Research

For a potentially more up-to-date list of publications, see Semantic Scholar.

Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models

Vishaal Udandarao and Max Burg and Samuel Albanie and Matthias Bethge
International Conference on Learning Representations (ICLR), 2024
paper, code

Iterative Averaging in the Quest for Best Test Error

Diego Granziol and Nicholas Baskerville and Xingchen Wan and Samuel Albanie and Stephen J. Roberts
Journal of Machine Learning Research, 2024
paper

Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs

Jonathan Roberts and Timo Lüddecke and Rehan Sheikh and Kai Han and Samuel Albanie
arXiv preprint arXiv:2311.14656, 2023
paper

SuS-X: Training-Free Name-Only Transfer of Vision-Language Models

Vishaal Udandarao and Ankush Gupta and Samuel Albanie
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
paper, project page, code

Simple Baselines for Interactive Video Retrieval with Questions and Answers

Kaiqu Liang and Samuel Albanie
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
paper, code

RLIPv2: Fast Scaling of Relational Language-Image Pre-training

Hangjie Yuan and Shiwei Zhang and Xiang Wang and Samuel Albanie and Yining Pan and Tao Feng and Jianwen Jiang and Dong Ni and Yingya Zhang and Deli Zhao
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
paper, code

Moment Detection in Long Tutorial Videos

Ioana Croitoru and Simion-Vlad Bogolin and Samuel Albanie and Yang Liu and Zhaowen Wang and Seunghyun Yoon and Hailin Jin and Trung Bui
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
paper, code

arXiVeri: Automatic table verification with GPT

Gyungin Shin and Weidi Xie and Samuel Albanie
NeurIPS Workshop on AI4Science Workshop, 2023
paper, project page, code

Zero-shot Unsupervised Transfer Instance Segmentation

Gyungin Shin and Samuel Albanie and Weidi Xie
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
paper, project page, code
Best paper at CVPRW L3D-IVU

GPT4GEO: How a Language Model Sees the World's Geography

Jonathan Roberts and Timo Lüddecke and Sowmen Das and Kai Han and Samuel Albanie
NeurIPS Workshop on Foundation Models for Decision Making, 2023
paper, code

Can GPT-4 Perform Neural Architecture Search?

Mingkai Zheng and Xiu Su and Shan You and Fei Wang and Chen Qian and Chang Xu and Samuel Albanie
arXiv preprint arXiv:2304.10970, 2023
paper, code

Satin: A multi-task metadataset for classifying satellite imagery using vision-language models

Jonathan Roberts and Kai Han and Samuel Albanie
ICCV Workshop: Towards the Next Generation of Computer Vision Datasets, 2023
paper, project page

DeepMIM: Deep Supervision for Masked Image Modeling

Sucheng Ren and Fangyun Wei and Samuel Albanie and Zheng Zhang and Han Hu
arXiv preprint arXiv:2303.08817, 2023
paper, code

ReCo: Retrieve and Co-segment for Zero-shot Transfer

Gyungin Shin and Weidi Wie and Samuel Albanie
Advances in Neural Information Processing Systems (NeurIPS), 2022
paper, project page, code

RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection

Hangjie Yuan and Jianwen Jiang and Samuel Albanie and Tao Feng and Ziyuan Huang and Dong Ni and Mingqian Tang
Advances in Neural Information Processing Systems (NeurIPS), 2022
paper

Weakly-supervised Fingerspelling Recognition in British Sign Language Videos

KR Prajwal and Hannah Bull and Liliane Momeni and Samuel Albanie and Gül Varol and Andrew Zisserman
Proceedings of the British Machine Vision Conference (BMVC), 2022
paper

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Teven Le Scao and Angela Fan and Christopher Akiki and Ellie Pavlick and Suzana Ilić and Daniel Hesslow and Roman Castagné and Alexandra Luccioni and François Yvon and Matthias Gallé and others
arXiv preprint arXiv:2211.05100, 2022
paper, code

Crosslingual Generalization through Multitask Finetuning

Niklas Muennighoff and Thomas Wang and Lintang Sutawika and Adam Roberts and Stella Biderman and Teven Le Scao and M Saiful Bari and Sheng Shen and Zheng-Xin Yong and Hailey Schoelkopf and Xiangru Tang and Dragomir Radev and Alham Fikri Aji and Khalid Almubarak and Samuel Albanie and Zaid Alyafeai and Albert Webson and Edward Raff and Colin Raffel
arXiv preprint arXiv:2211.01786, 2022
paper, code, video_summary

Automatic dense annotation of large-vocabulary sign language videos

Liliane Momeni and Hannah Bull and KR Prajwal and Samuel Albanie and Gül Varol and Andrew Zisserman
European Conference on Computer Vision (ECCV), 2022
paper, project page

Unsupervised Salient Object Detection with Spectral Cluster Voting

Gyungin Shin and Samuel Albanie and Weidi Wie
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022
paper, code

Cross Modal Retrieval with Querybank Normalisation

Simion-Vlad Bogolin* and Ioana Croitoru* and Hailin Jin and Yang Liu and Samuel Albanie
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
paper, project page, code, video_summary

Sign Language Video Retrieval with Free-Form Textual Queries

Amanda Duarte and Samuel Albanie and Xavier Giró-i-Nieto and Gül Varol
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
paper, project page

Quantum Self-Supervised Learning

Ben Jaderberg and Lewis W. Anderson and Weidi Xie and Samuel Albanie and M. Kiffner and Dieter Jaksch
Quantum Science and Technology, 2022
paper

Scaling up sign spotting through sign language dictionaries

Gül Varol* and Liliane Momeni* and Samuel Albanie* and Triantafyllos Afouras and Andrew Zisserman
International Journal of Computer Vision, 2022
paper

Audio Retrieval with Natural Language Queries: A Benchmark Study

A Koepke* and Andreea-Maria Oncescu* and João F Henriques and Zeynep Akata and Samuel Albanie
Transactions on Multimedia, 2022
paper, project page, code, demo
Extension of Interspeech 2021 paper with a new dataset

BOBSL: BBC-Oxford British Sign Language Dataset

Samuel Albanie* and Gül Varol* and Liliane Momeni* and Hannah Bull* and Triantafyllos Afouras and Himel Chowdhury and Neil Fox and Bencie Woll and Rob Cooper and Andrew McParland and Andrew Zisserman
Technical Report, 2021
paper, project page, coverage, BBC R&D coverage

All you need are a few pixels: semantic segmentation with PixelPick

Gyungin Shin and Weidi Xie and Samuel Albanie
IEEE International Conference on Computer Vision Workshops (ICCVW), 2021
paper, project page, code
Won best paper at ILDAV ICCVW 2021

TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval

Ioana Croitoru* and Simion-Vlad Bogolin* and Marius Leordeanu and Hailin Jin and Andrew Zisserman and Samuel Albanie and Yang Liu
Proceedings of the IEEE International Conference on Computer Visionp (ICCV), 2021
paper, project page, code
Won the Condensed Movies Challenge at ICCV 2021

Aligning Subtitles in Sign Language Videos

Hannah Bull* and Triantafyllos Afouras* and Gül Varol and Samuel Albanie and Liliane Momeni and Andrew Zisserman
Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021
paper, project page

Audio Retrieval with Natural Language Queries

Andreea-Maria Oncescu* and A. Sophia Koepke* and João F. Henriques and Zeynep Akata and Samuel Albanie
Interspeech, 2021
paper, project page, code, demo
Shortlisted for best student paper at Interspeech

Read and Attend: Temporal Localisation in Sign Language Videos

Gül Varol* and Liliane Momeni* and Samuel Albanie* and Triantafyllos Afouras* and Andrew Zisserman
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
paper, project page

Sign Segmentation with Changepoint-Modulated Pseudo-Labelling

Katrin Renz and Nicolaj C. Stache and Neil Fox and Gül Varol and Samuel Albanie
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021
paper, project page, code

Sign Language Segmentation with Temporal Convolutional Networks

Katrin Renz and Nicolaj C. Stache and Samuel Albanie and Gül Varol
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
paper, project page, code

QUERYD: A Video Dataset with High-Quality Text and Audio Narrations

Andreea-Maria Oncescu and João F. Henriques and Yang Liu and Andrew Zisserman and Samuel Albanie
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
paper, project page, code

Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language Retrieval

Yang Liu* and Qingchao Chen* and Samuel Albanie
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
paper

Mind-the-Gap! Unsupervised Domain Adaptation for Text-Video Retrieval

Qingchao Chen* and Yang Liu* and Samuel Albanie
AAAI, 2021
paper

Watch, read and lookup: learning to spot signs from multiple supervisors

Liliane Momeni* and Gül Varol* and Samuel Albanie* and Triantafyllos Afouras and Andrew Zisserman
ACCV, 2020
paper, project page
Oral; Songde Ma Prize (Best Application Paper)

Explaining the Adaptive Generalisation Gap

Diego Granziol and Samuel Albanie and Xingchen Wan and Stephen J. Roberts
ArXiv, 2020

Movement change detected by optical flow precedes, but does not predict, tail-biting in pigs

Mona Lilian Vestbjerg Larsen and Lene Juul Pedersen and Sandra A. Edwards and Samuel Albanie and Marian Stamp Dawkins
Livestock Science, 2020
paper

Seeing wake words: Audio-visual Keyword Spotting

Liliane Momeni and Triantafyllos Afouras and Themos Stafylakis and Samuel Albanie and Andrew Zisserman
Proceedings of the British Machine Vision Conference, 2020
paper, project page, code

BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues

Samuel Albanie and Gül Varol and Liliane Momeni and Triantafyllos Afouras and Joon Son Chung and Neil Fox and Andrew Zisserman
European Conference on Computer Vision, 2020
paper, project page, code

Disentangled Speech Embeddings Using Cross-Modal Self-Supervision

Arsha Nagrani* and Joon Son Chung* and Samuel Albanie* and Andrew Zisserman
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
paper, project page

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

James Thewlis* and Samuel Albanie* and Hakan Bilen and Andrea Vedaldi
IEEE/CVF International Conference on Computer Vision (ICCV), 2019
paper, project page

Small Steps and Giant Leaps: Minimal Newton Solvers for Deep Learning

João F. Henriques and Sébastien Ehrhardt and Samuel Albanie and Andrea Vedaldi
IEEE/CVF International Conference on Computer Vision (ICCV), 2019
paper, project page, code

Use What You Have: Video retrieval using representations from collaborative experts

Yang Liu* and Samuel Albanie* and Arsha Nagrani* and Andrew Zisserman
Proceedings of the British Machine Vision Conference (BMVC), 2019
paper, project page, code
Note: includes a correction to initially results (details on project page). We thank Valentin Gabeur for identifying the issue.