Sotabase

Career

· Junior Research Fellow (JRF), Kellogg College, University of Oxford2021–
· Senior Researcher in Machine Learning and Computer Vision, University of Oxford, Department of Engineering Science2020–
· R&D Distinguished Advisor, Softserve

Publications (87)

TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
European Conference on Computer Vision · 2018
1,013
cited
Language Model Tokenizers Introduce Unfairness Between Languages
Neural Information Processing Systems · 2023
174
cited
Target Response Adaptation for Correlation Filter Tracking
European Conference on Computer Vision · 2016
163
cited
In Defense of Sparse Tracking: Circulant Sparse Tracker
Computer Vision and Pattern Recognition · 2016
137
cited
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Neural Information Processing Systems · 2024
82
cited
Computationally Budgeted Continual Learning: What Does Matter?
Computer Vision and Pattern Recognition · 2023
79
cited
3D Part-Based Sparse Tracker with Automatic Synchronization and Registration
Computer Vision and Pattern Recognition · 2016
73
cited
Can Large Language Model Agents Simulate Human Trust Behaviors?
Neural Information Processing Systems · 2024
69
cited
Real-Time Evaluation in Online Continual Learning: A New Hope
Computer Vision and Pattern Recognition · 2023
59
cited
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Neural Information Processing Systems · 2022
58
cited
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
arXiv.org · 2024
58
cited
Multi-template Scale-Adaptive Kernelized Correlation Filters
2015 IEEE International Conference on Computer Vision Workshop (ICCVW) · 2015
43
cited
Open Problems in Machine Unlearning for AI Safety
arXiv.org · 2025
41
cited
Data Dependent Randomized Smoothing
Conference on Uncertainty in Artificial Intelligence · 2020
40
cited
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2018
39
cited
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
International Conference on Learning Representations · 2023
39
cited
ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Trans. Mach. Learn. Res. · 2021
35
cited
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Conference on Empirical Methods in Natural Language Processing · 2024
34
cited
Combating Adversaries with Anti-Adversaries
AAAI Conference on Artificial Intelligence · 2021
33
cited
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020
32
cited
Sotabase