Gerd Herzog
	DFKI GmbH
	German Research Center for Artificial Intelligence
	Email Address:	herzog@dfki.de
	Permanent Contact:	herzog@acm.org

Since 1996, Gerd Herzog is affiliated to the Intelligent User Interfaces Laboratory at the German Research Center for Artificial Intelligence (DFKI GmbH) in Saarbrücken and Kaiserslautern. He holds the position of a Chief Software Engineer and has been involved in various European and national research activities as well as industrial projects with a main focus on intelligent multimedia systems.

Before joining DFKI, he was a project manager at the Computer Science Department of Saarland University (Universität des Saarlandes), where he had been engaged in the VITRA (Visual Translator) project of the SFB 314, Special Collaborative Program on Artificial Intelligence and Knowledge-based Systems, funded by German Science Foundation (DFG). Before starting as a full-time researcher in 1988, he had already gained 3 years experience as a research assistant during the first funding period of the VITRA project.

From 1990 to 1991, he had also been working as a free lance for HQ Interaktive Mediensysteme, Weil am Rhein. The task consisted in the conception and realization of a multi-functional, PC-based teleconference system. The results have been documented in a conference paper (in German).

Selected Projects

		Theseus: Research program for a new Internet-based knowledge infrastructure.
		Smartweb: Mobile broadband access to the Semantic Web.
		Specter: Context- and affect-aware personal assistance in instrumented environments.
		VirtualHuman: Anthropomorphic Interaction Agents.
		SmartKom: Dialog-based human-technology interaction by coordinated analysis and generation of multiple modalities.
		Comic – Conversational Multimodal Interaction with Computers: Advanced multimodal interaction for the realization of novel eCommerce and eWork services.
		MLounge – Magic Lounge: A virtual meeting space with intelligent communication services.
		Rocco – RoboCup Commentator: Automated generation of multimedia reports for time-varying scenes on the basis of visual data. The prototype system generates TV-style live reports for matches of the RoboCup simulator league.
		Fluids – Future Lines of User Interface Decision Support: A framework for building intelligent interfaces for real-time decision support systems.
		Lidos – Literature Information and Documentation System: An online bibliography covering 25 years of Artificial Intelligence research until 1996.
		Vitra – Visual Translator: Integration of computer vision and natural language processing.

Computer Societies Membership

AAAI –

the Association for the Advancement of Artificial Intelligence;

ACM –

the Association for Computing Machinery, Special Interest Groups for Artificial Intelligence (SIGART) and for Multimedia (SIGMM);

GI –

Gesellschaft für Informatik, the German Computer Society, Fachbereich 1 Künstliche Intelligenz, the Artificial Intelligence section;

IEEE CS –

the Computer Society of the Institute of Electrical and Electronics Engineers.

Publications

• N. Reithinger, G. Herzog, and A. Blocher. SmartWeb: Mobile Broadband Access to the Semantic Web. In: KI – Künstliche Intelligenz, 07(2):30-33, 2007.
• D. Sonntag, R. Engel, G. Herzog, A. Pfalzgraf, N. Pfleger, M. Romanelli, and N. Reithinger. SmartWeb Handheld — Multimodal Interaction with Ontological Knowledge Bases and Semantic Web Services In: T.S. Huang, A. Nijholt, M. Pantic, A. Pentland (eds.), Artifical Intelligence for Human Computing: ICMI 2006 and IJCAI 2007 International Workshops, pp. 272-295. Berlin, Heidelberg: Springer, 2007.
• N. Reithinger and G. Herzog. An Exemplary Interaction with SmartKom. In: W. Wahlster (ed.), SmartKom: Foundations of Multimodal Dialogue Systems, pp. 41-52. Berlin, Heidelberg: Springer, 2006.
• G. Herzog and N. Reithinger. The SmartKom Architecture: A Framework for Multimodal Dialogue Systems. In: W. Wahlster (ed.), SmartKom: Foundations of Multimodal Dialogue Systems, pp. 55-70. Berlin, Heidelberg: Springer, 2006.
• G. Herzog and A. Ndiaye. Building Multimodal Dialogue Applications: System Integration in SmartKom. In: W. Wahlster (ed.), SmartKom: Foundations of Multimodal Dialogue Systems, pp. 439-452. Berlin, Heidelberg: Springer, 2006.
• N. Reithinger, S. Bergweiler, R. Engel, G. Herzog, N. Pfleger, M. Romanelli, and D. Sonntag. A Look under the Hood: Design and Development of the First SmartWeb System Demonstrator. In: Proceedings of the 7th International Conference on Multimodal interfaces (ICMI'05), Trento, Italy, pp. 159-166. New York: ACM Press, 2005.
• G. Herzog, A. Ndiaye, S. Merten, H. Kirchmann, T. Becker, and P. Poller. Large-scale Software Integration for Spoken Language and Multimodal Dialog Systems. In: Natural Language Engineering, 10(3/4):283-305, 2004.
• N. Reithinger, G. Herzog, and A. Ndiaye. Situated Multimodal Interaction in SmartKom. In: Computers & Graphics, 27(6):899-903, 2003.
• G. Herzog, H. Kirchmann, S. Merten, A. Ndiaye, and P. Poller. MULTIPLATFORM Testbed: An Integration Platform for Multimodal Dialog Systems. In: H. Cunningham and J. Patrick (eds.) Proceedings of the HLT-NAACL 2003 Workshop on Software Engineering and Architecture of Language Technology Systems (SEALTS), pp. 75-82, Edmonton, Canada, 2003.
• T. Rist, P. Brandmeier, G. Herzog, and E. André. Getting the Mobile Users in: Three Systems that Support Collaboration in an Environment with Heterogeneous Communication Devices. In: V. Di Gesù, S. Levialdi, L. Tarantino (eds.): Advanced Visual Interfaces (AVI'2000), pp. 250-254, New York: ACM Press, 2000.
• E. André, K. Binsted, K. Tanaka-Ishii, S. Luke, G. Herzog, and T. Rist. Three RoboCup Simulation League Commentator Systems. In: AI Magazine, 21(1):57-66, 2000.
• E. André, T. Rist und G. Herzog. Neue ,Neue Medien´? Von Multimedia zu Intellimedia-Präsentationssystemen. In: G. G. Voß, W. Holly und K. Boehneke (Hrsg.), Neue Medien im Alltag: Begriffsbestimmungen eines interdisziplinären Forschungsfeldes, pp. 221-233. Opladen: Leske + Budrich, 2000.
• D. Voelz, E. André, G. Herzog, and T. Rist. Rocco: A RoboCup Soccer Commentator System. In: M. Asada and H. Kitano (eds.), RoboCup-98: Robot Soccer World Cup II, pp. 50-60. Berlin, Heidelberg: Springer, 1999. This paper received a Scientific Challenge Award.
• T. Rist, G. Herzog, E. André, and S. Baldes. Aggregation of Alternatives in the Multimedia Presentation of Decision Support Information for Real-Time Control. In: L. Pineda, T. Rist, and J. Lee (eds.), 4th World Congress on Expert Systems, Workshop on Interpretation and Generation in Intelligent Multimodal Systems and Graphical Reasoning in Expert Systems, pp. 54-66, Mexico City, 1998.
• G. Herzog, E. André, S. Baldes und T. Rist. Zur multimedialen Präsentation von Handlungsalternativen in Verkehrsmanagement- und Verkehrssimulationssystemen. In: P. Lorenz und B. Preim (Hrsg.), Simulation und Visualisierung '98, pp. 235-248. Delft: SCS, 1998.
• G. Herzog, E. André, S. Baldes und T. Rist. Combining Alternatives in the Multimedia Presentation of Decision Support Information for Real-Time Control. In: A. Sutcliffe, J. Ziegler, and P. Johnson (eds.), Designing Effective and Usable Multimedia Systems, pp. 143-157. Boston: Kluwer, 1998.
• E. André, G. Herzog, and T. Rist. Generating Multimedia Presentations for RoboCup Soccer Games. In: H. Kitano (ed.), RoboCup-97: Robot Soccer World Cup I, pp. 200-215. Berlin Heidelberg: Springer, 1998.
• T. Längle, T. C. Lüth, E. Stopp, and G. Herzog. Natural Language Access to Intelligent Robots: Explaining Automatic Error Recovery. In: A. M. Ramsay (ed.), Artificial Intelligence: Methodology, Systems, Applications, pp. 259-267. Amsterdam: IOS, 1996.
• G. Herzog, A. Blocher, K.-P. Gapp, E. Stopp und W. Wahlster. VITRA: Verbalisierung visueller Information. In: Informatik Forschung und Entwicklung, 11(1):12-19, 1996.
• G. Herzog. From Visual Input to Verbal Output in the Visual Translator. In: R. K. Srihari (ed.), Proceedings of the AAAI Fall Symposium on Computational Models for Integrating Language and Vision, Cambridge, MA, 1995.
• G. Herzog and K. Rohr. Integrating Vision and Language: Towards Automatic Description of Human Movements. In: I. Wachsmuth, C.-R. Rollinger, and W. Brauer (eds.), KI-95: Advances in Artificial Intelligence. 19th Annual German Conference on Artificial Intelligence, pp. 257-268. Berlin, Heidelberg: Springer, 1995. This paper received the Springer Award for the best contribution.
• G. Herzog. Coping with Static and Dynamic Spatial Relations. In: P. Amsili, M. Borillo, and L. Vieu (eds.), Proceedings of TSM'95, Time, Space, and Movement: Meaning and Knowledge in the Sensible World, Château de Bonas, France, pp. C 47-59. Groupe Langue, Raisonnement, Calcul, Université Paul Sabatier, Toulouse, 1995.
• G. Herzog and P. Wazinski. VIsual TRAnslator: Linking Perceptions and Natural Language Descriptions. In: P. Mc Kevitt (ed.), Integration of Natural Language and Vision Processing: Computational Models and Systems, Volume 1, pp. 83-95. Dordrecht: Kluwer, 1995.
• E. André, G. Herzog, und T. Rist. Von der Bildfolge zur multimedialen Präsentation. In: Fachtagung Integration von Bild, Modell und Text '95 am 2. und 3. März 1995 in Magdeburg, pp. 129-142. Arbeitsgemeinschaft Simulation in der GI (ASIM), Mitteilungen aus den Arbeitskreisen, Heft Nr. 46, Technische Universität. Wien, 1995.
• T. Längle, T. C. Lüth, E. Stopp, G. Herzog, and G. Kamstrup. KANTRA — A Natural Language Interface for Intelligent Robots. In: U. Rembold, R. Dillman, L. O. Hertzberger, and T. Kanade (eds.), Intelligent Autonomous Systems (IAS 4), pp. 357-364. Amsterdam: IOS, 1995.
• E. Stopp, K.-P. Gapp, G. Herzog, T. Längle, and T. C. Lüth. Utilizing Spatial Relations for Natural Language Access to an Autonomous Mobile Robot. In: B. Nebel and L. Dreschler-Fischer (eds.), KI-94: Advances in Artificial Intelligence. 18th German Annual Conference on Artificial Intelligence, pp. 39-50. Berlin, Heidelberg: Springer, 1994.
• G. Herzog und P. Wazinski. KI-Programmierung in LISP. KIFS-94, 12. Frühjahrsschule Künstliche Intelligenz, 26.2.-5.3.1994 Günne / Möhnesee, Kursunterlagen, 1994.
• E. André, G. Herzog, and T. Rist. Multimedia Presentation of Interpreted Visual Data. In: P. Mc Kevitt (ed.), Proceedings of AAAI-94 Workshop on Integration of Natural Language and Vision Processing, pp. 74-82, Seattle, WA, 1994.
• G. Herzog and P. Wazinski. VIsual TRAnslator: Linking Perceptions and Natural Language Descriptions. In: Artificial Intelligence Review, 8(2/3):175-187, 1994.
• T. C. Lüth, T. Längle, G. Herzog, E. Stopp, and U. Rembold. KANTRA: Human-Machine Interaction for Intelligent Robots Using Natural Language. In: Proceedings of the 3rd IEEE International Workshop on Robot and Human Communication, RO-MAN'94, pp. 106-111, Nagoya, Japan, 1994.
• W. Maaß, P. Wazinski, and G. Herzog. VITRA GUIDE: Multimodal Route Descriptions for Computer Assisted Vehicle Navigation. In: Proceedings of the Sixth International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE-93, pp. 144-147, Edinburgh, Scotland, 1993.
• G. Herzog, J. Schirra, und P. Wazinski. Arbeitsbericht für den Zeitraum 1991-1993: VITRA – Kopplung bildverstehender und sprachverstehender Systeme. Memo 58, Universität des Saarlandes, SFB 314 (VITRA), Juli 1993.
• G. Herzog, W. Maaß, and P. Wazinski. VITRA GUIDE: Utilisation du Langage Naturel et de Représentation Graphiques pour la Description d'Itinéraires. In: Images et Langages: Multimodalité et Modélisation Cognitive, Colloque Interdisciplinaire du Comité National de la Recherche Scientifique, pp. 243-251, Paris, 1993.
• G. Herzog. Visualization Methods for the VITRA Workbench. Memo 53, Universität des Saarlandes, SFB 314 (VITRA), 1992.
• P. Wazinski and G. Herzog. Coping with Topological and Directional Relations Based on 3-Dimensional Geometric Representations. In: Spatial Concepts: Connecting Cognitive Theories with Formal Representations, Workshop Notes, 10th Eeuropean Conference on Artificial Intelligence, Vienna, Austria, 1992.
• G. Herzog. Utilizing Interval-Based Event Representations for Incremental High-Level Scene Analysis. In: M. Aurnague, A. Borillo, M. Borillo, and M. Bras (eds.), Proceedings of the 4th International Workshop on Semantics of Time, Space, and Movement and Spatio-Temporal Reasoning, Château de Bonas, France, pp. 425-435. Groupe Langue, Raisonnement, Calcul, Université Paul Sabatier, Toulouse, 1992.
• R. M. Jansen-Winkeln, J. Allgayer, M. Bolz, G. Herzog und C. Huwig. Kooperatives Arbeiten am multifunktionalen Bewegtbild-Arbeitsplatz mfBApl. In: J. Friedrich und K.-H. Rödiger (Hrsg.), Computergestützte Gruppenarbeit (CSCW), pp. 259-268. Stuttgart: Teubner, 1991.
• G. Herzog, T. Rist, und E. André. Sprache und Raum: Natürlichsprachlicher Zugang zu visuellen Daten. In: C. Freksa und C. Habel (Hrsg.), Repräsentation und Verarbeitung räumlichen Wissens, pp. 207-220. Berlin, Heidelberg: Springer, 1990.
• G. Herzog und G. Retz-Schmidt. Das System SOCCER: Simultane Interpretation und natürlichsprachliche Beschreibung zeitveränderlicher Szenen. In: J. Perl (Hrsg.), Sport & Informatik, pp. 95-119. Schorndorf: Hofmann, 1989.
• G. Herzog, C.-K. Sung, E. André, W. Enkelmann, H.-H. Nagel, T. Rist, W. Wahlster, and G. Zimmermann. Incremental Natural Language Description of Dynamic Imagery. In: C. Freksa and W. Brauer (eds.), Wissensbasierte Systeme. 3. Internationaler GI-Kongreß, pp. 153-162. Berlin, Heidelberg: Springer, 1989.
• E. André, G. Herzog, and T. Rist. Natural Language Access to Visual Data: Dealing with Space and Movement. Report 63, Universität des Saarlandes, SFB 314 (VITRA), 1989. Presented at the 1st Workshop on Logical Semantics of Time, Space and Movement in Natural Language, Toulouse, France, 1989.
• G. Herzog und T. Rist. Simultane Interpretation und natürlichsprachliche Beschreibung zeitveränderlicher Szenen: Das System SOCCER. Memo 25, Universität des Saarlandes, SFB 314 (VITRA), 1988.
• E. André, G. Herzog, and T. Rist. On the Simultaneous Interpretation of Real World Image Sequences and their Natural Language Description: The System SOCCER. In: Proceedings of the 8th European Conference on Artificial Intelligence, pp. 449-454, Munich, Germany, 1988.
• G. Herzog. LISPM Miniatures. Memo 19, Universität des Saarlandes, SFB 314, 1987.
• T. Rist, G. Herzog, und E. André. Ereignismodellierung zur inkrementellen High-level Bildfolgenanalyse. In: E. Buchberger und J. Retti (Hrsg.), 3. Österreichische Artificial-Intelligence-Tagung, pp. 1-11. Berlin, Heidelberg: Springer, 1987.
• E. André, T. Rist, und G. Herzog. Generierung natürlichsprachlicher Äußerungen zur simultanen Beschreibung zeitveränderlicher Szenen. In: K. Morik (Hrsg.), GWAI-87. 11th German Workshop on Artificial Intelligence, pp. 330-337. Berlin, Heidelberg: Springer, 1987.
• E. André, G. Bosch, G. Herzog, and T. Rist. Coping with the Intrinsic and the Deictic Uses of Spatial Prepositions. In: K. Jorrand and L. Sgurev (eds.), Artificial Intelligence II: Methodology, Systems, Applications, pp. 375-382. Amsterdam: North-Holland, 1987.
• G. Herzog. Ein Werkzeug zur Visualisierung und Generierung von geometrischen Bildfolgenbeschreibungen. Memo 12, Universität des Saarlandes, SFB 314 (VITRA), 1986.
• E. André, G. Bosch, G. Herzog, and T. Rist. Characterizing Trajectories of Moving Objects Using Natural Language Path Descriptions. In: Proceedings of the 7th European Conference on Artificial Intelligence, volume 2, pp. 1-8, Brighton, UK, 1986.

Last update: Mon Jan 21 14:07:58 MET 2008