Mini Bio: I am an assistant professor in the Machine Intelligence Laboratory at the University of Cambridge in the UK. Previously, I was fortunate to be a researcher in the Visual Geometry Group and a research fellow at Balliol College, Oxford. Broadly, I aim to develop machine learning models that acquire knowledge efficiently in the presence of noise. I also have an interest in models that lie at the intersection of language and sensory modalities like sound and vision.
Augmented scientists: A central focus of my current work is developing tools to augment human scientists (by applying machine learning to vision, sound, text and code) to increase their productivity. If you are too, get in touch!
Foundation Models: I have an interest in the recent development of large self-supervised neural networks (sometimes referred to as “foundation models”) for generation and perception. See here for some of my online lectures on this topic.
Code generation: As part of the augmented scientists project, I aim to develop tools that allow software development in natural language.
Remote sensing: Satellite/aerial imagery offers the opportunity to tackle a range of logistical problems relating to food security and ecosystem monitoring. I’m particularly interested in models that can parse satellite data accurately with minimal annotation cost.
AI safety: I worry about AI safety.
Why come to research and build machine learning/augmented scientists in Cambridge? The author of this paragraph is not an impartial judge, but: if you’re passionate about researching and building the machines of the future, Cambridge is the place to be! It has great computing resources, beautiful scenery, and most importantly, a wonderful assembly of smart, creative and energetic people. In the winter it can get a bit chilly, so bring a warm coat.
Technical communication: I’m interested in the communication of technical ideas. I have a YouTube channel that represents an exploration on this topic.
Deployment: I have an interest in developing applications that see real-world usage through startups, non-profits etc., particularly those enabled by recent research developments in ML.
- 09 / 2022
ReCo: Retrieve and Co-segment for Zero-shot Transfer will appear at NeurIPS 2022.
- 09 / 2022
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection will appear at NeurIPS 2022.
- 09 / 2022
If you are intersted in doing a PhD with me on the topics of: (i) augmented scientists, (ii) language and vision, please send me an email samuel.albanie.academic [AT] gmail.com with subject "PhD interest".
- 08 / 2022
Serving as an area chair at WACV 2023, and having fun.
- 07 / 2022
Automatic dense annotation of large-vocabulary sign language videos will appear at ECCV 2022.
- 01 / 2022
If you are interested in doing a postdoc with me, please send me an email samuel.albanie.academic [AT] gmail.com with subject "postdoc interest".
- 12 / 2021
Thank you to everyone who participated in the Pre-registration workshop at NeurIPS! Video of the event can be found here.
- 11 / 2021
Our large-scale BOBSL dataset is now available!
- 10 / 2021
All you need are a few pixels: semantic segmentation with PixelPick won best paper at the ILDAV workshop at ICCV 2021. Congrats to Gyungin and Weidi.
- 09 / 2021
The NeurIPS 2021 Pre-registration Workshop is soliciting submissions! Deadline: 17th September 2021.
- 09 / 2021
Joined the ELLIS Society.
- 08 / 2021
Audio Retrieval with Natural Language Queries was shortlisted for best student paper at Interspeech 2021. Congrats to Andreea-Maria, Sophia, Joao and Zeynep.
- 07 / 2021
Serving as an Area Chair for BMVC 2021.
- 09 / 2020
We are soliciting submissions for The pre-registration experiment: an alternative publication model for machine learning research at NeuIPS 2020. Find out more about the workshop here.
- 07 / 2020
The schedule for the workshop Sign Language Recognition, Translation and Production at ECCV 2020 can be found here.
- 06 / 2020
Materials from the workshop The End-of-End-to-End: A Video Understanding Pentathlon at CVPR 2020 can be found here. A technical report describing the challenge is available here. A recording of the workshop is on YouTube.
- 11 / 2019
Materials from the Neural Architects Workshop at ICCV 2019 can be found here. A playlist of the invited talks is available on YouTube.
- 11 / 2019
Talks and papers from the ICCV 2019 workshop "Should we preregister experiments in computer vision?" can be found here. A playlist of the talks is on YouTube here.