div0 div1 div2 div3 div4 Flickr Twitter LinkedIn Blog Twitch Laboratory Social Media Library Blog CV Gallery About Publications


MindtoEye represents the collective works of Martin van Velsen. Martin van Velsen is a senior research engineer in the Human Computer Interaction institute and graduate student in the Language Technologies Institute at Carnegie Mellon University. He is the lead visualization developer for the CTAT authoring research group. Martin also works fulltime on research projects of a wildly varied nature, some which are: neurosurgery simulations, large scale artificial intelligence architectures, virtual humans and training simulations. Martin serves as technical adviser to many leading specialists in the field of serious games, simulations, and digital entertainment. As a digital storytelling expert, Martin serves as research consultant to entertainment companies including Fortune 500 companies. Martin has been a speaker and panel host for various entertainment technology gatherings. Most recently he took part as a panelist at the PAX East gaming convention, but he has also organized such scientific forums as a panel on Authoring Interactive Narrative at the Stanford Spring Symposium. Over the last 18 years Martin has been responsible for shepherding open-ended research projects towards viable products that can be deployed by such organizations as DARPA, Army Research Labs (ARL), Air Force Research Labs (AFRL) and the Office of Naval Research (ONR). Finally Martin is an award winning artist, published fiction author, engineer, and a researcher in the field of interactive narrative.

Ephemeral Essentialism

Ironically my version of art, which is an expression of humanity in all it's forms, usually goes towards a bare and austere representation. Call it essentialism if you will. Essentialism takes off the trivial and non essential layers of humanity and reveals its basic forms. As an extension it then allows the artist to find potential and future grace and explore ways in which to make otherwise invisible concepts available. An early attempt can be seen to the right in the top imagine. This represents a mask of a future humanity, a possible incarnation of rampant evolution in the abstract.

According to Wikipedia:

In philosophy, essentialism is the view that, for any specific kind of entity, there is a set of characteristics or properties all of which any entity of that kind must possess. Therefore all things can be precisely defined or described. In this view, it follows that terms or words should have a single definition and meaning.

Essentialism garnered a tremendous amount of criticm within philosophy, and rightfully so. However, using essentialism as a tool knowing its imperfections and shortcomings can be extremely useful. Within sculpture, breaking down a face into it's unique features and shapes can be the key to conveying a person's personality. Similarly we can use the key features that define a person's individuality to design a portrait containing one or more essenses of the subject.

I therefore work in terms of ephemeral essentialism, acknowledging that we only show and expose our core values, ingredients and individuality on very brief occasions.

Personal History

Essentialism as presented here stems from two distinct influences. First of all special makeup effects created a predisposition to see the human face in a layered metaphor. Faces and human emotion are multi-layered expressions. We are multiple people, multiple experiences and we have multiple ways of looking at the world. All of this is expressed by changing our features but we are hard pressed to emote multiple sensations at once. At any point in time we are animals, intellectuals, students, parents, and many other beings. While working in special makeup effects a desire to take away layers became important instead of adding more and more layers of clay on a cast of an actor's face. It is impossible to create a mask that takes away from an actors face and we are stuck with distorted features and a poor representation of what the artist had in mind.

Sphinx Mask

image-2 Old age sculpture on top of plaster life mask

image-3 Current setup for 17th century oil painting


Hoop: a text mining and language exploration workbench in Java. Primarily designed for event extraction and text-based event forecasting, the workbench is a generic text and language machine learning sandbox that can be adapted to a wide variety of tasks. Hoop is a collection of modules (hoops) each of which can take linguistic input from one, process it and pass it onto another. Combining those modules or hoops allows you to create complex analysis systems.


  1. Drag and Drop editor allowing you to stitch together custom tools and applications
  2. Rich API and developer support for rapid text analysis prototyping
  3. Large set of language oriented and related libraries with comprehensible API, see below
Many of the popular language processing tools are natively available directly from within the IDE. For example, shown below is a Hoop graph in which the last hoop is a visualization wrapper for the Standford NLP parse tree visualization panel. Below is an example of a graph that parses and shows a text file containing TREC questions.

Source Code


Social Media



“I have always imagined that Paradise will be a kind of library.”

― Jorge Luis Borges






  1. The Bureau for Imminent Souls, Excerpt from Novel, After Happy Hour Review (2014)
  2. Over, Flash Fiction, Lascaux Review (2014)


  1. Aleven, V., Sewall, J., Popescu, O., Ringenberg, M., van Velsen, M. and Demi, S., Embedding Intelligent Tutoring Systems in MOOCs and e-Learning Platforms, In Proceedings of the Thirteenth International Conference on Intelligent Tutoring Systems (ITS) (2016)
  2. Matsuda, N., van Velsen, M., Barbalios, N., Lin, S., Vasa, H., Hosseini, R., Sutner, K.and Bier, N., Cognitive Tutors Produce Adaptive Online Course: Inaugural Field Trial, In Proceedings of the Thirteenth International Conference on Intelligent Tutoring Systems (ITS) (2016)
  3. Aleven, V., Sewall, J., Popescu, O., van Velsen, M., Demi, S., & Leber, B. (2015). Reflecting on Twelve Years of ITS Authoring Tools Research with CTAT. Design Recommendations for Intelligent Tutoring Systems: Authoring Tools and Expert Modeling Techniques, 263.
  4. Ocumpaugh, J., Baker, R.S., Rodrigo, M.M.T., Salvi, A. van Velsen, M., Aghababyan, A., Martin, T. (in press). HART: The Human Affect Recording Tool. In Proceedings of the ACM Special Interest Group on the Design of Communication (SIGDOC).
  5. Adams, D.M., McLaren, B.M., Durkin, K., Mayer, R.E., Rittle-Johnson, B., Isotani, S., Van Velsen, M., Using erroneous examples to improve mathematics learning with a web-based tutoring system, Computers in Human Behavior, Volume 36, July 2014, Pages 401-411
  6. Hershkovitz, A., Baker, R.S.J.D., Moore, G., Rossi, L.M., Van Velsen, M., The Interplay between Affect and Engagement in Classrooms Using AIED Software, in proceedings of the 2013 conference Artificial Intelligence in Education (AIED) (2013)
  7. Van Velsen, M., The Persuasive Language of Interaction: Rhetoric in the Digital Age, in: Digital Rhetoric and Global Literacies: Communication Modes and Digital Practices in the Networked World, IGI Global (2013)
  8. Adams, D., McLaren B.M., Durkin, K., Mayer, R.E., Rittle-Johnson, B., Isotani, S., & Van Velsen, M. (2012). Erroneous examples versus problem solving: Can we improve how middle school students learn decimals? In N.Miyakem, D. Peebles, & R.P. Coppers (Eds.), Proceedings of the 34th Meeting of the Cognitive Science Society (CogSci 2012)
  9. Van Velsen, M., Williams J., Verhulsdonck G., Narrative Concepts for AI Driven Digital Interactive Story Telling, in proceedings of the 2009 ICIDS conference (2009)
  10. Van Velsen, M., Williams J., Verhulsdonck, G., Concepts for Interactive Digital Storytelling: From Table-top to Game-AI, in proceedings of the fifth conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), (2009)
  11. Jhala, A., Velsen, M., Challenges in Development and Design of Interactive Narrative Authoring Systems, a Panel, in proceedings of the 2009 AAAI Spring Symposium (2009)
  12. Van Velsen, M., Towards Real-time Authoring of Believable Agents in Interactive Narrative, in proceedings of the 8th International Conference on Intelligent Virtual Agents (IVA-08), (2008)
  13. Van Velsen, M., Narratoria, an Authoring Suite for Digital Interactive Narrative, accepted as a poster in proceedings of the 21st International Florida Artificial Intelligence Research Society Conference (2008)
  14. Kim, Y., van Velsen, M., Hill, R.W. Jr., Modeling Dynamic Perceptual Attention in a Complex Virtual Environment, 5th International Working Conference on Intelligent Virtual Agents (2005)
  15. Mark A. Spicer, Ph.D., M.D Martin van Velsen, John P. Caffrey, Ph.D., and Michael L.J. Apuzzo, M.D. Virtual Reality Neurosurgery - A Roadmap, International Journal: 'Neurosurgery' (April 2004)
  16. Gordon, A., van Lent, M., van Velsen, M., Carpenter, M., and Jhala, A., Branching Storylines in Virtual Reality Environments for Leadership Development. Proceedings of the Sixteenth Innovative Applications of Artificial Intelligence Conference (IAAI) (2004)
  17. Hill, R.W. Jr., Douglas, J., Gordon, A., Pighin, F.P., van Velsen, M. Guided Conversations about Leadership: Mentoring with Movies and Interactive Characters. Proceedings of the Fifteenth Innovative Applications of Artificial Intelligence Conference (IAAI) (2003)
  18. Sycara, K., Paolucci, M., van Velsen, M. and Giampapa, J., The RETSINA MAS Infrastructure. In the special joint issue of the international journal: Autonomous Agents and MAS, Volume 7, Nos. 1 and 2, July (2003)
  19. Massimo Paolucci, Zhendong Niu, Katia Sycara, Constantine Domashnev, Sean Owens and Martin van Velsen "Matchmaking to Support Intelligent Agents for Portfolio Management". In Proceedings of Autonomous Agents (2000)

Website Copyright (C) 2007- MindtoEye, All Rights Reserved
Painting by Charles John De Lacy - Harbour Scene From London