Selected Publications

Person re-identification is a critical security task for recognizing a person across spatially disjoint sensors. Previous work can be computationally intensive and is mainly based on low-level cues extracted from RGB data and implemented on a PC for a fixed sensor network (such as traditional CCTV). We present a practical and efficient framework for mobile devices (such as smart phones and robots) where high-level semantic soft biometrics are extracted from RGB and depth data. By combining these cues, our approach attempts to provide robustness to noise, illumination, and minor variations in clothing. 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 on the BIWI dataset are preliminary but encouraging.

We present a mobile visual clothing search system whereby a smart phone user can either choose a social networking photo or take a new photo of a person wearing clothing of interest and search for similar clothing in a retail database. From the query image, the person is detected, clothing is segmented, and clothing features are extracted and quantized. The information is sent from the phone client to a server, where the feature vector of the query image is used to retrieve similar clothing products from online databases. The phone’s GPS location is used to re-rank results by retail store location. State of the art work focuses primarily on the recognition of a diverse range of clothing offline and pays little attention to practical applications. Evaluated on a challenging dataset, the system is relatively fast and achieves promising results.

Open Source

Academic makes it easy to create a beautiful website for free using Markdown. Customize anything on your site with widgets, themes, and language packs.

Powering over 100,000 websites.

A RESTful OAuth2 API for the popular Mezzanine Content Management System. The API empowers developers to automate, extend, and combine Mezzanine with other services such as mobile apps.

Powering web and mobile apps by leading design agencies.

Recent & Upcoming Talks

Learn how R Markdown and Academic can help your team write, collaborate, and publish content online and internally. Examples include a landing page and documentation site for your package, a knowledge sharing platform, or a website for your lab/team.

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.

Recent Posts

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

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 …

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

Contact Me