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 Thomas Brox

Thomas Brox

University of Freiburg

Essentials for Class Incremental Learning


Feb 18, 2021
Sudhanshu Mittal, Silvio Galesso, Thomas Brox

Figure 1 for Essentials for Class Incremental Learning
Figure 2 for Essentials for Class Incremental Learning
Figure 3 for Essentials for Class Incremental Learning
Figure 4 for Essentials for Class Incremental Learning

  Access Paper or Ask Questions

Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins


Nov 20, 2020
Özgün Çiçek, Yassine Marrakchi, Enoch Boasiako Antwi, Barbara Di Ventura, Thomas Brox

Figure 1 for Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins
Figure 2 for Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins
Figure 3 for Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins
Figure 4 for Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins
* Accepted at MICCAI Workshop on Medical Image Learning with Less Labels and Imperfect Data, 2020 
  Access Paper or Ask Questions

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning


Nov 01, 2020
Simon Ging, Mohammadreza Zolfaghari, Hamed Pirsiavash, Thomas Brox

Figure 1 for COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Figure 2 for COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Figure 3 for COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
Figure 4 for COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
* 27 pages, 5 figures, 19 tables. To be published in the 34th conference on Neural Information Processing Systems (NeurIPS 2020). The first two authors contributed equally to this work 
  Access Paper or Ask Questions

Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation


Jul 19, 2020
Gabriel L. Oliveira, Senthil Yogamani, Wolfram Burgard, Thomas Brox

Figure 1 for Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
Figure 2 for Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
Figure 3 for Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation
Figure 4 for Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation

  Access Paper or Ask Questions

Scaling Imitation Learning in Minecraft


Jul 06, 2020
Artemij Amiranashvili, Nicolai Dorka, Wolfram Burgard, Vladlen Koltun, Thomas Brox

Figure 1 for Scaling Imitation Learning in Minecraft
Figure 2 for Scaling Imitation Learning in Minecraft
Figure 3 for Scaling Imitation Learning in Minecraft
Figure 4 for Scaling Imitation Learning in Minecraft

  Access Paper or Ask Questions

FlowControl: Optical Flow Based Visual Servoing


Jul 01, 2020
Max Argus, Lukas Hermann, Jon Long, Thomas Brox

Figure 1 for FlowControl: Optical Flow Based Visual Servoing
Figure 2 for FlowControl: Optical Flow Based Visual Servoing
Figure 3 for FlowControl: Optical Flow Based Visual Servoing
Figure 4 for FlowControl: Optical Flow Based Visual Servoing

  Access Paper or Ask Questions

Explicitly Modeled Attention Maps for Image Classification


Jun 14, 2020
Andong Tan, Duc Tam Nguyen, Maximilian Dax, Matthias Niessner, Thomas Brox

Figure 1 for Explicitly Modeled Attention Maps for Image Classification
Figure 2 for Explicitly Modeled Attention Maps for Image Classification
Figure 3 for Explicitly Modeled Attention Maps for Image Classification
Figure 4 for Explicitly Modeled Attention Maps for Image Classification
* 12 pages, 3 figures 
  Access Paper or Ask Questions

Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior


Jun 08, 2020
Osama Makansi, Özgün Cicek, Kevin Buchicchio, Thomas Brox

Figure 1 for Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior
Figure 2 for Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior
Figure 3 for Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior
Figure 4 for Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior
* In CVPR 2020 
  Access Paper or Ask Questions

Multi-Variate Temporal GAN for Large Scale Video Generation


Apr 04, 2020
Andres Muñoz, Mohammadreza Zolfaghari, Max Argus, Thomas Brox

Figure 1 for Multi-Variate Temporal GAN for Large Scale Video Generation
Figure 2 for Multi-Variate Temporal GAN for Large Scale Video Generation
Figure 3 for Multi-Variate Temporal GAN for Large Scale Video Generation
Figure 4 for Multi-Variate Temporal GAN for Large Scale Video Generation
* 13 pages, 13 figures 
  Access Paper or Ask Questions

Optimized Generic Feature Learning for Few-shot Classification across Domains


Jan 22, 2020
Tonmoy Saikia, Thomas Brox, Cordelia Schmid

Figure 1 for Optimized Generic Feature Learning for Few-shot Classification across Domains
Figure 2 for Optimized Generic Feature Learning for Few-shot Classification across Domains
Figure 3 for Optimized Generic Feature Learning for Few-shot Classification across Domains
Figure 4 for Optimized Generic Feature Learning for Few-shot Classification across Domains

  Access Paper or Ask Questions

Parting with Illusions about Deep Active Learning


Dec 11, 2019
Sudhanshu Mittal, Maxim Tatarchenko, Özgün Çiçek, Thomas Brox

Figure 1 for Parting with Illusions about Deep Active Learning
Figure 2 for Parting with Illusions about Deep Active Learning
Figure 3 for Parting with Illusions about Deep Active Learning
Figure 4 for Parting with Illusions about Deep Active Learning

  Access Paper or Ask Questions

Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control


Oct 31, 2019
Lukas Hermann, Max Argus, Andreas Eitel, Artemij Amiranashvili, Wolfram Burgard, Thomas Brox

Figure 1 for Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
Figure 2 for Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
Figure 3 for Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
Figure 4 for Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control

  Access Paper or Ask Questions

Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics


Oct 17, 2019
Oier Mees, Maxim Tatarchenko, Thomas Brox, Wolfram Burgard

Figure 1 for Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics
Figure 2 for Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics
Figure 3 for Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics
Figure 4 for Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics
* Accepted at the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Video at https://www.youtube.com/watch?v=oQgHG9JdMP4 
  Access Paper or Ask Questions

SELF: Learning to Filter Noisy Labels with Self-Ensembling


Oct 04, 2019
Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, Thomas Brox

Figure 1 for SELF: Learning to Filter Noisy Labels with Self-Ensembling
Figure 2 for SELF: Learning to Filter Noisy Labels with Self-Ensembling
Figure 3 for SELF: Learning to Filter Noisy Labels with Self-Ensembling
Figure 4 for SELF: Learning to Filter Noisy Labels with Self-Ensembling

  Access Paper or Ask Questions

DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision


Sep 28, 2019
Duc Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummad, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox

Figure 1 for DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
Figure 2 for DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
Figure 3 for DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
Figure 4 for DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
* NeuRIPS-2019 (Vancouver, Canada) 
  Access Paper or Ask Questions

Understanding and Robustifying Differentiable Architecture Search


Sep 20, 2019
Arber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, Frank Hutter

Figure 1 for Understanding and Robustifying Differentiable Architecture Search
Figure 2 for Understanding and Robustifying Differentiable Architecture Search
Figure 3 for Understanding and Robustifying Differentiable Architecture Search
Figure 4 for Understanding and Robustifying Differentiable Architecture Search
* 28 pages, 25 figures 
  Access Paper or Ask Questions

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images


Sep 13, 2019
Christian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan Russell, Max Argus, Thomas Brox

Figure 1 for FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
Figure 2 for FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
Figure 3 for FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
Figure 4 for FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
* Accepted to ICCV 2019, Project page: https://lmb.informatik.uni-freiburg.de/projects/freihand/ 
  Access Paper or Ask Questions

Semi-Supervised Semantic Segmentation with High- and Low-level Consistency


Aug 15, 2019
Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox

Figure 1 for Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
Figure 2 for Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
Figure 3 for Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
Figure 4 for Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

  Access Paper or Ask Questions

Group Pruning using a Bounded-Lp norm for Group Gating and Regularization


Aug 09, 2019
Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer

Figure 1 for Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Figure 2 for Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Figure 3 for Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Figure 4 for Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
* German Conference on Pattern Recognition (GCPR) 2019, 12 main pages, 3 pages of appendix, 4 figures, 2 tables 
  Access Paper or Ask Questions

Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction


Jun 09, 2019
Osama Makansi, Eddy Ilg, Özgün Cicek, Thomas Brox

Figure 1 for Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
Figure 2 for Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
Figure 3 for Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
Figure 4 for Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
* In CVPR 2019 
  Access Paper or Ask Questions

Robust Learning Under Label Noise With Iterative Noise-Filtering


Jun 01, 2019
Duc Tam Nguyen, Thi-Phuong-Nhung Ngo, Zhongyu Lou, Michael Klar, Laura Beggel, Thomas Brox

Figure 1 for Robust Learning Under Label Noise With Iterative Noise-Filtering
Figure 2 for Robust Learning Under Label Noise With Iterative Noise-Filtering
Figure 3 for Robust Learning Under Label Noise With Iterative Noise-Filtering
Figure 4 for Robust Learning Under Label Noise With Iterative Noise-Filtering

  Access Paper or Ask Questions

AutoDispNet: Improving Disparity Estimation with AutoML


May 17, 2019
Tonmoy Saikia, Yassine Marrakchi, Arber Zela, Frank Hutter, Thomas Brox

Figure 1 for AutoDispNet: Improving Disparity Estimation with AutoML
Figure 2 for AutoDispNet: Improving Disparity Estimation with AutoML
Figure 3 for AutoDispNet: Improving Disparity Estimation with AutoML
Figure 4 for AutoDispNet: Improving Disparity Estimation with AutoML

  Access Paper or Ask Questions

What Do Single-view 3D Reconstruction Networks Learn?


May 09, 2019
Maxim Tatarchenko, Stephan R. Richter, René Ranftl, Zhuwen Li, Vladlen Koltun, Thomas Brox

Figure 1 for What Do Single-view 3D Reconstruction Networks Learn?
Figure 2 for What Do Single-view 3D Reconstruction Networks Learn?
Figure 3 for What Do Single-view 3D Reconstruction Networks Learn?
Figure 4 for What Do Single-view 3D Reconstruction Networks Learn?

  Access Paper or Ask Questions

Learning Representations for Predicting Future Activities


May 09, 2019
Mohammadreza Zolfaghari, Özgün Çiçek, Syed Mohsin Ali, Farzaneh Mahdisoltani, Can Zhang, Thomas Brox

Figure 1 for Learning Representations for Predicting Future Activities
Figure 2 for Learning Representations for Predicting Future Activities
Figure 3 for Learning Representations for Predicting Future Activities
Figure 4 for Learning Representations for Predicting Future Activities
* 14 pages, ICCV 2019 submission, Code and Models: https://github.com/lmb-freiburg/PreFAct 
  Access Paper or Ask Questions

MAIN: Multi-Attention Instance Network for Video Segmentation


Apr 11, 2019
Juan Leon Alcazar, Maria A. Bravo, Ali K. Thabet, Guillaume Jeanneret, Thomas Brox, Pablo Arbelaez, Bernard Ghanem

Figure 1 for MAIN: Multi-Attention Instance Network for Video Segmentation
Figure 2 for MAIN: Multi-Attention Instance Network for Video Segmentation
Figure 3 for MAIN: Multi-Attention Instance Network for Video Segmentation
Figure 4 for MAIN: Multi-Attention Instance Network for Video Segmentation

  Access Paper or Ask Questions

CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth


Apr 03, 2019
Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera

Figure 1 for CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
Figure 2 for CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
Figure 3 for CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
Figure 4 for CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
* Camera ready version for CVPR 2019. Project page: http://webdiis.unizar.es/~jmfacil/camconvs/ 
  Access Paper or Ask Questions

CrossNorm: Normalization for Off-Policy TD Reinforcement Learning


Feb 14, 2019
Aditya Bhatt, Max Argus, Artemij Amiranashvili, Thomas Brox

Figure 1 for CrossNorm: Normalization for Off-Policy TD Reinforcement Learning
Figure 2 for CrossNorm: Normalization for Off-Policy TD Reinforcement Learning
Figure 3 for CrossNorm: Normalization for Off-Policy TD Reinforcement Learning
Figure 4 for CrossNorm: Normalization for Off-Policy TD Reinforcement Learning

  Access Paper or Ask Questions

Motion Perception in Reinforcement Learning with Dynamic Objects


Jan 10, 2019
Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox

Figure 1 for Motion Perception in Reinforcement Learning with Dynamic Objects
Figure 2 for Motion Perception in Reinforcement Learning with Dynamic Objects
Figure 3 for Motion Perception in Reinforcement Learning with Dynamic Objects
Figure 4 for Motion Perception in Reinforcement Learning with Dynamic Objects

  Access Paper or Ask Questions

Defending against Universal Perturbations with Shared Adversarial Training


Dec 10, 2018
Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen

Figure 1 for Defending against Universal Perturbations with Shared Adversarial Training
Figure 2 for Defending against Universal Perturbations with Shared Adversarial Training
Figure 3 for Defending against Universal Perturbations with Shared Adversarial Training
Figure 4 for Defending against Universal Perturbations with Shared Adversarial Training

  Access Paper or Ask Questions