Home  | News

27.02.2025

Tiny logo
Teaser image to MCML at WACV 2025

Eight Accepted Papers

IEEE/CVF Winter Conference on Applications of Computer Vision, Tucson, AZ, USA, Feb 28-Mar 04, 2025

We are happy to announce that MCML researchers have contributed a total of 8 papers to WACV 2025. Congrats to our researchers!

Main Track (8 papers)

R. Amoroso • G. ZhangR. Koner • L. Baraldi • R. Cucchiara • V. Tresp
Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI

A. H. Berger • L. Lux • S. Shit • I. Ezhov • G. KaissisM. J. MentenD. Rückert • J. C. Paetzold
Cross-Domain and Cross-Dimension Learning for Image-to-Graph Transformers.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI

S. Chen • Z. Han • B. He • J. Liu • M. Buckley • Y. Qin • P. Torr • V. Tresp • J. Gu
Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI URL

F. Fundel • J. SchusterbauerV. T. HuB. Ommer
Distillation of Diffusion Features for Semantic Correspondence.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI

F. Hofherr • B. Haefner • D. Cremers
On Neural BRDFs: A Thorough Comparison of State-of-the-Art Approaches.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. Oral Presentation. DOI

Y. LiM. Ghahremani • Y. Wally • C. Wachinger
DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI

O. Wysocki • Y. Tan • T. Froech • Y. XiaM. Wysocki • L. Hoegner • D. Cremers • C. Holst
ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI GitHub

Y. ZhangH. Chen • A. Frikha • Y. Yang • D. Krompass • G. Zhang • J. Gu • V. Tresp
CL-Cross VQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering.
WACV 2025 - IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025. DOI

#research #top-tier-work #cremers #kaissis #menten #navab #ommer #rueckert #tresp #wachinger
Subscribe to RSS News feed

Related

Link to Fabian Theis Featured in Handelsblatt on the Future of AI in Precision Medicine

16.12.2025

Fabian Theis Featured in Handelsblatt on the Future of AI in Precision Medicine

MCML PI Fabian Theis discusses AI-driven precision medicine and its growing impact on individualized healthcare and biomedical research.

Link to Gitta Kutyniok Featured in VDI Nachrichten on AI Ethics

16.12.2025

Gitta Kutyniok Featured in VDI Nachrichten on AI Ethics

Gitta Kutyniok discusses measurable criteria for ethical AI, promoting safe and responsible autonomous decision-making.

Link to Hinrich Schütze Featured in WirtschaftsWoche on Innovative AI Approaches

16.12.2025

Hinrich Schütze Featured in WirtschaftsWoche on Innovative AI Approaches

Hinrich Schütze discusses Giotto.ai’s efficient AI models, highlighting memory separation and context-aware decoding to improve robustness.

Link to Xiaoxiang Zhu Featured in Focus Online on Global 3D Building Atlas

16.12.2025

Xiaoxiang Zhu Featured in Focus Online on Global 3D Building Atlas

Xiaoxiang Zhu maps 2.75B buildings in 3D, revealing global urbanization, housing, and social inequalities using AI.

Link to From Sitting Dog to Standing: A New Way to Morph 3D Shapes

11.12.2025

From Sitting Dog to Standing: A New Way to Morph 3D Shapes

ICLR 2025 work by Lu Sang and Daniel Cremers in collaboration with U Bonn enables smooth, physics-aware 3D shape deformation from point clouds.

Back to Top