I am an Assistant Professor at ETH Zürich in Switzerland. I obtained my Ph.D. degree from Princeton University and became a postdoctoral researcher at UC Berkeley afterwards. I direct the Visual Intelligence and Systems (VIS) Group. I am a member of the Computer Vision Lab. My goal is to build perceptual systems capable of performing complex tasks in complex environments. My research is at the junction of machine learning, computer vision, and robotics. I currently work on the following topics:
- Representation Learning
- Algorithms for 2D and 3D motion analysis
- Real-world delivery of perception models
- Human machine collaboration for large-scale data exploration
- Policy learning for driving and manipulation
- Robot interaction in dynamic environments
I am currently looking for students with strong research records in computer science, electrical engineering, or mechanical engineering to join my group as Ph.D. students, postdoctoral researchers, or research interns. I also offer semester projects and master thesis advising to ETH students. To apply, please send me a cover letter and CV by email. I will usually reply within two weeks if there are suitable positions for the candidates.
Publications
![]() |
|
![]() |
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Computer Vision and Pattern Recognition,
2020
|
![]() |
|
![]() |
Joint Monocular 3D Vehicle Detection and Tracking
International Conference in Computer Vision,
2019
|
![]() |
Disentangling Propagation and Generation for Video Prediction
International Conference in Computer Vision,
2019
|
![]() |
Few-shot Object Detection via Feature Reweighting
International Conference in Computer Vision,
2019
|
![]() |
Hierarchical Discrete Distribution Decomposition for Match Density Estimation
Computer Vision and Pattern Recognition,
2019
|
![]() |
TAFE-Net: Task-Aware Feature Embeddings for Efficient Learning and Inference
Computer Vision and Pattern Recognition,
2019
|
![]() |
Semantic Predictive Control for Explainable and Efficient Policy Learning
International Conference on Robotics and Automation,
2019
|
![]() |
Deep Object Centric Policies for Autonomous Driving
International Conference on Robotics and Automation,
2019
|
![]() |
Deep Mixture of Experts via Shallow Embedding
Conference on Uncertainty in Artificial Intelligence,
2019
|
![]() |
SkipNet: Learning Dynamic Routing in Convolutional Networks
European Conference on Computer Vision,
2018
|
![]() |
Characterizing Adversarial Examples Based on Spatial Consistency Information for
Semantic Segmentation
European Conference on Computer Vision,
2018
|
![]() |
Deep Layer Aggregation
Computer Vision and Pattern Recognition,
2018
|
![]() |
TextureGAN: Controlling Deep Image Synthesis with Texture Patches
Computer Vision and Pattern Recognition,
2018
|
![]() |
PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
Computer Vision and Pattern Recognition,
2018
|
![]() |
IDK Cascades: Fast Deep Learning by Learning not to Overthink
Conference on Uncertainty in Artificial Intelligence,
2018
|
![]() |
Dilated Residual Networks
Computer Vision and Pattern Recognition,
2017
|
![]() |
Semantic Scene Completion from a Single Depth Image
Computer Vision and Pattern Recognition,
2017
|
![]() |
End-to-end Learning of Driving Models from Large-scale Video Datasets
Computer Vision and Pattern Recognition,
2017
|
![]() |
Scribbler: Controlling Deep Image Synthesis with Sketch and Color
Computer Vision and Pattern Recognition,
2017
|
![]() |
Interactive 3D Modeling with a Generative Adversarial Network
International Conference on 3D Vision,
2017
|
![]() |
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
arXiv:1612.02649 cs.CV,
2016
|
![]() |
Multi-Scale Context Aggregation by Dilated Convolutions
International Conference on Learning Representations,
2016
|
![]() |
Automatic Triage for a Photo Series
ACM Transactions on Graphics (Proc. SIGGRAPH),
2016
|
![]() |
SHREC’16 Track`: Large-Scale 3D Shape Retrieval from ShapeNet Core55
EuroGraphics SHREC2016 Workshop Report,
2016
|
![]() |
Semantic Alignment of LiDAR Data at City Scale
Computer Vision and Pattern Recognition,
2015
|
![]() |
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans
in the Loop
arXiv:1506.03365 cs.CV,
2015
|
![]() |
ShapeNet: An Information-Rich 3D Model Repository
arXiv:1512.03012 cs.GR,
2015
|
![]() |
3D ShapeNets: A Deep Representation for Volumetric Shape Modeling
Computer Vision and Pattern Recognition,
2015
|
![]() |
3D Reconstruction from Accidental Motion
Computer Vision and Pattern Recognition,
2014
|
![]() |
HelpingHand: Example-based Stroke Stylization
ACM Transactions on Graphics (Proc. SIGGRAPH),
2012
|
![]() |
Comparing Seven Spectral Methods for Interpolation and for Solving
the
Poisson Equation in a Disk: Zernike Polynomials, Logan-Shepp Ridge
Polynomials, Chebyshev-Fourier Series, Cylindrical Robert Functions,
Bessel-Fourier Expansions, Square-to-Disk Conformal Mapping and
Radial
Basis Functions
Journal of Computational Physics,
Volume 230, Issue 4, 2011
|
Services
- Organizer of Workshop on Autonomous Driving at CVPR 2017, 2018, 2019, 2020
- Organizer of Workshop on Machine Learning for Autonomous Driving at NeurIPS 2019
- Organizer of Workshop on Human In the Loop Learning (HILL) at ICML 2019
- Organizer of 3D Deep Learning Workshop at NIPS 2016
- Organizer of Large-scale Scene Understanding Challenge Workshop at CVPR 2016
- Organizer of CVPR 2016 tutorial on 3D Deep Learning with Marvin
- Organizer of Large-scale Scene Understanding Challenge Workshop at CVPR 2015