Toby Perrett

toby.perrett@bristol.ac.uk

Hi! I’m a Senior Research Engineer at Autodesk. Prior to that, I did my postdoc at the University of Bristol, working with Professor Dima Damen, and co-advising Chiara Plizzari and Saptarshi Sinha. I’m a founding member of the team collecting the EPIC Kitchens datasets, and also worked on the Visual AI project led by Professor Andrew Zisserman.

My reseach interests include datasets and benchmarks for Egocentric video , Captioning and 3D understanding.

I’m also interested in improving models when labelled data is scarse or imbalanced

news

Jun 15, 2025	It’s Just Another Day: Unique Captioning by Discriminative Prompting has received the EgoVis Distinguished Paper Award, announced at CVPR 2025.
Mar 2, 2025	I’ve just joined Autodesk as a Senior Research Engineer!
Mar 1, 2025	HD-EPIC: A Highly Detailed Egocentric Video Dataset has been accepted at CVPR 2025!
Feb 7, 2025	HD-EPIC: A Highly Detailed Egocentric Video Dataset is released and on arxiv!
Dec 12, 2024	Received the ACCV Best Paper Award for It’s Just Another Day: Unique Captioning by Discriminative Prompting!
Nov 7, 2024	Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind has been accepted at 3DV 2025!
Oct 15, 2024	Paper accepted at ACCV 2024 as an oral presentation (top 5%)! It’s Just Another Day: Unique Captioning by Discriminative Prompting. Code, benchmarks and models available.
Jun 1, 2024	I’ll be serving as an Area Chair for NeurIPS 2024, on the Datasets and Benchmarks track.
May 23, 2024	I was an Outstanding Reviewer at CVPR 2024!
Apr 9, 2024	New paper on arXiv: Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind. Web. Video. PDF. Code coming soon.
Sep 30, 2023	I was an Outstanding Reviewer at ICCV 2023!
Sep 29, 2023	I gave a talk at the JADE (UK Supercomputing Facility) 2023 event. We discussed why egocentric vision is important, and the computational requirements of egocentric datasets and video understanding models.
Jul 14, 2023	Paper accepted at ICCV 2023! What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations. Code, benchmarks and models available.
May 15, 2023	I gave a talk at Samsung AI Centre Cambridge. We looked at the difficulties of scaling few-shot models to handle long-tail tasks.
Feb 10, 2023	I gave a talk at the University of Exeter Computer Science Seminar Series. This included a brief history of image and video datasets, how their properties can cause models to take shortcuts, and some recent solutions.
Feb 3, 2023	Paper accepted at CVPR 2023! Use Your Head: Improving Long-Tail Video Recognition. Code, benchmarks and models available.
Jan 27, 2023	I gave a talk at the Visual AI group at the University of Oxford on our latest long-tail video work.

selected publications

2025

HD-EPIC: A Highly-Detailed Egocentric Video Dataset

Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha, Omar Emara, Sam Pollard, Kranti Parida, Kaiting Liu, Prajwal Gatti, Siddhant Bansal, Kevin Flanagan, Jacob Chalk, Zhifan Zhu, Rhodri Guerrier, Fahd Abdelazim, Bin Zhu, Davide Moltisanti, Michael Wray, Hazel Doughty, and Dima Damen

In CVPR, 2025

Bib HTML

@inproceedings{perrett2025hdepic,
  author = {Perrett, Toby and Darkhalil, Ahmad and Sinha, Saptarshi and Emara, Omar and Pollard, Sam and Parida, Kranti and Liu, Kaiting and Gatti, Prajwal and Bansal, Siddhant and Flanagan, Kevin and Chalk, Jacob and Zhu, Zhifan and Guerrier, Rhodri and Abdelazim, Fahd and Zhu, Bin and Moltisanti, Davide and Wray, Michael and Doughty, Hazel and Damen, Dima},
  title = {HD-EPIC: A Highly-Detailed Egocentric Video Dataset},
  booktitle = {CVPR},
  year = {2025},
}

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind

Chiara Plizzari, Shubham Goel, Toby Perrett, Jacob Chalk, Angjoo Kanazawa, and Dima Damen

In 3DV, 2025

Bib HTML

@inproceedings{Plizzari2023osnom,
  title = {Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind},
  author = {Plizzari, Chiara and Goel, Shubham and Perrett, Toby and Chalk, Jacob and Kanazawa, Angjoo and Damen, Dima},
  booktitle = {3DV},
  year = {2025},
}

2024

It’s Just Another Day: Unique Captioning by Discriminative Prompting

Toby Perrett, Tengda Han, Dima Damen, and Andrew Zisserman

In ACCV (Best Paper Award), 2024

Bib HTML

@inproceedings{Perrett2024unique,
  title = {It's Just Another Day: Unique Captioning by Discriminative Prompting},
  author = {Perrett, Toby and Han, Tengda and Damen, Dima and Zisserman, Andrew},
  booktitle = {ACCV (Best Paper Award)},
  year = {2024},
}

2023

Use Your Head: Improving Long-Tail Video Recognition

Toby Perrett, Saptarshi Sinha, Tilo Burghardt, Majid Mirmehdi, and Dima Damen

In CVPR, 2023

Bib HTML

@inproceedings{Perrett2023,
  title = {Use Your Head: Improving Long-Tail Video Recognition},
  author = {Perrett, Toby and Sinha, Saptarshi and Burghardt, Tilo and Mirmehdi, Majid and Damen, Dima},
  booktitle = {CVPR},
  year = {2023},
}

2022

Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray

IJCV, 2022

Bib HTML

@article{Damen2022,
  author = {Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria and Furnari, Antonino and Kazakos, Evangelos and Ma, Jian and Moltisanti, Davide and Munro, Jonathan and Perrett, Toby and Price, Will and Wray, Michael},
  journal = {IJCV},
  title = {{Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100}},
  year = {2022},
}

2021

Temporal-Relational CrossTransformers for Few-Shot Action Recognition

Toby Perrett, Alessandro Masullo, Tilo Burghardt, Majid Mirmehdi, and Dima Damen

In CVPR, 2021

Bib HTML

@inproceedings{Perrett2021,
  title = {Temporal-Relational CrossTransformers for Few-Shot Action Recognition},
  author = {Perrett, Toby and Masullo, Alessandro and Burghardt, Tilo and Mirmehdi, Majid and Damen, Dima},
  booktitle = {CVPR},
  year = {2021},
}

2019

DDLSTM: Dual-Domain LSTM for Cross-Domain Action Recognition

Toby Perrett, and Dima Damen

In CVPR, 2019

Bib HTML

2018

Scaling Egocentric Vision: The EPIC-KITCHENS Dataset

Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray

In ECCV, 2018

Bib HTML

@inproceedings{Damen2018EPICKITCHENS,
  author = {Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria and Fidler, Sanja and Furnari, Antonino and Kazakos, Evangelos and Moltisanti, Davide and Munro, Jonathan and Perrett, Toby and Price, Will and Wray, Michael},
  booktitle = {ECCV},
  title = {{Scaling Egocentric Vision: The EPIC-KITCHENS Dataset}},
  year = {2018},
}