I am an independent research group leader (Image & Video Analysis) at the Technical University of Darmstadt, as well as affiliated with the Hessian Center for Artificial Intelligence (hessian.AI). I recently got the renowned Emmy Noether Programme (ENP) fund of the German Research Foundation (DFG) supporting my research group. The focus of my research is on developing efficient, robust, and understandable methods and algorithms for image and video analysis. Before starting my own group, I was a postdoctoral researcher in the Visual Inference Lab of Prof. Stefan Roth. Prior to joining TU Darmstadt, I was a postdoctoral researcher at the Media Technology Center at ETH Zurich working on augmented reality. I obtained my doctoral degree from ETH Zurich, advised by Prof. Dr. Markus Gross and in collaboration with Disney Research Zurich. In my doctoral thesis, awarded with the ETH Medal, I developed novel methods for motion representation and video frame interpolation.
I also head the Efficient Video Analysis (EVA) project group at hessian.AI, researching novel AI methods for visual data with a focus on developing efficient, robust, and controllable methods and algorithms that can learn from limited data by exploiting low-level perception and high-level reasoning. EVA has been created as a DEPTH research group within the HMWK-funded cluster project “The Third Wave of Artificial Intelligence (3AI)”. The cluster project is embedded into hessian.AI, the Hessian Centre for Artificial Intelligence, with its mission to “understand the interplay of AI algorithms, AI systems, and synergies between artificial and natural intelligence to provide the foundation for AI transformation”.
News
- 10.2024 [Hiring] I am accepting applications for a open PhD position through ELLIS: Link to application instructions
- 09.2024 Our paper "Benchmarking the Attribution Quality of Vision Models" has been accepted at NeurIPS'24 Datasets and Benchmarks Track.
- 04.2024 Our workshop on Explainable Computer Vision: Where are We and Where are We Going? got accepted at ECCV 2024.
- 01.2024 I got accepted into the prestigious Emmy Noether Programme. More details soon.
- 01.2024 I got appointed as independent research group leader at TU Darmstadt.
- 08.2023 Our paper on evaluating explainable AI methods has been accepted at ICCV'23 as oral presentation.
- 07.2023 I am looking forward to attend and present our work on "Unsupervised Representation Learning from Videos" and "Accelerating and Assessing Explainable AI Methods in Computer Vision" at the 2nd ELLIS unConference in Paris.
- 04.2023 Our paper "Entropy-driven Unsupervised Keypoint Representation Learning in Videos" has been accepted at ICML'23 .
Publications
Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic ImagesK. Singh, T. Navaratnam, J. Holmer, S. Schaub-Meyer, S. Roth 2024 CVPR Workshop: SyntaGen-Harnessing Generative Models for Synthetic Visual Datasets (Best Paper Award) |
Boosting Unsupervised Semantic Segmentation with Principal Mask ProposalsO. Hahn, N. Araslanov, S. Schaub-Meyer, S. Roth 2024 Accepted to TMLR |
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI MethodsR. Hesse, S. Schaub-Meyer, S. Roth 2023 ICCV (Oral Presentation) |
Entropy-driven Unsupervised Keypoint Representation Learning in VideosA. Younes, S. Schaub-Meyer, G. Chalvatzaki 2023 ICML |
Content-Adaptive Downsampling in Convolutional Neural NetworksR. Hesse, S. Schaub-Meyer, S. Roth 2023 CVPR Workshop: Efficient Deep Learning for Computer Vision |
Efficient Feature Extraction for High-resolution Video Frame InterpolationM. Nottebaum, S. Roth, S. Schaub-Meyer 2022 BMVC |
$S^2$-Flow: Joint Semantic and Style Editing of Facial ImagesK. Singh, S. Schaub-Meyer, S. Roth 2022 BMVC |
Fast Axiomatic Attribution for Neural NetworksR. Hesse, S. Schaub-Meyer, S. Roth 2021 NeurIPS |
Dense Unsupervised Learning for Video SegmentationN. Araslanov, S. Schaub-Meyer, S. Roth 2021 NeurIPS |
Style Transfer for Keypoint Matching Under Adverse ConditionsA. Uzpak, A. Djelouah, S. Schaub-Meyer |
Neural inter-frame compression for video codingA. Djelouah, J. Campos, S. Schaub-Meyer, C. Schroers 2019 ICCV |
Deep Video Color PropagationS. Meyer, V. Cornillère, A. Djelouah, C. Schroers, M. Gross 2018 BMVC |
PhaseNet for Video Frame InterpolationS. Meyer, A. Djelouah, B. McWilliams, A. Sorkine-Hornung, M. Gross, C. Schroers 2018 CVPR |
Phase-Based Modification Transfer for VideoS. Meyer, A. Sorkine-Hornung, M. Gross |
Phase-based Frame Interpolation for VideoS. Meyer, O. Wang, H. Zimmer, M. Grosse, A. Sorkine-Hornung 2015 CVPR (Oral Presentation) |