>> Student Project Ideas (updated June 2021)

[ Check also out the new DASYA web page ]

Media collections are becoming a central information resource for a growing number of domains. This calls for very effective tools for not only finding content in those collections, but also gaining insights into the collections and analyzing them. Below are some projects related to two different media exploration systems that we are working on.

PhotoCube is a multi-dimensional media explorer based on faceted search. If you are familiar with pivot tables, you can think of extending them to multimedia. Then add 3D browsing of your collection! Then add virtual reality!! Then aim to scale this to *illions of media items!!! Now we start to have fun...

Video Browser Showdown

In this project, we propose to develop new versions of the C++-based media server and JS-based media browser. The goal is to expand the data model to videos and improve the performance sufficiently to take part in the Video Browser Showdown.


Virtual Reality Client

We are actively developing a new prototype for analysing large multimedia collections in virtual reality, based on the ObjectCube data model. There are many ways in which students can contribute to the project, including work on the user interface and the back-end, and later on running large-scale user experiments.


Exquisitor is an extremely scalable media explorer based on relevance feedback. To learn more about the basis of the Exquisitor system, please check this demonstration video made for the ACM Multimedia 2019 conference.

Hash-Based Indexing

In interactive learning systems, such as Exquisitor, the system presents potentially relevant images to users who label them as either relevant or irrelevant. Currently, Exquisitor uses a cluster-based index, which allows it to return results from a collection of 100 million images in 0.3 seconds. The goal of this project is to study the application of hash-based indexing to interactive learning and compare to the current approach.


Diversity in User Relevance Feedback

The choice of images to present to the user is a difficult problem, as a naïve approach may present too many similar images. The challenge addressed in this project is to ensure diversity (aka “one of each”) as well as relevance.