Sotabase

Career

· PhD in Computer Science, Georgia Institute of Technology2002–2010
· B.S. in Engineering and Applied Science (Computer Science Option), California Institute of Technology1999–2002
· Senior Engineering Director, Google DeepMind

Publications (21)

IBRNet: Learning Multi-View Image-Based Rendering
Computer Vision and Pattern Recognition · 2021
904
cited
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
European Conference on Computer Vision · 2015
369
cited
Terrain Synthesis from Digital Elevation Models
IEEE Transactions on Visualization and Computer Graphics · 2007
261
cited
Movie genre classification via scene categorization
ACM Multimedia · 2010
141
cited
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
IEEE International Conference on Computer Vision · 2023
85
cited
Feature-preserving artifact removal from dermoscopy images
SPIE Medical Imaging · 2008
82
cited
Spatially constrained segmentation of dermoscopy images
IEEE International Symposium on Biomedical Imaging · 2008
72
cited
Blockout: Dynamic Model Selection for Hierarchical Deep Networks
Computer Vision and Pattern Recognition · 2015
51
cited
NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
Neural Information Processing Systems · 2023
41
cited
Dermoscopic interest point detector and descriptor
IEEE International Symposium on Biomedical Imaging · 2009
28
cited
Exemplar-based segmentation of pigmented skin lesions from dermoscopy images
IEEE International Symposium on Biomedical Imaging · 2010
23
cited
TIPS: Text-Image Pretraining with Spatial Awareness
International Conference on Learning Representations · 2024
21
cited
Modeling Collaborator: Enabling Subjective Vision Classification with Minimal Human Effort via LLM Tool-Use
Computer Vision and Pattern Recognition · 2024
20
cited
ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images
European Conference on Computer Vision · 2024
8
cited
Dual Range Deringing for non-blind image deconvolution
2010 IEEE International Conference on Image Processing · 2010
8
cited
LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals
International Conference on 3D Vision · 2023
6
cited
Unifying Specialist Image Embedding into Universal Image Embedding
arXiv.org · 2020
5
cited
GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification
arXiv.org · 2025
Sotabase
Howard Zhou | Researcher Profile | Sotabase | Sotabase