, IEEE International Symposium
By Maja Stikic, Kristof Van Laerhoven, Bernt Schiele
Issue Date:October 2008
pp. 81-88
In recent years research on human activity recognition using wearable sensors has enabled to achieve impressive results on real-world data. However, the most successful activity recognition algorithms require substantial amounts of labeled training data. T...
 
Using rhythm awareness in long-term activity recognition
Found in: Wearable Computers, IEEE International Symposium
By Kristof Van Laerhoven, David Kilian, Bernt Schiele
Issue Date:October 2008
pp. 63-66
This paper reports on research where users' activities are logged for extended periods by wrist-worn sensors. These devices operated for up to 27 consecutive days, day and night, while logging features from motion, light, and temperature. This data, labele...
 
A new approach to enable gesture recognition in continuous data streams
Found in: Wearable Computers, IEEE International Symposium
By Andreas Zinnen, Bernt Schiele
Issue Date:October 2008
pp. 33-40
Gesture recognition has great potential for mobile and wearable computing. Most papers in this area focus on classifying different gestures, but do not evaluate the distinctiveness of gestures in continuous recordings of gestures in daily life. This paper ...
 
Decomposition, discovery and detection of visual categories using topic models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mario Fritz, Bernt Schiele
Issue Date:June 2008
pp. 1-8
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 ...
 
People-tracking-by-detection and people-detection-by-tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mykhaylo Andriluka, Stefan Roth, Bernt Schiele
Issue Date:June 2008
pp. 1-8
Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multiple people, complicated occlusions, and cluttered or even moving backgrounds. People detectors have been shown to be able to loc...
 
2007’s Wearable Computing Advances
Found in: IEEE Pervasive Computing
By Bernt Schiele
Issue Date:January 2008
pp. 82-84
The International Symposium on Wearable Computers (ISWC) is the premier conference in wearable computing, reporting the latest advances in research and technology. This year’s program emphasized gesture and activity recognition but also reported on power c...
 
Browsing patient records during ward rounds with a body worn gyroscope
Found in: Wearable Computers, IEEE International Symposium
By Andreas Zinnen, Bernt Schiele, Thomas Ziegert
Issue Date:October 2007
pp. 1-2
In this paper, we address the problem of contact free access and browsing of patient documents in the health care area. The documents are displayed on a bedside display. Gestures are used to navigate through the documents. A face detection system recognize...
 
How Good are Local Features for Classes of Geometric Objects
Found in: Computer Vision, IEEE International Conference on
By Michael Stark, Bernt Schiele
Issue Date:October 2007
pp. 1-8
Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. Such descriptors explicitly code local appearance and have shown impressive results on objects with sufficient local appearance stat...
 
Visual Object Class Recognition combining Generative and Discriminative Methods
Found in: Hybrid Intelligent Systems, International Conference on
By Bernt Schiele
Issue Date:September 2007
pp. 5
We describe various approaches capable of simultaneous recognition and localization of multiple object classes using a combination of generative and discriminative methods. A first approach uses a novel hierarchical representation allows to represent indiv...
   
Towards Robust Pedestrian Detection in Crowded Image Sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Edgar Seemann, Mario Fritz, Bernt Schiele
Issue Date:June 2007
pp. 1-8
Object class detection in scenes of realistic complexity remains a challenging task in computer vision. Most recent approaches focus on a single and general model for object class detection. However, in particular in the context of image sequences, it may ...
 
Towards Less Supervision in Activity Recognition from Wearable Sensors
Found in: Wearable Computers, IEEE International Symposium
By Tam Huynh, Bernt Schiele
Issue Date:October 2006
pp. 3-10
Activity Recognition has gained a lot of interest in recent years due to its potential and usefulness for context-aware wearable computing. However, most approaches for activity recognition rely on supervised learning techniques limiting their applicabilit...
 
Multiple Object Class Detection with a Generative Model
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Krystian Mikolajczyk, Bastian Leibe, Bernt Schiele
Issue Date:June 2006
pp. 26-36
In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation allows to represent individual images as well as various objects classes in a...
 
Towards Multi-View Object Class Detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Alexander Thomas, Vittorio Ferrar, Bastian Leibe, Tinne Tuytelaars, Bernt Schiel, Luc Van Gool
Issue Date:June 2006
pp. 1589-1596
We present a novel system for generic object class detection. In contrast to most existing systems which focus on a single viewpoint or aspect, our approach can detect object instances from arbitrary viewpoints. This is achieved by combining the Implicit S...
 
Multi-Aspect Detection of Articulated Objects
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Edgar Seemann, Bastian Leibe, Bernt Schiele
Issue Date:June 2006
pp. 1582-1588
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...
 
Local Features for Object Class Recognition
Found in: Computer Vision, IEEE International Conference on
By Krystian Mikolajczyk, Bastian Leibe, Bernt Schiele
Issue Date:October 2005
pp. 1792-1799
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 [20]. H...
 
Integrating Representative and Discriminative Models for Object Category Detection
Found in: Computer Vision, IEEE International Conference on
By Mario Fritz, Bastian Leibe, Barbara Caputo, Bernt Schiele
Issue Date:October 2005
pp. 1363-1370
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 prese...
 
Sensing and Monitoring Professional Skiers
Found in: IEEE Pervasive Computing
By Florian Michahelles, Bernt Schiele
Issue Date:July 2005
pp. 40-46
Wearable sensors can enhance the relationship between professional downhill skiers and their trainers by revealing information about the athlete's motions--such as force, rotation, or acceleration--that are difficult or impossible for the trainer to observ...
 
Pedestrian Detection in Crowded Scenes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bastian Leibe, Edgar Seemann, Bernt Schiele
Issue Date:June 2005
pp. 878-885
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 int...
 
Towards Distributed Awareness — An Artifact Based Approach
Found in: Mobile Computing Systems and Applications, IEEE Workshop on
By Florian Michahelles, Albrecht Schmidt, Bernt Schiele, Michael Beigl
Issue Date:December 2004
pp. 82-91
Perception is a central issue for many applications in ubiquitous computing. However, in current implementations, sensing and distributed perception is re-invented over and over again. Identifying commonalities and synthesizing a common model would be more...
 
Less Contact: Heart-Rate Detection Without Even Touching the User
Found in: Wearable Computers, IEEE International Symposium
By Florian Michahelles, Ramon Wicki, Bernt Schiele
Issue Date:November 2004
pp. 4-7
Heart-rate sensing is very important. Whereas there are different methods and commercial products available, they all have a common drawback: the user has to mount some piece of sensor to his body. This paper provides a case study on how micro-impulse rada...
 
A Model for Human Interruptability: Experimental Evaluation and Automatic Estimation from Wearable Sensors
Found in: Wearable Computers, IEEE International Symposium
By Nicky Kern, Stavros Antifakos, Bernt Schiele, Adrian Schwaninger
Issue Date:November 2004
pp. 158-165
For the estimation of user interruptability in wearable and mobile settings, we propose in [Context-aware notfication for wearable computing] to distinguish between the users' personal and social interruptability. In this paper, we verify this thesis with ...
 
Workshop on Generic Object Recognition and Categorization
Found in: Computer Vision and Pattern Recognition Workshop
By Sven Dickinson, Ales Leonardis, Bernt Schiele
Issue Date:July 2004
pp. 26
We discuss the issues and challenges of generic object recognition. We argue that high-level, volumetric part-based descriptions are essential in the process of recognizing objects that might never have been observed before, and for which no exact geometri...
 
Context-Aware Notification for Wearable Computing
Found in: Wearable Computers, IEEE International Symposium
By Nicky Kern, Bernt Schiele
Issue Date:October 2003
pp. 223
In this paper we propose to use context information obtained from body-worn sensors to mediate notifications for a wearable computer. In particular we introduce a model which uses two axes, namely personal and social interruptability of the user in order t...
 
Analyzing Appearance and Contour Based Methods for Object Categorization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bastian Leibe, Bernt Schiele
Issue Date:June 2003
pp. 409
Object recognition has reached a level where we can identify a large number of previously seen and known objects. However, the more challenging and important task of categorizing previously unseen objects remains largely unsolved. Traditionally, contour an...
 
The Light Field Oracle
Found in: Computer Graphics and Applications, Pacific Conference on
By Reto Lütolf, Bernt Schiele, Markus H. Gross
Issue Date:October 2002
pp. 116
We present the light field oracle, a novel mathematical concept for the acquisition, processing and representation of light fields. We first compute a hierarchical representation from a set of sparse image samples using a combination of wavelet transform a...
 
Analyzing Non-Negative Matrix Factorization for Image Classification
Found in: Pattern Recognition, International Conference on
By David Guillamet, Bernt Schiele, Jordi Vitrià
Issue Date:August 2002
pp. 20116
The Non-negative Matrix Factorization technique (NMF) has been recently proposed for dimensionality reduction. NMF is capable to produce a region- or part-based representation of objects and images. This paper experimentally compares NMF to Principal Compo...
 
How Many Classifiers Do I Need?
Found in: Pattern Recognition, International Conference on
By Bernt Schiele
Issue Date:August 2002
pp. 20176
Combining multiple classifiers promises to increase performance and robustness of a classification task. Currently however, the understanding which combination scheme should be used and the ability to quantify the expected benefit is inadequate. This paper...
 
3D Object Recognition from Range Images using Local Feature Histograms
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Günter Hetzel, Bastian Leibe, Paul Levi, Bernt Schiele
Issue Date:December 2001
pp. 394
This paper explores a view-based approach to recognize free-form objects in range images. We are using a set of local features that are easy to calculate and robust to partial occlusions. By combining those features in a multidimensional histogram, we can ...
 
Probabilistic Object Recognition and Localization
Found in: Computer Vision, IEEE International Conference on
By Bernt Schiele, Alex Pentland
Issue Date:September 1999
pp. 177
Objects can be represented by regions of local structure as well as dependencies between these regions. The appearance of local structure can be characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor f...
 
Keynote lecture 1: "Visual scene understanding — It's time to address it again"
Found in: 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Bernt Schiele
Issue Date:August 2013
pp. XVI
Inspired by the ability of humans to interpret and understand 3D scenes nearly effortlessly, the problem of 3D scene understanding has long been advocated as the "holy grail" of computer vision. In the early days this problem was addressed in a b...
   
Occlusion Patterns for Object Class Detection
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Bojan Pepikj,Michael Stark,Peter Gehler,Bernt Schiele
Issue Date:June 2013
pp. 3286-3293
Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion remains a major challenge, and a principled solution is yet to be found. In this paper we leave the beaten path of methods that treat occlusion a...
 
 1  2 Next >>