PhD Transfer Talk

Video content relating to a PhD Transfer talk in the School of Computing

Karen Carey - Transfer Talk - 10th April 2014

Video Category: 
Transfer Talk
Karen_Carey

Title: Improving ‘Concept Evaluation’ in the Exploratory Stages of Enterprise Mobile Service Development

Phelim Murnion - Transfer Talk - 10th March 2014

Video Category: 
Transfer Talk
Phelim_Murnion

Title: Measuring the Impact of Learning Analytics in Educational Management

Zhenxing Zhang - Transfer Talk - 26th September 2013

Video Category: 
Transfer Talk
Zhenxing Zhang

Title: Interactive Object Retrieval in Large Video Collections

Supervisor: Dr. Cathal Gurrin

Abstract:
Information retrieval technologies help people to maximize the value of information sources by enabling them to find information precisely and rapidly from massive archives. With the rapid growth of data capturing, storage, and transmission technologies, vast amounts of video data are publicly accessible for personal and enterprise customers and as a result, internet users spend more time on interaction with video content. Fast and efficient multimedia retrieval applications are widely needed for those archives. In this work, I analyse, index and retrieve videos based on the objects contained therein, not relying on Youtube-style manual annotation.  A high quality and useful framework based on Machine Learning technologies is proposed for solving this computer vision problem. This research is being undertaken as part of the annual TRECVid video search comparative evaluation framework. In this talk, I will present the research methodologies, evaluation datasets and proposed experiments that form my PhD topic. It is expected that the research result can inform the next generation of multimedia information access tools which can make it easier for any user to locate content from ever increasing, unannotated, digital video archives.

Lijuan Zhou - Transfer Talk - 3rd May 2013

Video Category: 
Transfer Talk
Lijuan Zhou

Title: Linkage-based organisation of LifeLog Archives

Supervisor: Dr. Cathal Gurrin

Abstract: As a result of the continual advances in digital sensing technologies, the creation, organisation and beneficial exploitation of lifelogs is becoming an increasing important research topic. Lifelogs are typically constructed using a range of wearable sensors and segmented into discrete events before being made accessible by a search or browsing tool.  In this work, we are developing a new model of lifelog data organisation called the MemoryMesh. The MemoryMesh is essentially a densely linked hypermedia of live experience events. In this research, we firstly propose to use a new suite of sensors based on wearable and ambient living sensors to generate a lifelog. This sensor data will be utilised for personal activity recognition, which will act as both input to the event segmentation process and an annotation source for the resultant events.  This improved event segmentation model, with broad semantic annotations, forms the basis of a new type of lifelog organisation methodology called the MemoryMesh that is inspired by the associative nature of human memory.  Using the MemoryMesh, we evaluate the applicability of WWW-derived linkage analysis algorithms to mine the structure as a source for knowledge extraction and to support user access and retrieval. This research is evaluated using both user studies and a test collection methodology.

Syndicate content