Peter V. Gehler
42 publications
8 venues
H Index 29
Affiliation
University of T bingen, Bernstein Center for Computational Neuroscience, GermanyMax Planck Institute for Intelligent Systems, T bingen, Germany
ETH Zurich, Computer Vision Laboratory, Switzerland
Links
| Name | Venue | Year | citations |
|---|---|---|---|
Assaying Out-Of-Distribution Generalization in Transfer Learning.
|
NIPS/NeurIPS | 2022 | 88 |
| Towards Total Recall in Industrial Anomaly Detection.
|
CVPR | 2022 | 0 |
| The Role of Pretrained Representations for the OOD Generalization of RL Agents.
|
ICLR | 2022 | 0 |
| Visual Representation Learning Does Not Generalize Strongly Within the Same Domain.
|
ICLR | 2022 | 0 |
| You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction.
|
ICLR | 2022 | 0 |
| CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations.
|
ICCV | 2021 | 154 |
| Backward-Compatible Prediction Updates: A Probabilistic Approach.
|
NIPS/NeurIPS | 2021 | 17 |
| Dynamic Inference with Neural Interpreters.
|
NIPS/NeurIPS | 2021 | 32 |
| Providing a Single Ground-Truth for Illuminant Estimation for the ColorChecker Dataset.
|
TPAMI | 2020 | 14 |
| Learning an Event Sequence Embedding for Dense Event-Based Deep Stereo.
|
ICCV | 2019 | 116 |
| Deep Directional Statistics: Pose Estimation with Uncertainty Quantification.
|
ECCV | 2018 | 98 |
| Efficient 2D and 3D Facade Segmentation Using Auto-Context.
|
TPAMI | 2018 | 0 |
| Semantic Video CNNs Through Representation Warping.
|
ICCV | 2017 | 216 |
| Unite the People: Closing the Loop Between 3D and 2D Human Representations.
|
CVPR | 2017 | 576 |
| A Generative Model of People in Clothing.
|
ICCV | 2017 | 230 |
| Video Propagation Networks.
|
CVPR | 2017 | 0 |
| Reflectance Adaptive Filtering Improves Intrinsic Image Estimation.
|
CVPR | 2017 | 0 |
| Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image.
|
ECCV | 2016 | 1746 |
| Superpixel Convolutional Networks Using Bilateral Inceptions.
|
ECCV | 2016 | 0 |
| DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation.
|
CVPR | 2016 | 0 |
| Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks.
|
CVPR | 2016 | 0 |
| Multi-View and 3D Deformable Part Models.
|
TPAMI | 2015 | 78 |
| Human Pose Estimation with Fields of Parts.
|
ECCV | 2014 | 81 |
| 2D Human Pose Estimation: New Benchmark and State of the Art Analysis.
|
CVPR | 2014 | 2724 |
| Intrinsic Video.
|
ECCV | 2014 | 44 |
| Efficient Nonlinear Markov Models for Human Motion.
|
CVPR | 2014 | 187 |
| A Non-parametric Bayesian Network Prior of Human Pose.
|
ICCV | 2013 | 50 |
| Occlusion Patterns for Object Class Detection.
|
CVPR | 2013 | 145 |
| Poselet Conditioned Pictorial Structures.
|
CVPR | 2013 | 363 |
| Strong Appearance and Expressive Spatial Models for Human Pose Estimation.
|
ICCV | 2013 | 222 |
| 3D2PM - 3D Deformable Part Models.
|
ECCV | 2012 | 107 |
| Teaching 3D geometry to deformable part models.
|
CVPR | 2012 | 244 |
| Learning Output Kernels with Block Coordinate Descent.
|
ICML | 2011 | 97 |
| Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance.
|
NIPS/NeurIPS | 2011 | 203 |
| Scene Carving: Scene Consistent Image Retargeting.
|
ECCV | 2010 | 81 |
| On Parameter Learning in CRF-Based Approaches to Object Class Image Segmentation.
|
ECCV | 2010 | 98 |
| On feature combination for multiclass object classification.
|
ICCV | 2009 | 923 |
| Let the kernel figure it out; Principled learning of pre-processing for kernel classifiers.
|
CVPR | 2009 | 60 |
| Bayesian color constancy revisited.
|
CVPR | 2008 | 446 |
| Deterministic Annealing for Multiple-Instance Learning.
|
AISTATS | 2007 | 105 |
| The rate adapting poisson model for information retrieval and object recognition.
|
ICML | 2006 | 116 |
| Products of Edge-perts.
|
NIPS/NeurIPS | 2005 | 19 |