Sotabase

Career

· Microsoft Research Cambridge

Publications (23)

Random forests versus Neural Networks — What's best for camera localization?
IEEE International Conference on Robotics and Automation · 2016
76
cited
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
IEEE International Conference on Computer Vision · 2021
51
cited
Stereosonic vision: Exploring visual-to-auditory sensory substitution mappings in an immersive virtual reality navigation paradigm
PLoS ONE · 2018
50
cited
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
AAAI Conference on Artificial Intelligence · 2023
50
cited
Disability-first Dataset Creation: Lessons from Constructing a Dataset for Teachable Object Recognition with Blind and Low Vision Data Collectors
International ACM SIGACCESS Conference on Computers and Accessibility · 2021
42
cited
FLIPDIAL: A Generative Model for Two-Way Visual Dialogue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2018
42
cited
NP-Match: When Neural Processes meet Semi-Supervised Learning
International Conference on Machine Learning · 2022
42
cited
A workable strategy for COVID-19 testing: stratified periodic testing rather than universal random testing
Oxford review of economic policy · 2020
39
cited
Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation
Energy Minimization Methods in Computer Vision and Pattern Recognition · 2016
38
cited
Understanding Personalized Accessibility through Teachable AI: Designing and Evaluating Find My Things for People who are Blind or Low Vision
International ACM SIGACCESS Conference on Computers and Accessibility · 2023
34
cited
Visual Dialogue without Vision or Dialogue
arXiv.org · 2018
34
cited
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods
arXiv.org · 2023
30
cited
A Dynamic AI System for Extending the Capabilities of Blind People
CHI Extended Abstracts · 2020
25
cited
Memory Efficient Meta-Learning with Large Images
Neural Information Processing Systems · 2021
21
cited
Explaining CLIP's Performance Disparities on Data from Blind/Low Vision Users
Computer Vision and Pattern Recognition · 2023
14
cited
Mining Pixels: Weakly Supervised Semantic Segmentation Using Image Labels
arXiv.org · 2016
13
cited
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation
International Conference on Machine Learning · 2023
9
cited
Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP
Conference on Empirical Methods in Natural Language Processing · 2023
6
cited
VizWiz grand challenge workshop at CVPR 2022
ACM SIGACCESS Accessibility and Computing · 2022
4
cited
Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks
International Conference on Learning Representations · 2023
2
cited
Sotabase
Daniela Massiceti | Researcher Profile | Sotabase | Sotabase