Jonathan Munro

University of BristolĀ· jonathan.munro@bristol.ac.uk

I am a final year PhD student at University of Bristol supervised Dr Dima Damen. My interests include fine-grained video understanding and transfer learning with a focus on domain adaptation for action recognition.

Projects

Multi-Modal Domain Adaptation for Fine-grained Action Recogntition

Fine-grained action recognition datasets exhibit environmental bias, where multiple video sequences are captured from a limited number of environments. Training a model in one environment and deploying in another results in a drop in performance due to an unavoidable domain shift. Unsupervised Domain Adaptation (UDA) approaches have frequently utilised adversarial training between the source and target domains. However, these approaches have not explored the multi-modal nature of video within each domain. In this work we exploit the correspondence of modalities as a self-supervised alignment approach for UDA in addition to adversarial alignment. We test our approach on three kitchens from our large-scale dataset, EPIC-Kitchens, using two modalities commonly employed for action recognition: RGB and Optical Flow. We show that multi-modal self-supervision alone improves the performance over source-only training by 2.4 on average. We then combine adversarial training with multi-modal self-supervision, showing that our approach outperforms other UDA methods by 3%.

EPIC-KITCHENS-100

The extended largest dataset in first-person (egocentric) vision; multi-faceted, audio-visual, non-scripted recordings in native environments - i.e. the wearers' homes, capturing all daily activities in the kitchen over multiple days. Annotations are collected using a novel 'Pause-and-Talk' narration interface.

Publications

Recaling egocentric vision

ArXiv

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

2020

The epic-kitchens dataset: Collection, challenges and baselines

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

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

2020

Multi-modal domain adaptation for fine-grained action recogntition

Computer Vision and Pattern Recognition(CVPR)

Jonathan Munro, Dima Damen

2020

Scaling egocentric vision: The EPIC-KITCHENS dataset

European Conference on Computer Vision (ECCV)

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

2018

Interships

Data Science Intern

Intent HQ

Summer 2017

Applications Engineering Intern

ARM

Summer 2015

Applications Engineering Intern

ARM

Summer 2014

Education

University of Bristol

PhD Computer Science
August 2017 - Now

University of Bristol

MEng Computer Science and Electronics

First

2013 - 2017

Skills

  • TensorFlow
  • PyTorch PyTorch


Awards & Certifications

  • EPSRC Scholarship 2017-2021