Peter Gehler

Computer Science · Physical Sciences

37h-index12.3kcitations113works0.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(30), Advanced Image and Video Retrieval Techniques(29), Human Pose and Action Recognition(23), Advanced Neural Network Applications(22), Video Surveillance and Tracking Methods(17)

Publications113 total

Exploring Fit and Shape for Predicting Garment Size Issues in Fashion with Multi-task Learning
Lecture notes in electrical engineering·2025
Alias-Free GAN for 3D-Aware Image Generation
2024Open Access
TeST: Test-time Self-Training under Distribution Shift
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)·2023· 25 cited
TeST: Test-time Self-Training under Distribution Shift
arXiv (Cornell University)·2022· 2 citedOpen Access
Assaying Out-Of-Distribution Generalization in Transfer Learning
arXiv (Cornell University)·2022· 26 citedOpen Access
Towards Total Recall in Industrial Anomaly Detection
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 1.2k cited
Backward-Compatible Prediction Updates: A Probabilistic Approach
Cambridge University Engineering Department Publications Database·2021· 1 citedOpen Access
Unsupervised Object Learning via Common Fate
arXiv (Cornell University)·2021· 1 citedOpen Access
Dynamic Inference with Neural Interpreters
arXiv (Cornell University)·2021· 9 citedOpen Access
Dynamic Inference with Neural Interpreters
Neural Information Processing Systems·2021
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory\n Prediction
arXiv (Cornell University)·2021· 13 citedOpen Access
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
arXiv (Cornell University)·2021· 4 citedOpen Access
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 125 cited
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
arXiv (Cornell University)·2021Open Access
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video\n Representations
arXiv (Cornell University)·2021· 3 citedOpen Access
InDomainGeneralizationBenchmarkdCelebGlow
Zenodo (CERN European Organization for Nuclear Research)·2021Open Access
Visual Representation Learning Does Not Generalize Strongly Within the\n Same Domain
arXiv (Cornell University)·2021· 8 citedOpen Access
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
arXiv (Cornell University)·2021· 6 citedOpen Access
The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
arXiv (Cornell University)·2021· 3 citedOpen Access
The Role of Pretrained Representations for the OOD Generalization of RL Agents
arXiv (Cornell University)·2021· 4 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Bernt Schiele(13), Martin Kiefel(9), Varun Jampani(8), Sebastian Nowozin(7), Christoph Lassner(6), Michael J. Black(6), Mykhaylo Andriluka(5), Leonid Pishchulin(5), Federica Bogo(5), Bernhard Schölkopf(5), Carsten Rother(5), Raghudeep Gadde(5), Michael Stark(5), Javier Romero(4), Bojan Pepik(4), Angjoo Kanazawa(3), Thomas Brox(3), Eldar Insafutdinov(2), Siyu Tang(2), Bjoern Andres(2)