SR
Stefan Roth
cs.CVcs.LGcs.ROcs.AIcs.CLstat.ML20 S proteasomeAlgorithmscancercs.GR
On Valency
published · living versionsW_uwb2dfzx·v1 · currentpublished
The Cityscapes Dataset for Semantic Urban Scene Understanding
with Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld +4
1 version
Preprints & journals
73 papers in the corpus · 2010–2026Importance-Aware Low-Rank Distillation of Diffusion Transformers2609.04646v1 · Denis Zavadski, Sebastian Heid, Damjan Kalsan et al.2026 · 0 citationsarXiv
ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views2608.28895v1 · Giuseppe Stracquadanio, Kevin Raj, Julia Grabinski et al.2026 · 0 citationsarXiv
Removing Cost Volumes from Optical Flow Estimators2510.13317v1 · Simon Kiefhaber, Stefan Roth, Simone Schaub-Meyer2025 · 2 citationsarXiv
A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation2510.11567v2 · Damjan Kalsan, Denis Zavadski, Tim Kuchler et al.2025 · 0 citationsPattern Recognition: 28th International Conference, ICPR 2026, Lyon, France, August 17-22, 2026, Proceedings, Part I, Pages 305-319
Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery2509.02545v1 · Xinrui Gong, Oliver Hahn, Christoph Reich et al.2025 · 0 citationsarXiv
Activation Subspaces for Out-of-Distribution Detection2508.21695v1 · Bar\is Zongur, Robin Hesse, Stefan Roth2025 · 2 citationsarXiv
Disentangling Polysemantic Channels in Convolutional Neural Networks2504.12939v1 · Robin Hesse, Jonas Fischer, Simone Schaub-Meyer et al.2025 · 3 citationsarXiv
DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning2408.14584v2 · Tobias Lingenberg, Markus Reuter, Gopika Sudhakaran et al.2024 · 2 citationsarXiv
GLASS: Guided Latent Slot Diffusion for Object-Centric Learning2407.17929v2 · Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth2024 · 2 citationsarXiv
Adapters Strike Back2406.06820v1 · Jan-Martin O. Steitz, Stefan Roth2024 · 15 citationsarXiv
Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images2405.20469v2 · Krishnakant Singh, Thanush Navaratnam, Jannik Holmer et al.2024 · 31 citationsarXiv
Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals2404.16818v2 · Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer et al.2024 · 1 citationarXiv
Pixel State Value Network for Combined Prediction and Planning in Interactive Environments2310.07706v1 · Sascha Rosbach, Stefan M. Leupold, Simon Gro\ssjohann et al.2023 · 0 citationsarXiv
Vision Relation Transformer for Unbiased Scene Graph Generation2308.09472v1 · Gopika Sudhakaran, Devendra Singh Dhami, Kristian Kersting et al.2023 · 26 citationsarXiv
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods2308.06248v1 · Robin Hesse, Simone Schaub-Meyer, Stefan Roth2023 · 22 citationsarXiv
Content-Adaptive Downsampling in Convolutional Neural Networks2305.09504v1 · Robin Hesse, Simone Schaub-Meyer, Stefan Roth2023 · 34 citationsarXiv
Efficient Feature Extraction for High-resolution Video Frame Interpolation2211.14005v1 · Moritz Nottebaum, Stefan Roth, Simone Schaub-Meyer2022 · 2 citationsarXiv
-Flow: Joint Semantic and Style Editing of Facial Images2211.12209v1 · Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth2022 · 0 citationsarXiv
Diverse Image Captioning with Grounded Style2205.01813v1 · Franz Klein, Shweta Mahajan, Stefan Roth2022 · 6 citationsIn Proceedings of the German Conference on Pattern Recognition (GCPR), Ed. by C. Bauckhage, J. Gall, and A. G. Schwing, Vol. 13024, Lecture Notes in Computer Science, Springer, 2021, pp. 421-436
Fast Axiomatic Attribution for Neural Networks2111.07668v1 · Robin Hesse, Simone Schaub-Meyer, Stefan Roth2021 · 15 citationsarXiv
Dense Unsupervised Learning for Video Segmentation2111.06265v1 · Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth2021 · 15 citationsarXiv
PixelPyramids: Exact Inference Models from Lossless Image Pyramids2110.08787v1 · Shweta Mahajan, Stefan Roth2021 · 2 citationsarXiv
xGQA: Cross-Lingual Visual Question Answering2109.06082v2 · Jonas Pfeiffer, Gregor Geigle, Aishwarya Kamath et al.2021 · 46 citationsarXiv
TxT: Crossmodal End-to-End Learning with Transformers2109.04422v1 · Jan-Martin O. Steitz, Jonas Pfeiffer, Iryna Gurevych et al.2021 · 1 citationarXiv
Self-Supervised Multi-Frame Monocular Scene Flow2105.02216v1 · Junhwa Hur, Stefan Roth2021 · 60 citationsarXiv
Self-supervised Augmentation Consistency for Adapting Semantic Segmentation2105.00097v1 · Nikita Araslanov, Stefan Roth2021 · 246 citationsarXiv
DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring2103.09962v2 · Jiangxin Dong, Stefan Roth, Bernt Schiele2021 · 92 citationsarXiv
Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise2103.08497v2 · Jannik Schmitt, Stefan Roth2021 · 4 citationsarXiv
Diverse Image Captioning with Context-Object Split Latent Spaces2011.00966v1 · Shweta Mahajan, Stefan Roth2020 · 27 citationsarXiv
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking2010.07548v2 · Patrick Dendorfer, Aljosa Osep, Anton Milan et al.2020 · 371 citationsarXiv
Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning2007.05798v2 · Sascha Rosbach, Xing Li, Simon Gro\ssjohann et al.2020 · 14 citations2020 IEEE/RSJ Int. Conf. on Intelligent Robots and Syst. (IROS), Las Vegas, USA, 2020, pp. 5187-5193
LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery2005.14264v1 · Wentong Liao, Xiang Chen, Jingfeng Yang et al.2020 · 13 citationsarXiv
Single-Stage Semantic Segmentation from Image Labels2005.08104v1 · Nikita Araslanov, Stefan Roth2020 · 294 citationsarXiv
Normalizing Flows with Multi-Scale Autoregressive Priors2004.03891v1 · Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz et al.2020 · 11 citationsarXiv
Self-Supervised Monocular Scene Flow Estimation2004.04143v2 · Junhwa Hur, Stefan Roth2020 · 123 citationsarXiv
Optical Flow Estimation in the Deep Learning Age2004.02853v1 · Junhwa Hur, Stefan Roth2020 · 51 citationsarXiv
Probabilistic Pixel-Adaptive Refinement Networks2003.14407v1 · Anne S. Wannenwetsch, Stefan Roth2020 · 14 citationsarXiv
MOT20: A benchmark for multi object tracking in crowded scenes2003.09003v1 · Patrick Dendorfer, Hamid Rezatofighi, Anton Milan et al.2020 · 497 citationsarXiv
Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings2002.06661v1 · Shweta Mahajan, Iryna Gurevych, Stefan Roth2020 · 14 citationsarXiv
Cell-Based Optimization of Covalent Reversible Ketoamide Inhibitors Bridging the Unprimed to the Primed Site of the Proteasome β5 Subunit.31675179 · Stubba, Daniel, Bensinger, Dennis, Steinbacher, Janika et al.2020 · 10 citationsChemMedChem. 2019;14(23):2005-2022
Deep Video Deblurring: The Devil is in the Details1909.12196v1 · Jochen Gast, Stefan Roth2019 · 27 citationsarXiv
Markov Decision Process for Video Generation1909.12400v1 · Vladyslav Yushchenko, Nikita Araslanov, Stefan Roth2019 · 10 citationsarXiv
Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings1909.06635v1 · Shweta Mahajan, Teresa Botschen, Iryna Gurevych et al.2019 · 9 citationsarXiv
Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice1909.03677v1 · Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler et al.2019 · 2 citationsarXiv
CVPR19 Tracking and Detection Challenge: How crowded can it get?1906.04567v1 · Patrick Dendorfer, Hamid Rezatofighi, Anton Milan et al.2019 · 63 citationsarXiv
Actor-Critic Instance Segmentation1904.05126v1 · Nikita Araslanov, Constantin Rothkopf, Stefan Roth2019 · 20 citationsarXiv
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation1904.05290v1 · Junhwa Hur, Stefan Roth2019 · 298 citationsarXiv
Neural Nearest Neighbors Networks1810.12575v1 · Tobias Plotz, Stefan Roth2018 · 44 citationsarXiv
Multi-view X-ray R-CNN1810.02344v1 · Jan-Martin O. Steitz, Faraz Saeedan, Stefan Roth2018 · 30 citationsarXiv
Lightweight Probabilistic Deep Networks1805.11327v1 · Jochen Gast, Stefan Roth2018 · 176 citationsarXiv
Career total: 171 works. 73 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.