Stefan Roth

Orcid: 0000-0001-9002-9832

Affiliations:
  • TU Darmstadt, Department of Computer Science, Germany
  • Brown University, Dept. of Computer Science, Providence, RI, USA
  • University of Mannheim, Dept. of Mathematics and Computer Science, Germany


According to our database1, Stefan Roth authored at least 143 papers between 2001 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
DIAGen: Diverse Image Augmentation with Generative Models.
CoRR, 2024

Guided Latent Slot Diffusion for Object-Centric Learning.
CoRR, 2024

Benchmarking the Attribution Quality of Vision Models.
CoRR, 2024

Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals.
CoRR, 2024

Adapters Strike Back.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

A Perspective on Deep Vision Performance with Standard Image and Video Codecs.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Semantic Self-adaptation: Enhancing Generalization with a Single Sample.
Trans. Mach. Learn. Res., 2023

Pixel State Value Network for Combined Prediction and Planning in Interactive Environments.
CoRR, 2023

Vision Relation Transformer for Unbiased Scene Graph Generation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Content-Adaptive Downsampling in Convolutional Neural Networks.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

S<sup>2</sup>-Flow: Joint Semantic and Style Editing of Facial Images.
CoRR, 2022

$S^2$-Flow: Joint Semantic and Style Editing of Facial Images.
Proceedings of the 33rd British Machine Vision Conference 2022, 2022

Efficient Feature Extraction for High-resolution Video Frame Interpolation.
Proceedings of the 33rd British Machine Vision Conference 2022, 2022

xGQA: Cross-Lingual Visual Question Answering.
Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022, 2022

2021
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking.
Int. J. Comput. Vis., 2021

Boosting Monocular Depth with Panoptic Segmentation Maps.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021

Fast Axiomatic Attribution for Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021


Dense Unsupervised Learning for Video Segmentation.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

PixelPyramids: Exact Inference Models from Lossless Image Pyramids.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

TxT: Crossmodal End-to-End Learning with Transformers.
Proceedings of the Pattern Recognition - 43rd DAGM German Conference, DAGM GCPR 2021, Bonn, Germany, September 28, 2021

Sampling-Free Variational Inference for Neural Networks with Multiplicative Activation Noise.
Proceedings of the Pattern Recognition - 43rd DAGM German Conference, DAGM GCPR 2021, Bonn, Germany, September 28, 2021

Diverse Image Captioning with Grounded Style.
Proceedings of the Pattern Recognition - 43rd DAGM German Conference, DAGM GCPR 2021, Bonn, Germany, September 28, 2021

Self-Supervised Multi-Frame Monocular Scene Flow.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Self-Supervised Augmentation Consistency for Adapting Semantic Segmentation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020
LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery.
CoRR, 2020

Optical Flow Estimation in the Deep Learning Age.
CoRR, 2020

MOT20: A benchmark for multi object tracking in crowded scenes.
CoRR, 2020

Diverse Image Captioning with Context-Object Split Latent Spaces.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings.
Proceedings of the 8th International Conference on Learning Representations, 2020

Probabilistic Pixel-Adaptive Refinement Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Self-Supervised Monocular Scene Flow Estimation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Normalizing Flows With Multi-Scale Autoregressive Priors.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Single-Stage Semantic Segmentation From Image Labels.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
CVPR19 Tracking and Detection Challenge: How crowded can it get?
CoRR, 2019

Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving.
Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019

Markov Decision Process for Video Generation.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Deep Video Deblurring: The Devil is in the Details.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice.
Proceedings of the Pattern Recognition, 2019

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Actor-Critic Instance Segmentation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018
A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning.
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, 2018

Neural Nearest Neighbors Networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Multimodal Frame Identification with Multilingual Evaluation.
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018

Normalized Blind Deconvolution.
Proceedings of the Computer Vision - ECCV 2018, 2018

Multi-view X-Ray R-CNN.
Proceedings of the Pattern Recognition - 40th German Conference, 2018

Detail-Preserving Pooling in Deep Networks.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Stochastic Variational Inference With Gradient Linearization.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Lightweight Probabilistic Deep Networks.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

UnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
Tree-Structured Models for Efficient Multi-Cue Scene Labeling.
IEEE Trans. Pattern Anal. Mach. Intell., 2017

The Stixel World: A medium-level representation of traffic scenes.
Image Vis. Comput., 2017

Automatic Registration of Images to Untextured Geometry Using Average Shading Gradients.
Int. J. Comput. Vis., 2017

Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking.
CoRR, 2017

ProbFlow: Joint Optical Flow and Uncertainty Estimation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation.
Proceedings of the IEEE International Conference on Computer Vision, 2017

Robust Multi-image HDR Reconstruction for the Modulo Camera.
Proceedings of the Pattern Recognition - 39th German Conference, 2017

Benchmarking Denoising Algorithms with Real Photographs.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Noise-Blind Image Deblurring.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Interactive Data Analytics for the Humanities.
Proceedings of the Computational Linguistics and Intelligent Text Processing, 2017

2016
Cascades of Regression Tree Fields for Image Restoration.
IEEE Trans. Pattern Anal. Mach. Intell., 2016

Multi-Target Tracking by Discrete-Continuous Energy Minimization.
IEEE Trans. Pattern Anal. Mach. Intell., 2016

MOT16: A Benchmark for Multi-Object Tracking.
CoRR, 2016

Harvesting Dynamic 3D Worlds from Commodity Sensor Clouds.
Proceedings of the GCH 2016 - Eurographics Workshop on Graphics and Cultural Heritage, 2016

Semantic Stixels: Depth is not enough.
Proceedings of the 2016 IEEE Intelligent Vehicles Symposium, 2016

Stereo Video Deblurring.
Proceedings of the Computer Vision - ECCV 2016, 2016

Playing for Data: Ground Truth from Computer Games.
Proceedings of the Computer Vision - ECCV 2016, 2016

Joint Optical Flow and Temporally Consistent Semantic Segmentation.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

Parametric Object Motion from Blur.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

The Cityscapes Dataset for Semantic Urban Scene Understanding.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

2015
3D Scene Flow Estimation with a Piecewise Rigid Scene Model.
Int. J. Comput. Vis., 2015

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking.
CoRR, 2015

A discriminative approach to perspective shape from shading in uncalibrated illumination.
Comput. Graph., 2015

Interleaved Regression Tree Field Cascades for Blind Image Deconvolution.
Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, 2015

Registering Images to Untextured Geometry Using Average Shading Gradients.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015

Discriminative shape from shading in uncalibrated illumination.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

2014
Continuous Energy Minimization for Multitarget Tracking.
IEEE Trans. Pattern Anal. Mach. Intell., 2014

A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them.
Int. J. Comput. Vis., 2014

Texture Synthesis: From Convolutional RBMs to Efficient Deterministic Algorithms.
Proceedings of the Structural, Syntactic, and Statistical Pattern Recognition, 2014

Localized Image Blur Removal through Non-parametric Kernel Estimation.
Proceedings of the 22nd International Conference on Pattern Recognition, 2014

View-Consistent 3D Scene Flow Estimation over Multiple Frames.
Proceedings of the Computer Vision - ECCV 2014, 2014

Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding.
Proceedings of the Computer Vision - ECCV 2014, 2014

Object-Level Priors for Stixel Generation.
Proceedings of the Pattern Recognition - 36th German Conference, 2014

Shrinkage Fields for Effective Image Restoration.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Privacy Preserving Multi-target Tracking.
Proceedings of the Computer Vision - ACCV 2014 Workshops, 2014

2013
Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes.
IEEE Trans. Pattern Anal. Mach. Intell., 2013

Piecewise Rigid Scene Flow.
Proceedings of the IEEE International Conference on Computer Vision, 2013

Learning People Detectors for Tracking in Crowded Scenes.
Proceedings of the IEEE International Conference on Computer Vision, 2013

An Evaluation of Data Costs for Optical Flow.
Proceedings of the Pattern Recognition - 35th German Conference, 2013

Efficient Multi-cue Scene Segmentation.
Proceedings of the Pattern Recognition - 35th German Conference, 2013

Discriminative Non-blind Deblurring.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

Challenges of Ground Truth Evaluation of Multi-target Tracking.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013

Detection- and Trajectory-Level Exclusion in Multiple Object Tracking.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Discriminative Appearance Models for Pictorial Structures.
Int. J. Comput. Vis., 2012

Mean Field for Continuous High-Order MRFs.
Proceedings of the Pattern Recognition, 2012

How Well Do Filter-Based MRFs Model Natural Images?
Proceedings of the Pattern Recognition, 2012

Object Detection in Multi-view X-Ray Images.
Proceedings of the Pattern Recognition, 2012

Pottics - The Potts Topic Model for Semantic Image Segmentation.
Proceedings of the Pattern Recognition, 2012

Learning rotation-aware features: From invariant priors to equivariant descriptors.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

Discrete-continuous optimization for multi-target tracking.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

2011
A Database and Evaluation Methodology for Optical Flow.
Int. J. Comput. Vis., 2011

An analytical formulation of global occlusion reasoning for multi-target tracking.
Proceedings of the IEEE International Conference on Computer Vision Workshops, 2011

3D scene flow estimation with a rigid motion prior.
Proceedings of the IEEE International Conference on Computer Vision, 2011

Monocular 3D scene understanding with explicit occlusion reasoning.
Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011

Bayesian deblurring with integrated noise estimation.
Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011

Connecting non-quadratic variational models and MRFs.
Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011

2010
Fusion Moves for Markov Random Field Optimization.
IEEE Trans. Pattern Anal. Mach. Intell., 2010

A Semantic World Model for Urban Search and Rescue Based on Heterogeneous Sensors.
Proceedings of the RoboCup 2010: Robot Soccer World Cup XIV [papers from the 14th annual RoboCup International Symposium, 2010

Vision based victim detection from unmanned aerial vehicles.
Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010

Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes.
Proceedings of the Computer Vision, 2010

Secrets of optical flow estimation and their principles.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

Automatic discovery of meaningful object parts with latent CRFs.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

A generative perspective on MRFs in low-level vision.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

Monocular 3D pose estimation and tracking by detection.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010

2009
Fields of Experts.
Int. J. Comput. Vis., 2009

Real-time Stereo-Image Stitching using GPU-based Belief Propagation.
Proceedings of the 14th International Workshop on Vision, Modeling, and Visualization, 2009

Discriminative structure learning of hierarchical representations for object detection.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

Pictorial structures revisited: People detection and articulated pose estimation.
Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 2009

2008
Learning Optical Flow.
Proceedings of the Computer Vision, 2008

Discrete-Continuous Optimization for Optical Flow Estimation.
Proceedings of the Statistical and Geometrical Approaches to Visual Motion Analysis, 2008

FusionFlow: Discrete-continuous optimization for optical flow estimation.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

People-tracking-by-detection and people-detection-by-tracking.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008

2007
High-Order Markov Random Fields for Low-Level Vision.
PhD thesis, 2007

Evaluation of a convex relaxation to a quadratic assignment matching approach for relational object views.
Image Vis. Comput., 2007

On the Spatial Statistics of Optical Flow.
Int. J. Comput. Vis., 2007

Steerable Random Fields.
Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

2006
Denoising Archival Films using a Learned Bayesian Model.
Proceedings of the International Conference on Image Processing, 2006

Efficient Belief Propagation with Learned Higher-Order Markov Random Fields.
Proceedings of the Computer Vision, 2006

Specular Flow and the Recovery of Surface Structure.
Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 2006

2005
Modeling Neural Population Spiking Activity with Gibbs Distributions.
Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

Fields of Experts: A Framework for Learning Image Priors.
Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), 2005

2004
Tracking Loose-Limbed People.
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), with CD-ROM, 27 June, 2004

Gibbs Likelihoods for Bayesian Tracking.
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), with CD-ROM, 27 June, 2004

2001
Evaluation of Convex Optimization Techniques for the Weighted Graph-Matching Problem in Computer Vision.
Proceedings of the Pattern Recognition, 2001


  Loading...