Ludger van Elst
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ludger van Elst has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Dengel
German Research Center for Artificial Intelligence (DFKI)
3 shared publications Franz Schmalhofer
University of Osnabrueck
3 shared publicationsGeorg Buscher
German Research Center for Artificial Intelligence (DFKI), WA
3 shared publicationsMalte Kiesel
German Research Center for Artificial Intelligence (DFKI) GmbH
3 shared publications- Abdul Hannan Khan
Department of Computer Science German Research Center for Artificial Intelligence (DFKI GmbH) RPTU Kaiserslautern-Landau 2 67663 Kaiserslautern Germany
2 shared publications - Andreas Abecker
Disy Informationssysteme GmbH
2 shared publications
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 419-433
Object Risk Estimation for Autonomous Driving Safety
- 2 January 2026
- Published by Springer Nature
- p. 419-433
Object Risk Estimation for Autonomous Driving Safety
- 24 June 2025
- Published by Springer Nature
- p. 306-321
CCATS: Moving Forward with Class-Conditional Time Series Generation
- 24 June 2025
- Published by Springer Nature
- p. 306-321
CCATS: Moving Forward with Class-Conditional Time Series Generation
- Open Access
F2DNet: Fast Focal Detection Network for Pedestrian Detection
Two-stage detectors are state-of-the-art in object detection as well as pedestrian detection. However, the current two-stage detectors are inefficient as they do bounding box regression in multiple steps i.e. in region proposal networks and bounding box heads. Also, the anchor-based region proposal networks are computationally expensive to train. We propose F2DNet, a novel two-stage detection architecture which eliminates redundancy of current two-stage detectors by replacing the region proposal network with our focal detection network and bounding box head with our fast suppression head. We benchmark F2DNet on top pedestrian detection datasets, thoroughly compare it against the existing state-of-the-art detectors and conduct cross dataset evaluation to test the generalizability of our model to unseen data. Our F2DNet achieves 8.7\%, 2.2\%, and 6.1\% MR-2 on City Persons, Caltech Pedestrian, and Euro City Person datasets respectively when trained on a single dataset and reaches 20.4\% and 26.2\% MR-2 in heavy occlusion setting of Caltech Pedestrian and City Persons datasets when using progressive fine-tunning. Furthermore, F2DNet have significantly lesser inference time compared to the current state-of-the-art. Code and trained models will be available at https://github.com/AbdulHannanKhan/F2DNet.
Open AccessF2DNet: Fast Focal Detection Network for Pedestrian Detection
Two-stage detectors are state-of-the-art in object detection as well as pedestrian detection. However, the current two-stage detectors are inefficient as they do bounding box regression in multiple steps i.e. in region proposal networks and bounding box heads. Also, the anchor-based region proposal networks are computationally expensive to train. We propose F2DNet, a novel two-stage detection architecture which eliminates redundancy of current two-stage detectors by replacing the region proposal network with our focal detection network and bounding box head with our fast suppression head. We benchmark F2DNet on top pedestrian detection datasets, thoroughly compare it against the existing state-of-the-art detectors and conduct cross dataset evaluation to test the generalizability of our model to unseen data. Our F2DNet achieves 8.7\%, 2.2\%, and 6.1\% MR-2 on City Persons, Caltech Pedestrian, and Euro City Person datasets respectively when trained on a single dataset and reaches 20.4\% and 26.2\% MR-2 in heavy occlusion setting of Caltech Pedestrian and City Persons datasets when using progressive fine-tunning. Furthermore, F2DNet have significantly lesser inference time compared to the current state-of-the-art. Code and trained models will be available at https://github.com/AbdulHannanKhan/F2DNet.
- Open Access
- 13 January 2012
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 1 (2) , 1-30
Attentive documents
Reading is one of the most frequent activities of knowledge workers. Eye tracking can provide information on what document parts users read, and how they were read. This article aims at generating implicit relevance feedback from eye movements that can be used for information retrieval personalization and further applications. We report the findings from two studies which examine the relation between several eye movement measures and user-perceived relevance of read text passages. The results show that the measures are generally noisy, but after personalizing them we find clear relations between the measures and relevance. In addition, the second study demonstrates the effect of using reading behavior as implicit relevance feedback for personalizing search. The results indicate that gaze-based feedback is very useful and can greatly improve the quality of Web search. The article concludes with an outlook introducing attentive documents keeping track of how users consume them. Based on eye movement feedback, we describe a number of possible applications to make working with documents more effective.
- 13 January 2012
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 1 (2) , 1-30
Open AccessAttentive documents
Reading is one of the most frequent activities of knowledge workers. Eye tracking can provide information on what document parts users read, and how they were read. This article aims at generating implicit relevance feedback from eye movements that can be used for information retrieval personalization and further applications. We report the findings from two studies which examine the relation between several eye movement measures and user-perceived relevance of read text passages. The results show that the measures are generally noisy, but after personalizing them we find clear relations between the measures and relevance. In addition, the second study demonstrates the effect of using reading behavior as implicit relevance feedback for personalizing search. The results indicate that gaze-based feedback is very useful and can greatly improve the quality of Web search. The article concludes with an outlook introducing attentive documents keeping track of how users consume them. Based on eye movement feedback, we describe a number of possible applications to make working with documents more effective.
- 18 January 2011
- Published by IGI Global Scientific Publishing
- p. 2280-2304
The Social Semantic Desktop
- 1 January 2008
- Published by Springer Nature
- p. 172-187
Contextualized Knowledge Acquisition in a Personal Semantic Wiki
- 1 January 2008
- Published by Springer Nature
- p. 172-187
Contextualized Knowledge Acquisition in a Personal Semantic Wiki
- 1 January 2008
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 817-821
Mymory: Enhancing a Semantic Wiki with Context Annotations
- 1 January 2008
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 817-821
Mymory: Enhancing a Semantic Wiki with Context Annotations
- 1 January 2007
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 594-608
Distributed Knowledge Representation on the Social Semantic Desktop: Named Graphs, Views and Roles in NRL
- 1 January 2007
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 594-608
Distributed Knowledge Representation on the Social Semantic Desktop: Named Graphs, Views and Roles in NRL
- 24 January 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 340-345
Weakly-structured workflows for knowledge-intensive tasks: an experimental evaluation
- 24 January 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 340-345
Weakly-structured workflows for knowledge-intensive tasks: an experimental evaluation