Scholar
Philipp Krähenbühl
Google Scholar ID: dzOd2hgAAAAJ
UT Austin / Apple
Citations & Impact
Citations
32,932
H-index
47
i10-index
63
Publications
20
Co-authors
97
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024)
- Promptable Closed-loop Traffic Simulation (CoRL 2024)
- PartDistillation: Learning Parts from Instance Segmentation (CVPR 2023)
- Learning Video Representations from Large Language Models (CVPR 2023)
- Language Conditioned Traffic Generation (CoRL 2023)
- Language-conditioned Detection Transformer (CVPR 2023)
- Predicting a Protein's Stability under a Million Mutations (NeurIPS 2023)
- Real-Time Online Video Detection with Temporal Smoothing Transformers (ECCV 2022)
- Long-tail detection with effective class-margins (ECCV 2022)
- Detecting twenty-thousand classes using image-level supervision (ECCV 2022)
- Learning from All Vehicles (CVPR 2022)
- Cross-view Transformers for real-time Map-view Semantic Segmentation (CVPR 2022)
- Global Tracking Transformers (CVPR 2022)
- Simple multi-dataset detection (CVPR 2022)
- Multimodal Virtual Point 3D Detection (NeurIPS 2021)
- Learning to drive from a world on rails (ICCV 2021)
- Towards Long-Form Video Understanding (CVPR 2021)
- Center-based 3d object detection and tracking (CVPR 2021)
- Memory Optimization for Deep Networks (ICLR 2021)
- Probabilistic two-stage detection (arXiv 2021)
- Domain Adaptation Through Task Distillation (ECCV 2020)
- Tracking Objects as Points (ECCV 2020)
- A Multigrid Method for Efficiently Training Video Models (CVPR 2020)
- Learning by Cheating (CORL 2019)
- Monocular plan view networks for autonomous driving (IROS 2019)
- Objects as points (arXiv preprint arXiv:1904.07850 2019)
- Long-Term Feature Banks for Detailed Video Understanding (CVPR 2019)
Research Experience
- Associate Professor in the Department of Computer Science at the University of Texas at Austin and Researcher at Apple.
Education
- Received PhD in 2014 from the CS Department at Stanford University and then spent two wonderful years as a PostDoc at UC Berkeley.
Background
- Research interests lie in Computer Vision, Machine learning and Computer Graphics. Particularly interested in deep learning, image, video and scene understanding.
