Tuesday, April 28, 2015

Fact Ranking

Dear students!
We have developed a quiz which will allow us to tackle one of our main scientific research problems and we would really appreciate your participation and help in our experiment!


The problem is that there is too much information available on the web. How do we decide which facts are most important for a specific object?

Just a quick example. Let's assume we have the following two facts:
(1) Albert Einstein is a physicist.
(2) Albert Einstein is a vegetarian.

Which of the two facts is more important or relevant? This is difficult to answer, simply because the truth often lies in the eye of the beholder. For a vegetarian, maybe the second fact is more important. But, what about the most common opinion? What would the mainstream think? Probably, most people would say that fact (1) in general is more important.

We selected about 500 popular concepts from Wikipedia and would like to gather as much input as possible, regarding the ranking of their facts. Therefore, we really appreciate your help in this task!

Our quiz can be found here. (the registration takes just 1 minute)
 
There is no right or wrong answer. Just vote as you think it seems right for you. Afterwards, we will aggregate all votes from all participants to determine a general (mainstream) relevance for the presented facts.

You may pause at any time and continue later. As you go, you will get score points which depend on how well you've answered the questions and how many concepts you've covered.

Please do also spread the word and share the task with your friends and family. The more participants, the more valid our ground truth will be. While you are playing this game, your inputs will contribute to our scientific experiment. Together, we will build a first corpus that will help our scientific community in evaluating different fact ranking strategies!

For more information, see: 

Monday, April 20, 2015

Tasks for the first Team Meeting next week

The team meetings will start on an individual basis next week on Monday, April 27, 2015 in A-1.2.
  • 3:15pm: Team Semantic Video Player & Editor
  • 4:00pm: Team Insect Image Segmentation

Please prepare for the following tasks until next week:
  1. Sketch a first working plan for the task
  2. Coordinate the work among group participants (who is responsible for what?)
  3. Start reading literature (according to references in the slides)
  4. Find already existing applications/libraries that can be used/adapted for the task or one of its subtasks

Thursday, April 16, 2015

Monday, April 13, 2015

Semantic Multimedia


The Web of Data provides useful information on a variety of topics. Even though the available Linked Data knowledge bases are interlinked, the connections to traditional data sources on the web, such as web platforms, online databases, etc. are often missing. During the course of this seminar, we will combine Linked Open Data resources and multimedia content, such as videos and images from the foreground. Visual analysis, as well as semantic analysis and annotation techniques are to be used and implemented in form of a web application.

Seminar contents

  • Visual analysis of multimedia data
  • Integration of semantic and traditional metadata
  • Linked Data management
  • Fine-grained (semantic) annotation of multimedia data
  • Efficient visualization(s) and visual analytics

Possible solutions scenarios should be developed and implemented in small groups (max 3-4 students).

Seminar challenges

  •  Semantic media fragments enchanced Video Player and Editor
    • Display video with various video metadata based on media fragments
    • Support aggregated views and visualizations of time-based video metadata
    • Manual annotation and manipulation/editing of time-based video metadata
    • Support video annotation with semantic metadata
    • Export of video metadata as Linked Open Data
  •  Semantic image analysis of insect speciments
    • Visual analysis
      • Image segmentation
      • Classification
    • Semantic Image Annotation
    • Data publication as Linked Open Data

Relevant literature and software packages


Presentation slides



General information

  • Time: Mondays, 15:15h - 16:45h, A-1.2
  • SWS / Credit points : 4 / 6.0 (graded)
  • Seminar language: English
  • Blog: http://semmul2015.blogspot.de

First meeting:

Monday, April 13th, 15:15h, A-1.2


Important dates

  • 20.04.2015: Formation of student teams, technical introduction
  • 27.04.2015: First team meetings
  • 08.06.2015: Midterm presentation (plenary session)
  • 20.07.2015: Final presentations (plenary session)
  • 31.08.2015: Deadline for seminar reports

Grading


  • Implementation of a research application
  • Final written report on the achieved results (seminar paper)
  • Presentation of achieved results (midterm, final, team meetings)