Publication Alert: Smart Eyes, FlowBench and Amending Inherent Interpretability
Three Publications from the DFG Research Unit “Learning to Sense” accepted by Shashank Agnihotri (Group of Margret Keuper at U Mannheim) – Congratulations and outstanding work!
- Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging by Nicolas Poggi, Shashank Agnihotri, and Margret Keuper has been accepted at ICCV Workshop On Computer Vision for Developing Countries, 2025.
- FlowBench: Benchmarking Optical Flow Estimation Methods for Reliability and Generalization by Shashank Agnihotri, Julian Caspary, Luca Schwarz, Xinyan G., Jenny Schmalfuss, Andrés Bruhn and Margret Keuper has been accepted at Transactions on Machine Learning Research, 2025.
- AIM: Amending Inherent Interpretability via Self-Supervised Masking by Eyad Alshami, Shashank Agnihotri, Bernt Schiele, and Margret Keuper has been accepted at the International Conference on Computer Vision, IEEE, 2025.
