Stefan Roth
47 papers · 2013–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
π Interdisciplinary Bridge π Renaissance Researcher (8) π Academic Marathon (12) π Conference Polyglot (8) πΊοΈ Taxonomy Completionist (94)
π§
Keyword Pioneer
πΊοΈ
Taxonomy Completionist
(94)
π
Renaissance Researcher
(8)
π
Conference Loyalist
(24)
π
Keyword Trendsetter Combo
(4)
π§¬
Topic Evolution
π
Keyword Champion
(2)
π
Trend Setter
π
Conference Pioneer
π
Century Club
(47)
π₯
Unstoppable
(13)
β‘
Prolific Year
(7)
ποΈ
Keyword Collector
(228)
Conferences
CVPR (24)
ICCV (12)
NIPS (6)
ACL (1)
ECCV (1)
ICLR (1)
NAACL (1)
WACV (1)
Top co-authors
Keywords
neural network
(7)
image restoration
(6)
semantic segmentation
(6)
optical flow
(5)
self-supervised learning
(5)
convolutional neural network
(4)
depth estimation
(4)
image deblurring
(4)
instance segmentation
(3)
unsupervised learning
(3)
zero-shot learning
(3)
3d geometry
(3)
feature attribution
(2)
image denoising
(2)
monocular depth estimation
(2)
transfer learning
(2)
map estimation
(2)
variational inference
(2)
multimodal learning
(2)
density estimation
(2)
Papers
ART: Adaptive Relation Tuning for Generalized Relation Prediction
ICCV 2025
Removing Cost Volumes from Optical Flow Estimators
ICCV 2025
GLASS: Guided Latent Slot Diffusion for Object-Centric Learning
CVPR 2025
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
ICCV 2025
Activation Subspaces for Out-of-Distribution Detection
ICCV 2025
Scene-Centric Unsupervised Panoptic Segmentation
CVPR 2025
Adapters Strike Back
CVPR 2024
Benchmarking the Attribution Quality of Vision Models
NIPS 2024
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
ICCV 2023
Vision Relation Transformer for Unbiased Scene Graph Generation
ICCV 2023
xGQA: Cross-Lingual Visual Question Answering
ACL 2022
PixelPyramids: Exact Inference Models From Lossless Image Pyramids
ICCV 2021
Self-Supervised Augmentation Consistency for Adapting Semantic Segmentation
CVPR 2021
Self-Supervised Multi-Frame Monocular Scene Flow
CVPR 2021
Boosting Monocular Depth With Panoptic Segmentation Maps
WACV 2021
Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring
CVPR 2021
Dense Unsupervised Learning for Video Segmentation
NIPS 2021
Fast Axiomatic Attribution for Neural Networks
NIPS 2021
Self-Supervised Monocular Scene Flow Estimation
CVPR 2020
Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring
NIPS 2020
Diverse Image Captioning with Context-Object Split Latent Spaces
NIPS 2020
Single-Stage Semantic Segmentation From Image Labels
CVPR 2020
Normalizing Flows With Multi-Scale Autoregressive Priors
CVPR 2020
Probabilistic Pixel-Adaptive Refinement Networks
CVPR 2020
Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
ICLR 2020
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
CVPR 2019
Actor-Critic Instance Segmentation
CVPR 2019
Lightweight Probabilistic Deep Networks
CVPR 2018
Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
CVPR 2018
Stochastic Variational Inference With Gradient Linearization
CVPR 2018
Normalized Blind Deconvolution
ECCV 2018
Multimodal Frame Identification with Multilingual Evaluation
NAACL 2018
Detail-Preserving Pooling in Deep Networks
CVPR 2018
Neural Nearest Neighbors Networks
NIPS 2018
MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation
ICCV 2017
ProbFlow: Joint Optical Flow and Uncertainty Estimation
ICCV 2017
Noise-Blind Image Deblurring
CVPR 2017
Benchmarking Denoising Algorithms With Real Photographs
CVPR 2017
Parametric Object Motion From Blur
CVPR 2016
The Cityscapes Dataset for Semantic Urban Scene Understanding
CVPR 2016
Registering Images to Untextured Geometry Using Average Shading Gradients
ICCV 2015
Discriminative Shape From Shading in Uncalibrated Illumination
CVPR 2015
Shrinkage Fields for Effective Image Restoration
CVPR 2014
Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
CVPR 2013
Discriminative Non-blind Deblurring
CVPR 2013
Learning People Detectors for Tracking in Crowded Scenes
ICCV 2013
Piecewise Rigid Scene Flow
ICCV 2013