What I do...
Visual Media production is a large and growing industry, and as a result have a number of research challenges within it. Multiple viewpoint video is becoming commonplace in film and music video production, where shots are captured using multiple, wide-spaced, synchronized cameras for later editing. Within this i have two research questions
What I have researched before:
Every day, users struggle with the ever increasing quantity of data available to them. Trying to find “that” photo they took on holiday last year, the video on YouTube they were watching at their friends last week, or the news article someone mentioned at work. I am working on developing approaches that can automatically understand what is happening in huge amounts of very diverse types of media including, photos, documents, audio and videos, without needing to tell the computer beforehand what it is looking at.
- Two arXiv versions of submitted journal around interactive active learning style grouping of media and inpainting to remove actors from multi view video, now available in the publications
- ImageCLEF 2016 Scalable Concept Image Annotation Challenge results now in check out the summary papers
- 6 Excellent Technical Meetings arranged for 2016, with the BMVA on topics such as deep learning, remote sensing, sketch, plant and automotive applications of computer vision and machine learning - check them out and register
- Geometric Mining: Scaling Geometric Hashing to Large Datasets, work presented at ICCV15 Workshop VSM using geometric hashing to perform object recognition with no labelled annotated data
- Data mining for Action Recognition Work accepted for ACCV 2014 in Singapore with myself and Richard Bowden on using dense trajectories within a data mining framework, to achieve state of the art results on the Hollywood2 action recognition dataset.