Home      Log In      Contacts      FAQs      INSTICC Portal
Special Session
Special Session on
Multimodal and Lifelong Machine Learning
 - MALM 2019

19 - 21 February, 2019 - Prague, Czech Republic

Within the 11th International Conference on Agents and Artificial Intelligence - ICAART 2019


Lambert Schomaker
University of Groningen
Brief Bio
Lambert Schomaker (19-2-1957) is professor in artificial intelligence at the university of Groningen since 2001 and director of the AI institute at this university. He is known for research in simulation and recognition of handwriting, writer identification, style-based document dating and other studies in pattern recognition and machine learning. He has (co)authored over 200 publications and was involved in the organization of many conferences in handwriting recognition and document analysis. In recent years he and his team have worked on the Monk system: an interactively trainable search engine and e-Science service for historical manuscripts. The availability of up to thousands of training images for single classes of complex patterns has brought pattern recognition and machine learning into the ballpark of big data. Other recent work is in the area of robotics and industrial maintenance, in the EU ECSEL project Mantis. In 2015, he became co-chair of the Data Science and Systems Complexity center at the Faculty of Science and Engineering at the University of Groningen. In 2017, he joined the CogniGron center for cognitive systems and materials in a large-scale seven-year project in neuromorphic computing. He is a member of the IAPR and senior member of IEEE.
Marco Wiering
University of Groningen

Brief Bio
Marco Wiering is an assistant professor in the department of artificial intelligence from the University of Groningen, The Netherlands. He performed his PhD research in the research institute IDSIA in Switzerland and graduated in 1999 on the topic of reinforcement learning. Before going to the University of Groningen, he worked as an assistant professor at Utrecht University. His main research topics are reinforcement learning, deep learning, neural networks, support vector machines, computer vision, game playing, time-series prediction and optimization.


Modern machine learning has proven to be very successful in unimodal applications (image OR text OR sound). Furthermore, the successes are usually based on idealized training conditions with nicely packaged benchmark tests. The reality of historical-document retrieval is quite different. Optical character recognition is too limited to handle the variety of visual patterns in such image collections: text, graphics, tabular structures, doodles and diverse image problems make this a challenging playing field. Such systems start with zero labels, the labels change over time and the data is neither stationary nor ergodic. This session is intended for researchers who have picked up challenges in multimodal machine learning, possibly even in a time-varying context.

- Multimodal Deep Learning
- Image and Text Correspondence
- Data-driven Semantics
- Deep Multimodal Semantic Embeddings
- Historical Documents
- Interactive Data Mining


Paper Submission: January 3, 2019 (expired)
Authors Notification: January 10, 2019 (expired)
Camera Ready and Registration: January 15, 2019 (expired)


Maruf A. Dhali, University of Groningen, Netherlands
Klaas Dijkstra, NHL Stenden University of Applied Sciences, Netherlands
Sheng He, Harvard Medical School, United States
Hamidreza Kasaei, University of Groningen, Netherlands
Emmanuel Okafor, University of Groningen, Netherlands
Matthia Sabatelli, University of Liège, Belgium
Jos van de Wolfshaar, University of Groningen, Netherlands

(list not yet complete)


Prospective authors are invited to submit papers in any of the topics listed above.
Instructions for preparing the manuscript (in Word and Latex formats) are available at: Paper Templates
Please also check the Guidelines.
Papers must be submitted electronically via the web-based submission system using the appropriated button on this page.


After thorough reviewing by the special session program committee, all accepted papers will be published in a special section of the conference proceedings book - under an ISBN reference and on digital support - and submitted for indexation by DBLP, Web of Science / Conference Proceedings Citation Index, EI, Microsoft Academic, SCOPUS, Semantic Scholar and Google Scholar.
SCITEPRESS is a member of CrossRef ( and every paper is given a DOI (Digital Object Identifier).
All papers presented at the conference venue will be available at the SCITEPRESS Digital Library


ICAART Special Sessions - MALM 2019