Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Stefan Roth

Self-Supervised Multi-Frame Monocular Scene Flow


May 05, 2021
Junhwa Hur, Stefan Roth

* To appear at CVPR 2021. Code available: https://github.com/visinf/multi-mono-sf 

  Access Paper or Ask Questions

Self-supervised Augmentation Consistency for Adapting Semantic Segmentation


Apr 30, 2021
Nikita Araslanov, Stefan Roth

* To appear at CVPR 2021. Code: https://github.com/visinf/da-sac 

  Access Paper or Ask Questions

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring


Mar 18, 2021
Jiangxin Dong, Stefan Roth, Bernt Schiele

* Accepted to NeurIPS 2020 as an oral presentation. Project page: https://gitlab.mpi-klsb.mpg.de/jdong/dwdn 

  Access Paper or Ask Questions

Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise


Mar 16, 2021
Jannik Schmitt, Stefan Roth


  Access Paper or Ask Questions

Diverse Image Captioning with Context-Object Split Latent Spaces


Nov 02, 2020
Shweta Mahajan, Stefan Roth

* To appear at NeurIPS 2020 

  Access Paper or Ask Questions

MOTChallenge: A Benchmark for Single-camera Multiple Target Tracking


Oct 15, 2020
Patrick Dendorfer, Aljoša Ošep, Anton Milan, Konrad Schindler, Daniel Cremers, Ian Reid, Stefan Roth, Laura Leal-Taixé

* Accepted at IJCV 

  Access Paper or Ask Questions

Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning


Jul 11, 2020
Sascha Rosbach, Xing Li, Simon Großjohann, Silviu Homoceanu, Stefan Roth

* Manuscript accepted at 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Received March 1, 2020. Typos corrected 

  Access Paper or Ask Questions

LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery


May 28, 2020
Wentong Liao, Xiang Chen, Jingfeng Yang, Stefan Roth, Michael Goesele, Michael Ying Yang, Bodo Rosenhahn

* 8 pages 

  Access Paper or Ask Questions

Single-Stage Semantic Segmentation from Image Labels


May 16, 2020
Nikita Araslanov, Stefan Roth

* To appear at CVPR 2020; minor corrections in Eq. (9). Code: https://github.com/visinf/1-stage-wseg 

  Access Paper or Ask Questions

Self-Supervised Monocular Scene Flow Estimation


Apr 15, 2020
Junhwa Hur, Stefan Roth

* To appear at CVPR 2020 (Oral); a typo corrected in the reference section 

  Access Paper or Ask Questions

Normalizing Flows with Multi-Scale Autoregressive Priors


Apr 08, 2020
Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz, Bernt Schiele, Stefan Roth

* To appear in CVPR 2020 

  Access Paper or Ask Questions

Optical Flow Estimation in the Deep Learning Age


Apr 06, 2020
Junhwa Hur, Stefan Roth

* To appear as a book chapter in Modelling Human Motion, N. Noceti, A. Sciutti and F. Rea, Eds., Springer, 2020 

  Access Paper or Ask Questions

Probabilistic Pixel-Adaptive Refinement Networks


Mar 31, 2020
Anne S. Wannenwetsch, Stefan Roth

* To appear at CVPR 2020 

  Access Paper or Ask Questions

MOT20: A benchmark for multi object tracking in crowded scenes


Mar 19, 2020
Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixé

* The sequences of the new MOT20 benchmark were previously presented in the CVPR 2019 tracking challenge ( arXiv:1906.04567 ). The differences between the two challenges are: - New and corrected annotations - New sequences, as we had to crop and transform some old sequences to achieve higher quality in the annotations. - New baselines evaluations and different sets of public detections 

  Access Paper or Ask Questions

Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings


Feb 16, 2020
Shweta Mahajan, Iryna Gurevych, Stefan Roth

* Published as a conference paper at ICLR 2020 

  Access Paper or Ask Questions

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving


Dec 07, 2019
Sascha Rosbach, Vinit James, Simon Großjohann, Silviu Homoceanu, Xing Li, Stefan Roth

* ICRA 2020. C 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 

  Access Paper or Ask Questions

Markov Decision Process for Video Generation


Sep 26, 2019
Vladyslav Yushchenko, Nikita Araslanov, Stefan Roth

* To appear at 2019 ICCV Workshop on Large Scale Holistic Video Understanding 

  Access Paper or Ask Questions

Deep Video Deblurring: The Devil is in the Details


Sep 26, 2019
Jochen Gast, Stefan Roth

* To appear at ICCVW 2019 

  Access Paper or Ask Questions

Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings


Sep 14, 2019
Shweta Mahajan, Teresa Botschen, Iryna Gurevych, Stefan Roth

* Accepted at ICCV 2019 Workshop on Cross-Modal Learning in Real World 

  Access Paper or Ask Questions

Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice


Sep 09, 2019
Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler, Stefan Roth

* To appear at GCPR 2019 

  Access Paper or Ask Questions

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


Jun 10, 2019
Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixe

* arXiv admin note: substantial text overlap with arXiv:1603.00831, arXiv:1504.01942 

  Access Paper or Ask Questions

Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving


May 01, 2019
Sascha Rosbach, Vinit James, Simon Großjohann, Silviu Homoceanu, Stefan Roth

* Manuscript submitted to 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Received March 1, 2019 

  Access Paper or Ask Questions

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation


Apr 10, 2019
Junhwa Hur, Stefan Roth

* To appear in CVPR 2019 

  Access Paper or Ask Questions

Actor-Critic Instance Segmentation


Apr 10, 2019
Nikita Araslanov, Constantin Rothkopf, Stefan Roth

* To appear at CVPR 2019 

  Access Paper or Ask Questions

Neural Nearest Neighbors Networks


Oct 30, 2018
Tobias Plötz, Stefan Roth

* to appear at NIPS*2018, code available at https://github.com/visinf/n3net/ 

  Access Paper or Ask Questions

Lightweight Probabilistic Deep Networks


May 29, 2018
Jochen Gast, Stefan Roth

* To appear at CVPR 2018 

  Access Paper or Ask Questions

Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers


Apr 29, 2018
Stephan R. Richter, Stefan Roth

* Published at the Conference on Computer Vision and Pattern Recognition (CVPR 2018) 

  Access Paper or Ask Questions

Detail-Preserving Pooling in Deep Networks


Apr 11, 2018
Faraz Saeedan, Nicolas Weber, Michael Goesele, Stefan Roth

* To appear at CVPR 2018 

  Access Paper or Ask Questions

Stochastic Variational Inference with Gradient Linearization


Mar 28, 2018
Tobias Plötz, Anne S. Wannenwetsch, Stefan Roth

* To appear at CVPR 2018 

  Access Paper or Ask Questions