Stefan Roth 0001
83 publications
9 venues
H Index 49
Affiliation
TU Darmstadt, Department of Computer Science, GermanyBrown University, Dept. of Computer Science, Providence, RI, USA
University of Mannheim, Dept. of Mathematics and Computer Science, Germany
Links
DBLPGoogle Scholar
ORCID- http://www.visinf.tu-darmstadt.de/team_members/sroth/sroth.en.jsp
- https://openreview.net/profile?id=~Stefan_Roth1
- https://dl.acm.org/profile/81330497485
- https://mathscinet.ams.org/mathscinet/MRAuthorID/969973
- https://mathgenealogy.org/id.php?id=211122
- https://en.wikipedia.org/wiki/Stefan_Roth
- https://www.wikidata.org/entity/Q76650232
- https://id.loc.gov/authorities/names/nb2019004351
- https://d-nb.info/gnd/111482747
- https://ieeexplore.ieee.org/author/37282906600
| Name | Venue | Year | citations |
|---|---|---|---|
Scene-Centric Unsupervised Panoptic Segmentation.
|
CVPR | 2025 | 5 |
| Editorial: Introduction to the Special Section on Best of CVPR'2022.
|
TPAMI | 2025 | 0 |
| Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model.
|
IROS | 2025 | 0 |
| GLASS: Guided Latent Slot Diffusion for Object-Centric Learning.
|
CVPR | 2025 | 0 |
| Benchmarking the Attribution Quality of Vision Models.
|
NIPS/NeurIPS | 2024 | 5 |
| Adapters Strike Back.
|
CVPR | 2024 | 17 |
| FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods.
|
ICCV | 2023 | 49 |
| Vision Relation Transformer for Unbiased Scene Graph Generation.
|
ICCV | 2023 | 26 |
| DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring.
|
TPAMI | 2022 | 0 |
| Self-Supervised Augmentation Consistency for Adapting Semantic Segmentation.
|
CVPR | 2021 | 270 |
| PixelPyramids: Exact Inference Models from Lossless Image Pyramids.
|
ICCV | 2021 | 2 |
| Self-Supervised Multi-Frame Monocular Scene Flow.
|
CVPR | 2021 | 58 |
| Fast Axiomatic Attribution for Neural Networks.
|
NIPS/NeurIPS | 2021 | 49 |
| Dense Unsupervised Learning for Video Segmentation.
|
NIPS/NeurIPS | 2021 | 37 |
| Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring.
|
CVPR | 2021 | 37 |
| Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning.
|
IROS | 2020 | 12 |
| Diverse Image Captioning with Context-Object Split Latent Spaces.
|
NIPS/NeurIPS | 2020 | 46 |
| Single-Stage Semantic Segmentation From Image Labels.
|
CVPR | 2020 | 319 |
| Self-Supervised Monocular Scene Flow Estimation.
|
CVPR | 2020 | 117 |
| Probabilistic Pixel-Adaptive Refinement Networks.
|
CVPR | 2020 | 18 |
| Normalizing Flows With Multi-Scale Autoregressive Priors.
|
CVPR | 2020 | 19 |
| Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings.
|
ICLR | 2020 | 38 |
| Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving.
|
ICRA | 2020 | 0 |
| Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring.
|
NIPS/NeurIPS | 2020 | 0 |
| Actor-Critic Instance Segmentation.
|
CVPR | 2019 | 19 |
| Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation.
|
CVPR | 2019 | 293 |
| Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving.
|
IROS | 2019 | 66 |
| Lightweight Probabilistic Deep Networks.
|
CVPR | 2018 | 0 |
| Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers.
|
CVPR | 2018 | 143 |
| Detail-Preserving Pooling in Deep Networks.
|
CVPR | 2018 | 105 |
| Neural Nearest Neighbors Networks.
|
NIPS/NeurIPS | 2018 | 368 |
| Stochastic Variational Inference With Gradient Linearization.
|
CVPR | 2018 | 2 |
| Normalized Blind Deconvolution.
|
ECCV | 2018 | 42 |
| UnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss.
|
AAAI | 2018 | 0 |
| Benchmarking Denoising Algorithms with Real Photographs.
|
CVPR | 2017 | 663 |
| ProbFlow: Joint Optical Flow and Uncertainty Estimation.
|
ICCV | 2017 | 65 |
| Noise-Blind Image Deblurring.
|
CVPR | 2017 | 43 |
| MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation.
|
ICCV | 2017 | 101 |
| Tree-Structured Models for Efficient Multi-Cue Scene Labeling.
|
TPAMI | 2017 | 14 |
| The Cityscapes Dataset for Semantic Urban Scene Understanding.
|
CVPR | 2016 | 13131 |
| Multi-Target Tracking by Discrete-Continuous Energy Minimization.
|
TPAMI | 2016 | 183 |
| Playing for Data: Ground Truth from Computer Games.
|
ECCV | 2016 | 2197 |
| Stereo Video Deblurring.
|
ECCV | 2016 | 51 |
| Parametric Object Motion from Blur.
|
CVPR | 2016 | 23 |
| Cascades of Regression Tree Fields for Image Restoration.
|
TPAMI | 2016 | 0 |
| Discriminative shape from shading in uncalibrated illumination.
|
CVPR | 2015 | 58 |
| Registering Images to Untextured Geometry Using Average Shading Gradients.
|
ICCV | 2015 | 11 |
| Continuous Energy Minimization for Multitarget Tracking.
|
TPAMI | 2014 | 581 |
| Shrinkage Fields for Effective Image Restoration.
|
CVPR | 2014 | 549 |
| Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding.
|
ECCV | 2014 | 65 |
| View-Consistent 3D Scene Flow Estimation over Multiple Frames.
|
ECCV | 2014 | 69 |
| Piecewise Rigid Scene Flow.
|
ICCV | 2013 | 243 |
| Discriminative Non-blind Deblurring.
|
CVPR | 2013 | 6 |
| Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes.
|
TPAMI | 2013 | 109 |
| Learning People Detectors for Tracking in Crowded Scenes.
|
ICCV | 2013 | 95 |
| Detection- and Trajectory-Level Exclusion in Multiple Object Tracking.
|
CVPR | 2013 | 215 |
| Discrete-continuous optimization for multi-target tracking.
|
CVPR | 2012 | 373 |
| Learning rotation-aware features: From invariant priors to equivariant descriptors.
|
CVPR | 2012 | 100 |
| 3D scene flow estimation with a rigid motion prior.
|
ICCV | 2011 | 110 |
| Bayesian deblurring with integrated noise estimation.
|
CVPR | 2011 | 78 |
| Connecting non-quadratic variational models and MRFs.
|
CVPR | 2011 | 2 |
| Monocular 3D scene understanding with explicit occlusion reasoning.
|
CVPR | 2011 | 95 |
| Vision based victim detection from unmanned aerial vehicles.
|
IROS | 2010 | 116 |
| Fusion Moves for Markov Random Field Optimization.
|
TPAMI | 2010 | 248 |
| Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes.
|
ECCV | 2010 | 91 |
| A generative perspective on MRFs in low-level vision.
|
CVPR | 2010 | 140 |
| Secrets of optical flow estimation and their principles.
|
CVPR | 2010 | 1621 |
| Automatic discovery of meaningful object parts with latent CRFs.
|
CVPR | 2010 | 54 |
| Monocular 3D pose estimation and tracking by detection.
|
CVPR | 2010 | 588 |
| Pictorial structures revisited: People detection and articulated pose estimation.
|
CVPR | 2009 | 938 |
| Discriminative structure learning of hierarchical representations for object detection.
|
CVPR | 2009 | 71 |
| Learning Optical Flow.
|
ECCV | 2008 | 297 |
| FusionFlow: Discrete-continuous optimization for optical flow estimation.
|
CVPR | 2008 | 182 |
| People-tracking-by-detection and people-detection-by-tracking.
|
CVPR | 2008 | 998 |
| A Database and Evaluation Methodology for Optical Flow.
|
ICCV | 2007 | 2886 |
| Steerable Random Fields.
|
ICCV | 2007 | 64 |
| Specular Flow and the Recovery of Surface Structure.
|
CVPR | 2006 | 96 |
| Efficient Belief Propagation with Learned Higher-Order Markov Random Fields.
|
ECCV | 2006 | 225 |
| Modeling Neural Population Spiking Activity with Gibbs Distributions.
|
NIPS/NeurIPS | 2005 | 11 |
| Fields of Experts: A Framework for Learning Image Priors.
|
CVPR | 2005 | 1229 |
| On the Spatial Statistics of Optical Flow.
|
ICCV | 2005 | 110 |
| Tracking Loose-Limbed People.
|
CVPR | 2004 | 461 |
| Gibbs Likelihoods for Bayesian Tracking.
|
CVPR | 2004 | 39 |