Sotabase

Career

· Research Scientist, Meta2025–
· Postdoctoral Researcher, Stanford University2022–2024
· PhD Student, Carnegie Mellon University2016–2022
· M.Sc., Toronto Metropolitan University2014–2016
· Bachelor's degree, Toronto Metropolitan University2008–2012

Publications (54)

Evaluation of deep convolutional nets for document image classification and retrieval
IEEE International Conference on Document Analysis and Recognition · 2015
444
cited
Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness
ECCV Workshops · 2016
422
cited
Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories
European Conference on Computer Vision · 2022
243
cited
PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking
IEEE International Conference on Computer Vision · 2023
213
cited
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
IEEE International Conference on Robotics and Automation · 2022
175
cited
Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision
IEEE International Conference on Computer Vision · 2017
162
cited
Segmentation-Aware Convolutional Networks Using Local Attention Masks
IEEE International Conference on Computer Vision · 2017
147
cited
VR facial animation via multiview image translation
ACM Transactions on Graphics · 2019
130
cited
An Interactive Node-Link Visualization of Convolutional Neural Networks
International Symposium on Visual Computing · 2015
126
cited
MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds
Computer Vision and Pattern Recognition · 2024
121
cited
Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos
ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia · 2024
75
cited
TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
European Conference on Computer Vision · 2022
48
cited
Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping
International Conference on Learning Representations · 2019
31
cited
Reward Learning from Narrated Demonstrations
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2018
31
cited
CoCoNets: Continuous Contrastive 3D Scene Representations
Computer Vision and Pattern Recognition · 2021
26
cited
Embodied Language Grounding With 3D Visual Feature Representations
Computer Vision and Pattern Recognition · 2019
26
cited
Move to See Better: Self-Improving Embodied Object Detection
British Machine Vision Conference · 2021
26
cited
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
arXiv.org · 2025
25
cited
A Simple Baseline for BEV Perception Without LiDAR
arXiv.org · 2022
22
cited
Disentangling 3D Prototypical Networks For Few-Shot Concept Learning
International Conference on Learning Representations · 2020
21
cited
Sotabase
Adam W. Harley | Researcher Profile | Sotabase | Sotabase