About the Workshop

Human memory holds a lifetime worth of information, which forms the base of our knowledge, our character, and identity. Sometimes this memory fails us, which is why people have always sought to develop tools to make sure information is not lost: through the advent of writing all the way to the printing press and the invention of computers. Such tools help us retain information, browse through it, and ultimately remember. Nowadays, a vast array of commercially available technologies enable us to record extensive amounts of data of our lives. This personal data contains activities, locations, experiences, and therefore memories. Advances in machine learning have made it feasible to turn this data into memories that can be processed, queried, and retrieved. Hence, Vannevar Bush’s Memex vision of an external memory extension has become reality through near-constant recording capabilities, vast storage space and a ubiquitous Internet connection. In theory, people have their entire set of experiences and knowledge at their fingertips. However, to truly use this information to extend human cognition – our ability to learn and solve tasks; our beliefs; our attention and engagement; and of course our memory – the challenge persists: delivering information at the right time to the right extent in a context-driven way.

In this workshop, we are looking for visions and application scenarios that utilizes lifelogs for augmenting human memory and human cognition. In its third rendition, we are building on a growing community. WAHM 2014 had 15 participants, which grew to 34 in last year’s edition. For this year’s edition, we start from the question “What constitutes as a modern lifelog?”. It is a challenge to the community to focus on the use of lifelogs as the basis for extending human cognition, as a source of additional information that we can integrate with other information sources that people will query in the future when they are looking for information. Rather than using an online search engine or manually looking through terabytes of personal data, people may simply ask an assisting system: ”What was the name of that tapas place I enjoyed in Barcelona a few years ago?”. Searches may no longer take place purely in online archives, but also draw from personal experiences and memories.

We would like to invite researchers, designers, and practitioners to envision and exchange ideas on how ubiquitous technologies and applications enhance people’s cognition and memory in everyday life. At the intersection of technology and cognitive psychology, we concentrate on the integration of lifelogs in application layers, the utilization of “e-memories”, and new forms of memory aids.

Themes

We are proposing a number of more directed themes, which will be addressed depending on participants’ contributions:

• Applied cognitive memory theories.
  How can lifelogs and ubiquitous technologies be used to re-enforce (or even attenuate) memories? Forgetting is a common phenomenon for information or experiences, which are rarely rehearsed or reflected on. Technology could be used to retrieve items from lifelogs and help remedy this memory loss by providing users with time-relevant and context-appropriate cues.
• Harvesting existing data sources.
  An increasing number of commercial products are available for quantifying peoples lives. Although the adoption of additional recording devices, such as wearable cameras or step counters, has been slow, people have increasingly engaged in recording and sharing their daily habits and experiences on social media platforms. How much of this data can be used for personal lifelogs or implicitly collected in order to support memory?
• Information retrieval and processing.
  It is crucial for extracting information from vast lifelogs. We want to discuss potential technologies relevant for memory processing and retrieval and how retrieved information can be made available for application layers.
• Attention awareness.
  A holistic lifelog allows algorithms to derive user patterns, such as favourite foods, preferred outdoor activities, authors read, countries travelled, but also detailed information about how users spend their days. Based on phases of concentrated focus, e.g. complex work activity or reading a sophisticated text, over time an algorithm can recreate the user’s circadian cycle, i.e. attention phase pattern across the day. This information can then be used by systems where attention-awareness is crucial, such as task recommendations, notifications and interruptions, or deciding how dense information can be presented when the user is making a search request.
• Designing knowledge acquisition points.
  Whenever people consume information or have a new experience, they advance their personal knowledge: whether that is consciously focusing on digesting information, such as when reading, or learning something during a conversation. At the point of consumption, information can be linked to existing memories or experiences, which can help anchor that information in long-term memory. Therefore, lifelog queries need to be made in real-time and linked to existing content.
• Privacy and security.
  Personal recording technologies, culmination of information in lifelogs, and providing access to such raise new challenges to people’s security of personal data. When private memory records are stored for later retrieval, they need to be protected from unauthorized access and tinkering.
• Designing for shared memories.
  There is a crucial need to develop flexible paradigms for sharing and provenance of e-memories. They should resolve the conflict between multiple owners of a single memory. For example, sharing of group photos on social networks if a member rejects it or accidental capture of a person through automated capture devices. Another aspect is encouraging users to contribute personal memories into central services to derive valuable insights about communities. Such insights are used to enhance the life quality of the individuals. A clear example is the estimation of traffic congestion through the GPS logs of users.
• Commercial application areas for e-memories.
  While many of the application domains for memory technologies are targeting the public good, the same technologies can also be employed in the commercial context. For example, drawing information from lifelogs could be used to support a new form of advertising, in which products are linked to past experiences.

Goal

The workshop goal is to develop and share visions and concrete application scenarios using ubiquitous technologies to exploit personal data in supporting and augmenting cognitive processes and the human mind. The above-mentioned themes will be used as a starting point for discussion and group analysis (described below). However, we will also pay attention to new themes possibly emerging from morning presentation and discussions.

Submissions

Workshop candidates are requested to send a position paper (4-8 pages in the ACM SIGCHI non-archival Extended Abstracts template, i.e. landscape format) to the organizers about their research and link to one or several of the proposed workshop themes. In addition to describing their work, candidates will be asked to write about challenges and opportunities they see for actionable lifelogs and technologies that augment cognitive processes and human memory, in order to prepare for the workshop theme. We have assembled a group of experts from related fields (see below) who will serve on the program committee to evaluate submissions and give detailed feedback to the authors.

All submissions should be sent in PDF to [email protected] with "WAHM 2016 Submission" as e-mail subject.

Preliminary Agenda

• - 09:00am: Introduction and Keynote by Dr. Lewis Chuang (30+15min)
• - 10:00am: Talks (3 papers, each 5+5mins)
• - 10:30am: Coffee Break
• - 11:00am: Talks (3 papers, each 5+5mins)
• - 11:30am: Discussion and inspirations for the afternoon
• - 12:30pm: Lunch
• - 02:00pm: Application scenarios development
• - 03:30pm: Coffee break
• - 04:00pm: Group Discussion
• - 05:00pm: Wrap-up and next actions
• - 06:00pm: End of workshop
• - 07:30pm: Dinner

Organizers

Andreas Dengel is a member of the Management Board as well as Scientific Director at the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern where he is leading the Knowledge Management Research Department. In 1993 he became a Professor at the Computer Science Department of the University of Kaiserslautern. Since 2009 he also holds a Honorary Professorship at the Dept. of Computer Science and Intelligent Systems, Graduate School of Engineering, of Osaka Prefecture University. His main scientific emphasis is in the areas of Smart Data, Deep Learning, Document Understanding, Semantic Technologies, Information Retrieval, Multimedia Mining, and Social Media.

Tilman Dingler is a researcher at the Institute for Visualization and Interactive Systems at University of Stuttgart. He focusses on concepts and applications in the field of Pervasive Computing, thereby developing embedded devices and software for context-aware systems that put users and their context at the center. Tilman holds a Diploma in Media Computer Science from the University of Munich, a Master’s degree in Web Science from the University of San Francisco and an Honors degree in Technology Management from the Center for Digital Technology and Management in Munich. Before starting his PhD, Tilman was developing software for TinyCo and Yahoo!.

Ioannis Giannopoulos is a post-doctoral researcher and lecturer at the Chair of Geoinformation Engineering at the Swiss Federal Institute of Technology (ETH) Zurich. His research interests focus on mobile gaze based assistance of spatio-temporal decisions during wayfinding. This includes the performance of user studies in real urban and virtual environments for the exploration of processes such as self-localization and orientation, the development of novel mobile gaze based wayfinding assistance concepts and their evaluation in realistic scenarios.

Cathal Gurrin is a lecturer at the School of Computing, at Dublin City University, Ireland and he is a principal investigator at the Insight Centre for Data Analytics. His research interest is personal data analytics, information retrieval and lifelogging. He has developed WWW search algorithms, multimedia content mining tools and he has gathered a digital memory since 2006. He has been PC and General chair of a number of related conferences and he is the author of Lifelogging: Personal Big Data, published in 2014 in the FNTIR series.

Koichi Kise is a Professor at Department of Computer Science and Intelligent Systems, Graduate School of Engineering, Osaka Prefecture University and the director of Institute of Document Analysis and Knowledge Science (IDAKS), Osaka Prefecture University, Japan. He received B.E., M.E. and Ph.D. degrees in communication engineering from Osaka University, Osaka, Japan in 1986, 1988 and 1991, respectively. From 2000 to 2001, he visited German Research Center for Artificial Intelligence (DFKI), Germany. He works as the chair of the IAPR technical committee 11 (reading systems), a member of the IAPR conferences and meetings committee, and an editor-in-chief of the international journal of document analysis and recognition. His research interests include analysis, recognition and retrieval of documents, images and human activities with a special focus on reading.

Kai Kunze works as an Associate project Professor at Keio Media Design, Keio University. Beforehand, he held an assistant professorship at Osaka Prefecture University. He received a Summa Cum Laude for his PhD thesis, University Passau. He was visiting researcher at the MIT Media Lab. His work experience includes internships at the Palo Alto Research Center (PARC), Sunlabs Europe and the Research Department of the German Stock Exchange. His major research contributions are in pervasive computing, especially in sensing, physical and cognitive activity recognition. Recently, he focuses on tracking knowledge acquisition activities, especially reading.

Evangelos Niforatos is a researcher at Università della Svizzera italiana (USI) in Lugano, Switzerland. His main research interests lie in the area of Ubiquitous Computing, where he develops methods and tools for supporting episodic memory recall. Evangelos holds a 4-year degree in Informatics and a Master diploma in Computer Networks and Communications, both obtained from Ionian University in Greece. He has previously worked as a research assistant at Madeira Interactive Technologies Institute in Portugal, in a joint collaboration with CGI for delivering innovative service design.

Program Committee

Besides the workshop organizers, we have put together a program committee for the workshop who will provide detailed feedback on all submissions:

Passant El Agroudy, University of Stuttgart, Germany

Agon Bexheti, Università della Svizzer italiana, Switzerland

Andreas Dengel, DKFI, Germany

Tilman Dingler, University of Stuttgart, Germany

Ioannis Giannopoulos, ETH, Switzerland

Cathal Gurrin, Dublin City University, Ireland

Koichi Kise, Osaka Prefecture University, Japan

Kai Kunze, Keio University, Japan

Marc Langheinrich, Università della Svizzera italiana, Switzerland

Evangelos Niforatos, Università della Svizzera italiana, Switzerland