HDI 2017

1st International Workshop on Human-Document Interaction (HDI 2017)

To be held in Kyoto, Japan, on November 12, 2017 in conjunction with ICDAR 2017

HDI 2017 will focus on how humans interact with written information around them, and the interfaces between users and documents. The term document is meant in the wider possible sense, to refer to any physical object that carries written information.

The workshop aims to create a space for debate between the Document Image Analysis and Recognition and the Human-Computer Interaction communities, and it is motivated by a number of recent developments that point to a coming change of paradigm in the way we interact with written information around us.

Scope and motivation

Physical and digital documents are finally settling to coexist in peace - connecting the two is empowering for both sides. Technology advances, such as in augmented reality, permit bringing forms of digital interaction to the physical world and vice versa, while the linking between the physical and the digital world is done in an increasingly more fluid and realistic manner.

At the same time, a new generation of readers, conditioned by the affordances offered by electronic content and the new media types (e.g. blogs and social media posts), have developed distinct reading behaviours and new ways to interact with written content. Wearable sensors allow observing the user and introducing the user context it in the loop, offering personalised services by intelligently linking written information with the user actions. Mobile cameras are changing, the market is shaped by new trends, including virtual and augmented reality. At the same time, embedded 3D mobile cameras (computational and interactive) are already transforming the mobile camera function. The Internet of Things is evolving the way everyday objects (many of them carriers of text) can influence our actions.

In this context, it is useful to study the way humans interact with written information around them and ponder on the evolution of the paper document towards an interactive medium, or indeed on the evolution of written information in general, no matter how it is delivered, as an interaction element in the reading process. Understanding the behaviour and needs of the reader, and the ability to link it in real time to the written information is important.

Document image analysis technology is a sine-qua-non for enabling interaction. The DIAR researchers have to build bridges with other disciplines, including Human-Computer Interaction, eye-tracking and gaze analysis, wearable sensors, reading behaviour analysis and augmented reality to mention just a few, and create an multidisciplinary research space.

For enabling interaction with written information around us, it is necessary to challenge the way things are traditionally done in DIAR research. We need to move from server-side systems thought to process large collections in a sequential manner, to real-time, responsive systems on the client-side. The extraction of relevant information on-the-spot, from not-seen-before documents (written information carriers) might remain an open challenge for the near future, but the need for fluid interaction can easily become new fuel for DIAR and shift the focus to this kind of issues.

Topics of Interest

  • Augmented documents
  • Linking physical and digital content
  • Reading behaviour analysis
  • Human factors
  • User experience and usability
  • Wearable sensors in reading
  • Interaction for facilitating Document Image Analysis (teaching reading systems through the way humans interact with written information)
  • Document Image Analysis for enabling Interaction
  • Content personalisation
  • Applications (e.g. document editing, interactive translation, collaborative editing)

Important Dates

  • Submission Deadline (normal papers): July 1, 2017
  • Submission Deadline (ICDAR resubmissions): July 15, 2017
  • Notification: July 31, 2017
  • Camera Ready: September 1, 2017
  • Workshop: November 10 or 11, 2017 (TBC)