Researcher (Assistant Professor) in Computer Vision and Machine Learning for Cultural Heritage in the Center for Cultural Heritage Technology (CCHT). Following a Postdoctoral Researcher position also at the Istituto Italiano di Tecnologia (IIT) working on 3D scene understanding with Dr Alessio Del Bue. Previously Stuart was a Research Associate at University College London (UCL) working with Prof. Tim Weyrich. While at the University of Surrey Stuart completed his PhD and a post doc with Dr John Collomosse. Stuart's research focus is on Visual Big Data problems in the area of Computer Vision, Machine Learning and Digital Humanities. Prior projects have covered 3D Reconstruction, Texture Analysis, Social Media classification, Sketch-based Video Retrieval and Human Pose Retrieval and Domain Adaptation.

Stuart James



 

 

 

About

Starting in 2019 as a Researcher (Assistant Professor) in Computer Vision and Machine Learning for Cultural Heritage following a Postdoctoral Researcher position at Istituto Italiano di Tecnologia (IIT) working on 3D scene understanding with Dr Alessio Del Bue. Prior to which Stuart worked at University College London (UCL) as a Research Associate working with Prof. Tim Weyrich working on 3D reconstruction of large relief art. While at the University of Surrey he worked as a Research Fellow working on Charting the Digital Lifespan – a big social data classification task through the fusion of social image and comments while exploring the social implications.

Stuart’s PhD completed in 2015, also at the University of Surrey, explored how Visual Narratives (Free-Hand sketched storyboards) can be used for Video Retrieval and Synthesis. Contributions involved approaches for Sketch-based Video retrieval and Dance Choreography Synthesis. He also holds a BSc in Computer Science with Games development from the University of Hull.

During 2013 he visited INESC-ID (IST), Portugal for an internship. The research project looked at expanding prior work and integrating the user into the process of choreographic video synthesis. This work focused on Human Computer Interaction developed and interactive process.

During his PhD and Post-doc positions at University of Surrey and UCL, Stuart has enthusiastically engaged with students through teaching opportunities. By working as a lab assistant or marking student work. He has assisted in Computer Vision, Robotics, Research Methods and Programming (C, C++) modules.

Stuart is a member of several professional bodies including ACM, IEEE, BCS; additionally part of specialist groups in research related fields. Stuart regularly peer reviewers for: BMVC, ICIAP, GCH conferences and workshops. As well as the Computers & Graphics and IEEE Transaction on MultiMedia journals.

Additionally, Stuart has worked at JCS Technology for over ten years as IT Manager. Organising the lab infrastructure and services while making informed purchasing decisions. This experience has broadened Stuart’s interaction with industrial technologies and given an understanding which inturn has been used to guide research infrastructure.

PhD Students

  • Supervisor of Mohamed Dahy Abdelaher Elkhouly

    Visual scene understanding through geometry

    with Dr Alessio Del Bue (IIT)
  • Collaborative supervisor of Daniele Giunchi

    How we can sketch in Virtual Environments

    with Prof. Anthony Steed (UCL)

Latest Blog Post

18 Apr 2018 . research . Organising VisArt @ ECCV'18! Comments

This year I’m very excited to be organising the workshop VISART IV with several other great chairs:

Alessio Del Bue, Istituto Italiano di Tecnologia (IIT); Leonardo Impett, EPFL & Biblioteca Hertziana, Max Planck for Art History; Peter Hall, University of Bath; Joao Paulo Costeira, ISR, Instituto Superior Técnico; Peter Bell, Friedrichs-Alexander University Nüremberg.

We hope that this year pushes harder the collaboration between Computer Vision, Digital Humanities and Art History. With aims to generate some fantastic new partnerships to be published at this workshop and future ones.

The further bonding is exemplified by the new track...

Previous posts

newsfeed

  • January 2019

    Researcher (Assist. Prof) in Cultural Heritage in IIT

  • April 2017

    Moved to Istituto Italiano di Tecnologia (IIT)

  • April 2017

    Became Honorary Research Associate at UCL

  • February 2017

    ‘Texture Stationarization: Turning Photos into Tileable Textures’ accpeted to Eurographics’17

  • October 2016

  • August 2016

    Paper ‘Evolutionary Data Purification for Social Media Classification’ accpeted to ICPR’16

  • July 2016

    Attended SIGGRAPH

  • April 2016

    Attended Rank Prize Symposium on Computer Vision and Video Effects

  • April 2016

    Graduated as Doctor of Philosophy

  • February 2016

    Presented poster at SketchX ‘Towards Sketched Visual Narratives for Retrieval’

  • October 2015

    Moved to UCL to work with Professor Tim Weyrich

  • September 2015

    Successfully defended PhD Thesis

Latest Publication

2019 re-OBJ:Jointly learning the foreground and background for object instance re-identification

Conventional approaches to object instance re-identification rely on matching appearances of the target objects among a set of frames. However, learning appearances of the objects alone might fail when there are multiple objects with similar appearance or multiple instances of same object class present in the scene. This paper proposes that partial observations of the background can be utilized to aid in the object re-identification task for a rigid scene, especially a rigid environment with a lot of reoccurring identical models of objects. Using an extension to the Mask R-CNN architecture, we learn to encode the important and distinct information in the background jointly with the foreground relevant to rigid real-world scenarios such as an indoor environment where objects are static and the camera moves around the scene. We demonstrate the effectiveness of our joint visual feature in the re-identification of objects in the ScanNet dataset and show a relative improvement of around 28.25% in the rank-1 accuracy over the deepSort method.

Accepted at ICIAP'19 in Trento, Italy.

See full publication index

Contact

Drop me an email if you are interested in my research or have any questions!