Bernt Schiele
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bernt Schiele has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Tam Huynh
Computer Science Department, TU Darmstadt, Germany
2 shared publications - Albrecht Schmidt
LMU Munich
1 shared publication - Andreas Zinnen
Computer Science Department, TU Darmstadt, Germany
1 shared publication - Edgar Seemann
TU Darmstadt, Germany
1 shared publication - Julia Vogel
University of British Columbia
1 shared publication - Kristof Van Laerhoven1 shared publication
Latest Publications
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 107-108
Browsing patient records during ward rounds with a body worn gyroscope
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 recognizes attention of the doctor towards the screen and activates and deactivates the gesture interface automatically. The activation enables the system to distinguish day-to-day from navigation gestures.
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 107-108
Browsing patient records during ward rounds with a body worn gyroscope
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 recognizes attention of the doctor towards the screen and activates and deactivates the gesture interface automatically. The activation enables the system to distinguish day-to-day from navigation gestures.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Towards Robust Pedestrian Detection in Crowded Image Sequences
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 be advantageous to adapt the general model to a more object-instance specific model in order to detect this particular object reliably within the image sequence. In this work we present a generative object model that is capable to scale from a general object class model to a more specific object-instance model. This allows to detect class instances as well as to distinguish between individual object instances reliably. We experimentally evaluate the performance of the proposed system on both still images and image sequences.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Towards Robust Pedestrian Detection in Crowded Image Sequences
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 be advantageous to adapt the general model to a more object-instance specific model in order to detect this particular object reliably within the image sequence. In this work we present a generative object model that is capable to scale from a general object class model to a more specific object-instance model. This allows to detect class instances as well as to distinguish between individual object instances reliably. We experimentally evaluate the performance of the proposed system on both still images and image sequences.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
How Good are Local Features for Classes of Geometric Objects
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 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 appearance-based descriptors such as SIFT. The analysis includes a direct comparison of feature statistics as well as results within standard recognition frameworks, which are partly intuitive, but sometimes surprising.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
How Good are Local Features for Classes of Geometric Objects
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 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 appearance-based descriptors such as SIFT. The analysis includes a direct comparison of feature statistics as well as results within standard recognition frameworks, which are partly intuitive, but sometimes surprising.
- 1 October 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15504816,p. 3-10
Towards Less Supervision in Activity Recognition from Wearable Sensors
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 lim iting their applicability in real-world scenarios and their scalability to large amounts of activities and training data. State-of-the-art activity recognition algorithms can roughly be divided in two groups concerning the choice of the classifier, one group using generative models and the other discriminative approaches. This paper presents a method for activity recognition which combines a generative model with a discriminative classifier in an integrated approach. The generative part of the algorithm allows to extract and learn structure in activity data without any labeling or supervision. The discriminant part then uses a small but labeled subset of the training data to train a discriminant classifier. In experiments we show that this scheme enables to attain high recognition rates even though only a subset of the training data is used for training. Also the tradeoff between labeling effort and recognition performance is analyzed and discussed.
- 1 October 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15504816,p. 3-10
Towards Less Supervision in Activity Recognition from Wearable Sensors
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 lim iting their applicability in real-world scenarios and their scalability to large amounts of activities and training data. State-of-the-art activity recognition algorithms can roughly be divided in two groups concerning the choice of the classifier, one group using generative models and the other discriminative approaches. This paper presents a method for activity recognition which combines a generative model with a discriminative classifier in an integrated approach. The generative part of the algorithm allows to extract and learn structure in activity data without any labeling or supervision. The discriminant part then uses a small but labeled subset of the training data to train a discriminant classifier. In experiments we show that this scheme enables to attain high recognition rates even though only a subset of the training data is used for training. Also the tradeoff between labeling effort and recognition performance is analyzed and discussed.
- 16 August 2006
- Published by Springer Nature in Personal and Ubiquitous Computing
- Vol. 11 (4) , 251-263
Recognizing context for annotating a live life recording
- 16 August 2006
- Published by Springer Nature in Personal and Ubiquitous Computing
- Vol. 11 (4) , 251-263
Recognizing context for annotating a live life recording
- 23 July 2006
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 72 (2) , 133-157
Semantic Modeling of Natural Scenes for Content-Based Image Retrieval
- 23 July 2006
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 72 (2) , 133-157
Semantic Modeling of Natural Scenes for Content-Based Image Retrieval