General

This page contains all relevant information regarding the Seminar Vision and Language (Prof. Dr. Radu Timofte,  Prof. Dr. Goran Glavaš ) in the Winter  Semester of 2025.

For WueStudy related questions and other administrative things please check the video tutorials from:

https://www.uni-wuerzburg.de/en/wuestudy/help/video-tutorials/

Description

The topics of the seminar will cover the many research topics and challenges about the vision+language field, namely how we can model the task for deep learning methods, what tasks and datasets people have created, and how we can evaluate our models to measure how well they work. In this seminar, we review, explore and debate these challenges based on recent research at the intersection of Machine Learning, Computer Vision, and Natural Language Processing.

Each participant will be assigned one topic, including but not limited to those listed below. 

Each participant is expected to prepare a written review report covering the state-of-the-art on the particular topic and a corresponding oral presentation. 

At the same time, each participant is expected to interact, read and comment on the reports provided and presented by the other participants.

Each participant will get skills in critical analysis, scientific discourse, and preparation, writing, and presentation on a research topic. Moreover, the participants will get acquainted with state-of-the-art vision+language research.

Objectives

• Get skills on:
  - critical analysis
  - scientific discourse
  - preparation (literature review), report writing (latex), and presentation (power point) on a vision+language topic.

Prerequisites

• Basic concepts of mathematical analysis and linear algebra.
• Basic knowledge of machine learning and deep learning is helpful.
• The course language is English.

Read the course slide for detailed specification of what is to do for the seminar!

Templates

Dates and Locations

• Kick-off Meeting (TBA)
• Until the next week: topic assignment finalized
• IMPORTANT: Registration deadline for seminar is *very* early. Don't miss it.
• 09.01.2026: Deadline for Report Draft
• End of January/ Start of February: Presentations in Blocks (depends on course size, details TBA)
• 06.02.2026: Deadline for Final Report, Slides, and Reviews

Contact:

For general questions related to the course, please use the Moodle forum General and only use mail for individual problems or questions.

List of topics and papers (the students can have own suggestions for topics):

1. CLIP: Cross-modal embeddings (for retrieval, classification & more) https://arxiv.org/abs/2103.00020 

2. Making Large Language Models (like ChatGPT) multimodal https://arxiv.org/abs/2301.12597 

3. Not just English - Multilingual models and benchmarks https://arxiv.org/abs/2201.11732

4. Text-Conditional image generation https://arxiv.org/abs/2204.06125

5. Working with text-rich images (figures, websites, graphs, …) https://arxiv.org/abs/2203.10244 https://arxiv.org/abs/2307.02499
   

6. Detecting and dealing with visual hallucinations in image captioning and beyond https://aclanthology.org/D18-1437/ https://arxiv.org/abs/2210.07688