Thomas Brox
115 publications
15 venues
H Index 54
Affiliation
University of Freiburg, Department of Computer Science, GermanySaarland University, Saarbr cken, Germany
Links
DBLPGoogle Scholar
ORCID- http://lmb.informatik.uni-freiburg.de/people/brox/index.en.html
- https://openreview.net/profile?id=~Thomas_Brox1
- https://mathscinet.ams.org/mathscinet/MRAuthorID/707107
- https://mathgenealogy.org/id.php?id=200416
- https://www.wikidata.org/entity/Q102441385
- https://d-nb.info/gnd/1081454105
| Name | Venue | Year | citations |
|---|---|---|---|
Legend-Informed Symbol Recognition in Engineering Diagrams with Self-supervised Learning.
|
ECML/PKDD | 2025 | 0 |
| When and How Does CLIP Enable Domain and Compositional Generalization?
|
ICML | 2025 | 5 |
| Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapters.
|
IROS | 2025 | 5 |
| Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach.
|
ICLR | 2025 | 0 |
| Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models.
|
ICLR | 2025 | 0 |
| Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond.
|
ECCV | 2024 | 5 |
| DITTO: Demonstration Imitation by Trajectory Transformation.
|
IROS | 2024 | 35 |
| Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching.
|
CoRL | 2024 | 54 |
| Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy.
|
ICLR | 2024 | 22 |
| Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems.
|
ICML | 2024 | 0 |
| Amodal Optical Flow.
|
ICRA | 2024 | 0 |
| Compositional Servoing by Recombining Demonstrations.
|
ICRA | 2024 | 0 |
| Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation.
|
CVPR | 2024 | 0 |
| CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity.
|
ICLR | 2024 | 0 |
| Unsupervised Open-Vocabulary Object Localization in Videos.
|
ICCV | 2023 | 14 |
| Object-Centric Multiple Object Tracking.
|
ICCV | 2023 | 9 |
| Open-vocabulary Attribute Detection.
|
CVPR | 2023 | 0 |
| Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars.
|
NIPS/NeurIPS | 2023 | 0 |
| Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations.
|
ICLR | 2023 | 0 |
| Bridging the Gap to Real-World Object-Centric Learning.
|
ICLR | 2023 | 0 |
| Conditional Visual Servoing for Multi-Step Tasks.
|
IROS | 2022 | 4 |
| Assaying Out-Of-Distribution Generalization in Transfer Learning.
|
NIPS/NeurIPS | 2022 | 88 |
| Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives.
|
AAAI | 2022 | 59 |
| Towards Total Recall in Industrial Anomaly Detection.
|
CVPR | 2022 | 0 |
| Towards Understanding Adversarial Robustness of Optical Flow Networks.
|
CVPR | 2022 | 0 |
| You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction.
|
ICLR | 2022 | 0 |
| On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors.
|
ICCV | 2021 | 68 |
| CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations.
|
ICCV | 2021 | 154 |
| Improving robustness against common corruptions with frequency biased models.
|
ICCV | 2021 | 49 |
| Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors.
|
CVPR | 2021 | 17 |
| Explicitly Modeled Attention Maps for Image Classification.
|
AAAI | 2021 | 0 |
| Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency.
|
TPAMI | 2021 | 0 |
| Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View With a Reachability Prior.
|
CVPR | 2020 | 40 |
| FlowControl: Optical Flow Based Visual Servoing.
|
IROS | 2020 | 29 |
| Improving Unimodal Object Recognition with Multimodal Contrastive Learning.
|
IROS | 2020 | 24 |
| COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning.
|
NIPS/NeurIPS | 2020 | 178 |
| Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering.
|
TPAMI | 2020 | 215 |
| Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control.
|
ICRA | 2020 | 0 |
| Understanding and Robustifying Differentiable Architecture Search.
|
ICLR | 2020 | 0 |
| SELF: Learning to Filter Noisy Labels with Self-Ensembling.
|
ICLR | 2020 | 0 |
| What Do Single-View 3D Reconstruction Networks Learn?
|
CVPR | 2019 | 484 |
| AutoDispNet: Improving Disparity Estimation With AutoML.
|
ICCV | 2019 | 84 |
| Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics.
|
IROS | 2019 | 25 |
| DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision.
|
NIPS/NeurIPS | 2019 | 83 |
| CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth.
|
CVPR | 2019 | 152 |
| Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction.
|
CVPR | 2019 | 211 |
| FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images.
|
ICCV | 2019 | 477 |
| Defending Against Universal Perturbations With Shared Adversarial Training.
|
ICCV | 2019 | 1 |
| Anomaly Detection With Multiple-Hypotheses Predictions.
|
ICML | 2019 | 0 |
| Automated Boxwood Topiary Trimming with a Robotic Arm and Integrated Stereo Vision
|
IROS | 2019 | 0 |
| DeepTAM: Deep Tracking and Mapping.
|
ECCV | 2018 | 241 |
| DPDB-Net: Exploiting Dense Connections for Convolutional Encoders.
|
ICRA | 2018 | 5 |
| Uncertainty Estimates and Multi-hypotheses Networks for Optical Flow.
|
ECCV | 2018 | 249 |
| ECO: Efficient Convolutional Network for Online Video Understanding.
|
ECCV | 2018 | 528 |
| Efficient and robust deep networks for semantic segmentation.
|
IJRR | 2018 | 32 |
| Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation.
|
ECCV | 2018 | 220 |
| 3D Human Pose Estimation in RGBD Images for Robotic Task Learning.
|
ICRA | 2018 | 172 |
| Motion Perception in Reinforcement Learning with Dynamic Objects.
|
CoRL | 2018 | 36 |
| DeMoN: Depth and Motion Network for Learning Monocular Stereo.
|
CVPR | 2017 | 5 |
| Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection.
|
ICCV | 2017 | 224 |
| Topometric Localization with Deep Learning.
|
ISRR | 2017 | 35 |
| Universal Adversarial Perturbations Against Semantic Image Segmentation.
|
ICCV | 2017 | 300 |
| Semantics-aware visual localization under challenging perceptual conditions.
|
ICRA | 2017 | 129 |
| Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs.
|
ICCV | 2017 | 774 |
| Learning to Estimate 3D Hand Pose from Single RGB Images.
|
ICCV | 2017 | 784 |
| Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications.
|
CVPR | 2017 | 0 |
| FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks.
|
CVPR | 2017 | 0 |
| Learning to Generate Chairs, Tables and Cars with Convolutional Networks.
|
TPAMI | 2017 | 0 |
| Deep learning for human part discovery in images.
|
ICRA | 2016 | 107 |
| Efficient deep models for monocular road segmentation.
|
IROS | 2016 | 217 |
| Generating Images with Perceptual Similarity Metrics based on Deep Networks.
|
NIPS/NeurIPS | 2016 | 1185 |
| Synthesizing the preferred inputs for neurons in neural networks via deep generator networks.
|
NIPS/NeurIPS | 2016 | 721 |
| Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images.
|
NIPS/NeurIPS | 2016 | 44 |
| Multi-view 3D Models from Single Images with a Convolutional Network.
|
ECCV | 2016 | 0 |
| Inverting Visual Representations with Convolutional Networks.
|
CVPR | 2016 | 0 |
| A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation.
|
CVPR | 2016 | 0 |
| Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks.
|
TPAMI | 2016 | 0 |
| Global, Dense Multiscale Reconstruction for a Billion Points.
|
ICCV | 2015 | 75 |
| Motion Trajectory Segmentation via Minimum Cost Multicuts.
|
ICCV | 2015 | 207 |
| Video Segmentation with Just a Few Strokes.
|
ICCV | 2015 | 127 |
| Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts.
|
ICCV | 2015 | 131 |
| Unsupervised Generation of a View Point Annotated Car Dataset from Videos.
|
ICCV | 2015 | 41 |
| FlowNet: Learning Optical Flow with Convolutional Networks.
|
ICCV | 2015 | 4536 |
| Learning to generate chairs with convolutional neural networks.
|
CVPR | 2015 | 0 |
| Reconstruction of rigid body models from motion distorted laser range data using optical flow.
|
ICRA | 2014 | 8 |
| Motion Based Foreground Detection and Poselet Motion Features for Action Recognition.
|
ACCV | 2014 | 8 |
| Dense Semi-rigid Scene Flow Estimation from RGBD Images.
|
ECCV | 2014 | 128 |
| Discriminative Unsupervised Feature Learning with Convolutional Neural Networks.
|
NIPS/NeurIPS | 2014 | 1055 |
| Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation.
|
CVPR | 2014 | 84 |
| Training Deformable Object Models for Human Detection Based on Alignment and Clustering.
|
ECCV | 2014 | 18 |
| Segmentation of Moving Objects by Long Term Video Analysis.
|
TPAMI | 2014 | 0 |
| Blind Deconvolution of Widefield Fluorescence Microscopic Data by Regularization of the Optical Transfer Function (OTF).
|
CVPR | 2013 | 21 |
| A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis.
|
ICCV | 2013 | 174 |
| Point-Based 3D Reconstruction of Thin Objects.
|
ICCV | 2013 | 32 |
| An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision.
|
CVPR | 2013 | 67 |
| Fast Rotation Invariant 3D Feature Computation Utilizing Efficient Local Neighborhood Operators.
|
TPAMI | 2012 | 39 |
| Higher order motion models and spectral clustering.
|
CVPR | 2012 | 192 |
| Fast Joint Estimation of Silhouettes and Dense 3D Geometry from Multiple Images.
|
TPAMI | 2012 | 101 |
| Occlusion boundary detection and figure/ground assignment from optical flow.
|
CVPR | 2011 | 177 |
| Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions.
|
ICCV | 2011 | 246 |
| Object segmentation by alignment of poselet activations to image contours.
|
CVPR | 2011 | 117 |
| Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation.
|
TPAMI | 2011 | 0 |
| Object Segmentation by Long Term Analysis of Point Trajectories.
|
ECCV | 2010 | 885 |
| Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow.
|
ECCV | 2010 | 522 |
| Detecting People Using Mutually Consistent Poselet Activations.
|
ECCV | 2010 | 418 |
| Combined Region and Motion-Based 3D Tracking of Rigid and Articulated Objects.
|
TPAMI | 2010 | 0 |
| Large displacement optical flow.
|
CVPR | 2009 | 360 |
| Markerless motion capture of man-machine interaction.
|
CVPR | 2008 | 63 |
| Efficient Dense Scene Flow from Sparse or Dense Stereo Data.
|
ECCV | 2008 | 212 |
| Scaled Motion Dynamics for Markerless Motion Capture.
|
CVPR | 2007 | 62 |
| Variational Motion Segmentation with Level Sets.
|
ECCV | 2006 | 126 |
| High Accuracy Optical Flow Serves 3-D Pose Tracking: Exploiting Contour and Flow Based Constraints.
|
ECCV | 2006 | 84 |
| A TV Flow Based Local Scale Measure for Texture Discrimination.
|
ECCV | 2004 | 100 |
| High Accuracy Optical Flow Estimation Based on a Theory for Warping.
|
ECCV | 2004 | 3038 |
| Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space.
|
CVPR | 2003 | 298 |