Automatic summary of conference talks based on video and audio content

Research a method to create highlight videos of conference talks based on video and audio content by using a deep learning model.

Required interest(s)

  • Video recognition/detection/segmentation
  • Applied deep learning

What do you get

  • A challenging assignment within a practical environment
  • € 1000 compensation, € 500 + lease car or € 600 + living space
  • Professional guidance
  • Courses aimed at your graduation period
  • Support from our academic Research center at your disposal
  • Two vacation days per month

What you will do

  • 65% Research

Because of COVID-19, many conferences are presenting their content online. There’s so much content available, it’s hard to keep track of all the sessions. We want to provide audiences with automatic highlight videos of sessions that we’re uploading through our own channels.

Previous research in this area has shown that it is possible to create highlight videos for services like twitch. This works because we can gather clues from the chat and from specific markers in the video stream itself.

Conference talks, however, are quite different. Typically, we don’t have user feedback available that we can associate with timestamps in the video stream. Also, the audience on twitch tends to cheer the player on, while during a conference talk this behavior isn’t shown.

There is a structure to a conference talk, so our hypothesis is that it should be possible to segment conference talks and determine which segments are important based on labels that we assign to each segment.

About Info Support Research Center

We anticipate on upcoming and future challenges and ensures our engineers develop cutting-edge solutions based on the latest scientific insights. Our research community proactively tackles emerging technologies. We do this in cooperation with renowned scientists, making sure that research teams are positioned and embedded throughout our organisation and our community, so that their insights are directly applied to our business. We truly believe in sharing knowledge, so we want to do this without any restrictions.

Sign up for this assignment

  • Geaccepteerde bestandstypen: docx, doc, txt, pdf.

Application procedure

1

Introductory meeting

Discuss (study) career, interests and ambitions and introduction Info Support.

2

Review

Assessment of professional knowledge and personality (capacity, competences and motives).

3

Selection interview

Deepen professional knowledge and personality.

4

The signing of a contract

Contract offer and invitation for drawing moments.

Other Mastertheses

graduation assignment

Detecting forged documents with neural networks

Detect forged documents using a neural network. That is what this assignment is all about. One of our customers, a large credit provider, now checks all applications manually and is looking for a solu…

graduation assignment

What-if analysis on intent detection models and datasets

Research a method to visualize the impact of changes in the dataset for an intent detection solution impacts the performance of the trained intent detection model, without training the model.

graduation assignment

Protecting computer vision models against tampering when using transfer-learning

Research a method to protect state-of-the-art computer vision models against tampering in transfer-learning scenarios.

graduation assignment

Automatic summary of conference talks based on video and audio content

Research a method to create highlight videos of conference talks based on video and audio content by using a deep learning model.