Selected Publications

Person re-identification is a critical security task for recognizing a person across spatially disjoint sensors. A practical and efficient framework is presented for mobile devices (such as Google Glass, smart phones, and autonomous vehicles) where high-level semantic soft biometrics are extracted and analysed. This mobile approach may be particularly useful for the identification of persons in areas ill-served by fixed sensors or for tasks where the sensor position and direction need to dynamically adapt to a target. Results are preliminary but encouraging, shedding light on the practical aspects of applying person identification techniques to emerging wearable mobile devices.
In IEEE SITIS, 2015

A mobile visual clothing search system is presented whereby a smart phone user can either choose a social networking image or capture a new photo of a person wearing clothing of interest and search for similar clothing in a large cloud-based ecommerce database. The phone’s GPS location is used to re-rank results by retail store location, to inform the user of local stores where similar clothing items can be tried on.
In IEEE ICME, 2013

Recent Posts

Why you should use Academic and Hugo to create your personal website and how to get started.

CONTINUE READING

Hate your boring alarm clock? In the first part of this tutorial series, we’ll start to explore how to wake up to your favourite Spotify playlist using your Raspberry Pi.

CONTINUE READING

Hate your boring alarm clock? Here’s how to wake up to your favourite Spotify songs using your Ubuntu Linux laptop, desktop, or home theatre PC.

CONTINUE READING

Projects

Academic

A theme/framework for creating beautiful personal or academic websites.

Mezzanine API

A RESTful web API for Mezzanine Content Management System.

Mezzanine Client

A remote CLI and client SDK for Mezzanine API.

Recent & Upcoming Talks

From mail order to becoming a world class pureplay etailer, we are reimagining retail for our 4 million annual customers. Get insight into how we are leveraging cloud GPUs for deep learning to increase discovery of relevant products and transform how data scientists accelerate research. Learn how we are evolving to embrace microservices to become more agile and foster innovative ways of getting our products, services, and experiences to customers at scale. Finally, what is the future for retail technology and has the time finally come for FPGAs?

After completing his PhD in computer vision and machine learning, George Cushen took a job as the first computer vision data scientist at the UK’s second largest pureplay etailer, Shop Direct. Here, he examines the challenges and parallels between working on academic projects as a computer scientist, and working as a data scientist in a mid-size retail company. Having the opportunity to work within an agile startup-like environment within a well-established business requires breaking the habit of spending hours researching and not getting anything “done”, instead working closely with stakeholders and embracing the scope for innovation in order to create practical products and services. So here are some lessons learnt about the differences between academia and industry and how to make the most out of your academic experience.

Contact Me

  • george _at_ cushen.me
  • UK