Toby Perrett

toby.perrett@bristol.ac.uk

Hi! I’m a senior postdoctoral researcher 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 am also working on the Visual AI project led by Professor Andrew Zisserman.

My research is on video understanding, particularly from egocentric cameras. I’m interested in improving models and representations when labelled data is scarse or imbalanced, and exploring how to generalise to unseen domains. I’m currently looking at how we can exploit 3D and long-term temporal knowledge to improve reasoning in these situations.

news

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

2024

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

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

In ACCV, 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},
  year = {2024},
}

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 ArXiv, 2024

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 = {ArXiv},
  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},
}