A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.




Event Analysis

The goal is to analyse vast amounts of event-centric textual and visual information in multiple languages.

Misinformation Detection

Misinformation detection is a field of study to detect documents that include falsified information in the form of text, images, videos, etc. The research explores the ideas to detect misinformed facts from social media posts, news articles, videos and related multimedia data.

Multimodal Learning

Multimodal Learning is a method of analysing multimodal information such as videos, image and text pairs, etc. The main goal is to build computational models to jointly extract, interpret information from all available modalities.

Natural Language Understanding

Natural Language Understanding is a subtopic of natural language processing in Artifical Intelligence that deals with machine reading comprehension.

Video Summarization

Video summarization deals with providing a summary for lengthy videos by taking into account the audio, text and visual frames to create concise, informative summaries. The research mainly deals with educational videos where the aim is to provide short summaries that cover most of the information presented in a video to boost easier and quick way for skimming seminar, research talks.



Information Extraction from Web Tables

Graduate course, Bielefeld University, 2018

The task of the project is to i) develop and implement these higher level tasks by building on the basic tasks, thus to realize table understanding, ii) execute these tasks on real data, iii) extract information from tables and extend a knowledge base, and iv) evaluate the correctness of the tasks and the extracted information. Possibly, v) further basic tasks need to be implemented or existing basic tasks need to be improved.

Statistical Natural Language Processing

Graduate course, Bielefeld University, 2018

This course involves the creation of effective systems for the processing of text by means of statistical methods. There will be significant challenge in integrating these components into a scalable system that can handle the large amount of data required to obtain high accuracy. In addition to the technical challenges in this course, the students will be required to read recent research papers related to the task and integrate these results into their solutions. Between 2014-2018 (8 semesters).

Proseminar Visual Analytics

Undergraduate course, Hannover University, 2020

This seminars involves the understanding basic ideas around visual analytics and computational multimodal systems. The students are present a chosen publication and write a technical report about it.