Latest news!

Artistic video demonstration of human body parsing
A fun artistic video showing off various human body parsing methods. Won 2nd Prize at the 2019 ZEISS Photography Competition:

Low-cost AI heart monitor developed by Cambridge start-up
Excited to be part of Cambridge Heartwear which uses its wireless monitor to improve the detection of irregular and dangerous heart rhythms. Full story here!
New human body parsing system
Check out the new demo video below of our real-time multi-person clothing segmentation system:

Real-time human body parsing on mobile device.
2018 - Research now sponsored by Toyota
Excited to now have my research on high level understanding of humans in images and video sponsored by Toyota.
BMVC 2017 paper acceptance!
Real-time Factored ConvNets: Extracting the X Factor in Human Parsing, see video and publications below
Moved beginning of 2017 to work at the University of Cambridge!
Now working with Prof. Roberto Cipolla at the University of Cambridge on the Deep-Insight project sponsored by SeeQuestor.
Personalization code + YouTube Pose dataset release
The YouTube Pose dataset can now be downloaded: YouTube_Pose_dataset_1.0.zip

Personalization code: https://github.com/jjcharles/personalized_pose
ECCV 2016 workshop paper acceptance
Virtual Immortality: Reanimating characters from TV shows, see publications
CVPR 2016 paper acceptance
Personalizing Human Video Pose Estimation, see publications
Personalized human video pose estimation and new pose dataset!
New video dataset for upper body pose estimation, see publications
ICCV 2015 paper acceptance
Flowing ConvNets for human pose estimation in videos, see publications
Best poster award BMVC 2014
Upper body pose estimation with temporal sequential forests, see publications

Current project

High level understanding of humans in images and video

Developing new Deep Learning based methods for analysing humans in images and video

At the University of Cambridge I work with Prof. Roberto Cipolla on an exciting research project sponsored by Toyota to develop innovative Deep Learning based solutions for automatic understanding of humans in images and video.

Publications

Szymanowicz, S. and Charles, J. and Cipolla, R.
Discrete neural representations for explainable anomaly detection
Winter Conference on Applications of Computer Vision, 2022

bibtex:
@InProceedings{szymanowicz21,
  author       = "Szymanowicz, S. and Charles, J. and Cipolla, R.",
  title        = "Discrete neural representations for explainable anomaly detection",
  booktitle    = "Winter Conference on Applications of Computer Vision",	
  year         = "2022",
}

Szymanowicz, S. and Charles, J. and Cipolla, R.
X-MAN: Explaining multiple sources of anomalies in video
CVPR Workshop on Fair, Data Efficient and Trusted Computer Vision, 2021

bibtex:
@InProceedings{szymanowicz21,
  author       = "Szymanowicz, S. and Charles, J. and Cipolla, R.",
  title        = "X-MAN: Explaining multiple sources of anomalies in video",
  booktitle    = "CVPR Workshop on Fair, Data Efficient and Trusted Computer Vision",	
  year         = "2021",
}

Howells, B. and Charles, J. and Cipolla, R.
Real-time analogue gauge transcription on mobile phone
Mobile AI workshop in conjuction with CVPR, 2021

bibtex:
@InProceedings{howells21,
  author       = "Howells, B. and Charles, J. and Cipolla, R.",
  title        = "Real-time analogue gauge transcription on mobile phone",
  booktitle    = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops",	
  year         = "2021",
}

Charles, J. and Bucciarelli, S. and Cipolla, R.
Scaling digital screen reading with one-shot learning and re-identification
Winter Conference on Applications of Computer Vision, 2021

bibtex:
@InProceedings{Charles21,
  author       = "Charles, J. and Bucciarelli, S. and Cipolla, R.",
  title        = "Scaling digital screen reading with one-shot learning and re-identification",
  booktitle    = "Proc. of Winter Conference on Applications of Computer Vision",	
  year         = "2021",
}

Kok, F. and Charles, J. and Cipolla, R.
FootNet: An Efficient Convolutional Network for Multiview 3D Foot Reconstruction
Asian Conference on Computer Vision, 2020

bibtex:
@InProceedings{kok2020footnet,
  author       = "Kok, F. and Charles, J. and Cipolla, R.",
  title        = "FootNet: An Efficient Convolutional Network for Multiview 3D Foot Reconstruction",
  booktitle    = "Proc. of Asian Conference on Computer Vision",	
  year         = "2020",
}

Biggs, B. and Boyne, O. and Charles, J. and Fitzgibbon, A. and Cipolla, R.
Who left the dogs out: 3D animal reconstruction with expectation maximization in the loop
European Conference on Computer Vision, 2020

bibtex:
@InProceedings{biggs2020wldo,
  author       = "Biggs, B. and Boyne, O. and Charles, J. and Fitzgibbon, A. and Cipolla, R.",
  title        = "{W}ho left the dogs out: {3D} animal reconstruction with expectation maximization in the loop",
  booktitle    = "Proc. of European Conference on Computer Vision",	
  year         = "2020",
}

Charles, J. and Bucciarelli, S. and Cipolla, R.
Real-time screen reading: reducing domain shift for one-shot learning
British Machine Vision Conference, 2020

bibtex:
@InProceedings{Charles20,
  author       = "Charles, J. and Bucciarelli, S. and Cipolla, R.",
  title        = "Real-time screen reading: reducing domain shift for one-shot learning",
  booktitle    = "Proc. of British Machine Vision Conference",	
  year         = "2020",
}

Charles, J. and Budvytis, I. and Cipolla, R.
Real-time Factored ConvNets: Extracting the X factor in Human Parsing
British Machine Vision Conference, 2017

bibtex:
@InProceedings{Charles17,
  author       = "Charles, J. and Budvytis, I. and Cipolla, R.",
  title        = "Real-time Factored ConvNets: Extracting the X factor in Human Parsing",
  booktitle    = "Proc. of British Machine Vision Conference",	
  year         = "2017",
}

Duckworth, P. and Alomari, M. and Charles, J. and Hogg, D. C. and Cohn, A. G.
Latent Dirichlet Allocation for Unsupervised Activity Analysis on an Autonomous Mobile Robot
Association for the Advancement of Artificial Intelligence, 2017

bibtex:
@InProceedings{Duckworth17,
  author       = "Duckworth, P. and Alomari, M. and Charles, J. and Hogg, D. C. and Cohn, A. G.",
  title        = "Latent Dirichlet Allocation for Unsupervised Activity Analysis on an Autonomous Mobile Robot",
  booktitle    = "Proc. of Association for the Advancement of Artificial Intelligence {(AAAI)}",	
  year         = "2017",
}

Charles, J. and Magee, D. and Hogg, D.
Virtual Immortality: Reanimating characters from TV shows
VARVAI workshop in-conjuction with ECCV, 2016

bibtex:
@InProceedings{Charles16b,
  author       = "Charles, J. and Magee, D. and Hogg.",
  title        = "Virtual Immortality: Reanimating characters from TV shows",
  booktitle    = "ECCV Workshop on Virtual/Augmented Reality for Visual Artificial Intelligence (VARVAI)",	
  year         = "2016",
}

Charles, J. and Pfister, T. and Magee, D. and Hogg, D. Zisserman, A.
Personalizing Human Video Pose Estimation
Conference on Computer Vision and Pattern Recognition, 2016 (Oral)

bibtex:
@InProceedings{Charles16,
  author       = "Charles, J. and Pfister, T. and Magee, D. and Hogg, D. Zisserman, A.",
  title        = "Personalizing Human Video Pose Estimation",
  booktitle    = "Conference on Computer Vision and Pattern Recognition",	
  year         = "2016",
}

Pfister, T. and Charles, J. and Zisserman, A.
Flowing ConvNets for Human Pose Estimation in Videos
International Conference on Computer Vision, 2015

bibtex:
@InProceedings{Pfister15,
  author       = "Pfister, T. and Charles, J. and Zisserman, A.",
  title        = "Flowing ConvNets for Human Pose Estimation in Videos",
  booktitle    = "International Conference on Computer Vision",
  year         = "2015",
}

Charles, J. and Pfister, T. and Magee, D. and Hogg, D. and Zisserman, A.
Upper body pose estimation with temporal sequential forests
British Machine Vision Conference, 2014
Best Poster Award!

bibtex:
@InProceedings{Charles14b,
  author       = "Charles, J. and Pfister, T. and Magee, D. and Hogg, D. and Zisserman, A.",
  title        = "Upper Body Pose Estimation with Temporal Sequential Forests",
  booktitle    = "British Machine Vision Conference",
  year         = "2014",
}

Pfister, T. and Simonyan, K. and Charles, J. and Zisserman, A.
Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos
Asian Conference on Computer Vision, 2014

bibtex:
@InProceedings{Pfister14a,
  author       = "Pfister, T. and Simonyan, K. and Charles, J. and Zisserman, A.",
  title        = "Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos",
  booktitle    = "Asian Conference on Computer Vision",
  year         = "2014",
}

Pfister, T. and Charles, J. and Zisserman, A.
Domain-adaptive Discriminative One-shot Learning of Gestures
European Conference on Computer Vision, 2014

bibtex:
@InProceedings{Pfister14,
  author       = "Pfister, T. and Charles, J. and Zisserman, A.",
  title        = "Domain-adaptive Discriminative One-shot Learning of Gestures",
  booktitle    = "European Conference on Computer Vision",
  year         = "2014",
}

Charles, J. and Pfister, T. and Everingham, M. and Zisserman, A.
Automatic and Efficient Human Pose Estimation for Sign Language Videos
International Journal of Computer Vision, 2014

bibtex:
@Article{Charles14a,
  author       = "Charles, J. and Pfister, T. and Everingham, M. and Zisserman, A.",
  title        = "Automatic and Efficient Human Pose Estimation for Sign Language Videos",
  journal      = "International Journal of Computer Vision",
  volume       = "110",
  number       = "1",
  pages        = "70-90",
  year         = "2014",
}

Charles, J. and Pfister, T. and Magee, D. and Hogg, D. and Zisserman, A.
Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts
British Machine Vision Conference, 2013 (Oral)

bibtex:
@InProceedings{@InProceedings{Charles13,
  author       = "Charles, J. and Pfister, T. and Magee, D. and Hogg, D. and Zisserman, A.",
  title        = "Domain Adaptation for Upper Body Pose Tracking in Signed {TV} Broadcasts",
  booktitle    = "British Machine Vision Conference",
  year         = "2013",
}

Pfister, T. and Charles, J. and Zisserman, A.
Large-scale Learning of Sign Language by Watching TV (Using Co-occurrences)
British Machine Vision Conference, 2013

bibtex:
@InProceedings{Pfister13,
  author       = "Pfister, T. and Charles, J. and Zisserman, A.",
  title        = "Large-scale Learning of Sign Language by Watching {TV} (Using Co-occurrences)",
  booktitle    = "British Machine Vision Conference",
  year         = "2013",
}

Pfister, T. and Charles, J. and Everingham, M. and Zisserman, A.
Automatic and Efficient Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts
British Machine Vision Conference, 2012 (Oral)
Best Paper Honourable Mention & Best Video Award!

bibtex:
@InProceedings{Pfister12,
  author       = "Pfister, T. and Charles, J. and Everingham, M. and Zisserman, A.",
  title        = "Automatic and Efficient Long Term Arm and Hand Tracking for Continuous Sign Language {TV} Broadcasts",
  booktitle    = "British Machine Vision Conference",
  year         = "2012",
}

Charles, J. and Everingham, M.
Learning shape models for monocular human pose estimation from the Microsoft Xbox Kinect
CDC4CV workshop inconjuction with ICCV, 2011 (Oral)

bibtex:
@InProceedings{charles2011b,
author    = "Charles, J. and Everingham, M.",
title     = "Learning shape models for monocular human pose estimation from the Microsoft Xbox Kinect",
booktitle = "1st IEEE Workshop on Consumer Depth Cameras for Computer Vision (CDC4CV), in conjunction with ICCV 2011",
year      = "2011",
}

Jiang, J. and Charles, J.and Demestichas, K.
EcoGem: A European Framework-7 project towards cooperative and intelligent optimization of travel planning and energy saving for drivers of fully electric vehicles
IEEE Vehicular Technology Magazine, 2011

bibtex:
@Article{Jiang11,
title     = "ECOGEM: A European framework-7 project",
author    = "Jiang, J. and Charles, J.and Demestichas, K.",
journal   = "Vehicular Technology Magazine, IEEE",
volume    = "6",
number    = "3",
pages     = "22--26",
year      = "2011",
}

Charles, J.J.
Automatic recognition of complete palynomorphs in digital images
Machine Vision and Applications, 2011

bibtex:
@Article{Charles11a,
author       = "Charles, J.J.",
title        = "Automatic recognition of complete palynomorphs in digital images",
journal      = "Machine Vision and Applications",
volume       = "22",
number       = "1",
pages        = "53-60",
year         = "2011",
}

Charles, J.J. and Kuncheva, L.I. and Wells, B. and Lim, I.S.
Stability of Kerogen Classification with Regard to Image Segmentation
Mathematical Geosciences, 2009

bibtex:
@Article{Charles09,
author     ="Charles, J.J. and Kuncheva, L.I. and Wells, B. and Lim, I.S.",
title      ="Stability of Kerogen Classification with Regard to Image Segmentation",
journal    ="Mathematical Geosciences",
volume     ="41",
number     ="4",
pages      ="475-486",
year       ="2009",
}

J.J. Charles and L.I. Kuncheva and B. Wells and I.S. Lim
Object segmentation within microscope images of palynofacies
Computers & Geosciences, 2008

bibtex:
@InProceedings{Charles08c,
author      = "J.J. Charles and L.I. Kuncheva and B. Wells and I.S. Lim",
title       = "Object segmentation within microscope images of palynofacies ",
journal     = "Computers & Geosciences ",
volume      = "34",
number      = "6",
pages       = "688 - 698",
year        = "2008",
}

Charles, J. and Kuncheva, L. and Wells, B. and Lim, I
Background segmentation in microscope images
Computer Vision Theory and Applications, 2008

bibtex:
@InProceedings{Charles08b,
  author       = "Charles, J. and Kuncheva, L. and Wells, B. and  Lim, I",
  title        = "Background segmentation in microscope images",
  booktitle    = "Computer Vision Theory and Applications",
  year         = "2008",
}

Kuncheva, L.I. and Charles, J.J. and Miles, N. and Collins, A. and Wells, B. and Lim, I.S.
Automated kerogen classification in microscope images of dispersed kerogen preparation
Mathematical Geosciences, 2008

bibtex:
@Article{Charles08a,
  author       = "Kuncheva, L.I. and Charles, J.J. and Miles, N. and Collins, A. and Wells, B. and Lim, I.S.",
  title        = "Automated kerogen classification in microscope images of dispersed kerogen preparation",
  pages        = "639-652",
  journal      = "Mathematical Geosciences",
  year         = "2008",
  volume       = "40",
  number       = "6",
}

Charles, J. and Kuncheva, L. and Wells, B. and Lim, I
An evaluation measure of image segmentation based on object centres
LNCS Image analysis and recognition, 2006

bibtex:
@incollection{Charles06,
  author       = "Charles, J. and Kuncheva, L. and Wells, B. and  Lim, I",
  title        = "An evaluation measure of image segmentation based on object centres",
  pages        = "283--294",
  volume       = "4141",
  series       = "Lecture Notes in Computer Science",
  booktile    = "Image Analysis and Recognition",
  year         = "2006",
}