Home | Publications | Kon25a

Transformers for Efficient and High-Level Image and Video Understanding

MCML Authors

Abstract

This dissertation develops efficient Transformer-based architectures for high-level image and video understanding, addressing the computational challenges of attention while adapting Transformers to complex vision tasks. It introduces novel methods for scene graph generation, visual question answering, out-of-distribution detection, and video instance segmentation, achieving state-of-the-art performance with improved efficiency and interpretability. (Shortened.)

phdthesis Kon25a


Dissertation

LMU München. Oct. 2025

Authors

R. Koner

Links

DOI

Research Area

 A3 | Computational Models

BibTeXKey: Kon25a

Back to Top