Josiah Wang

I am a postgraduate student at the School of Computing, University of Leeds. I am currently working under the supervision of Dr. Mark Everingham and Dr. Katja Markert. Prior to that I worked on my M.Sc. dissertation under the supervision of Prof. David Hogg.

My primary research interest is in Visual Object Category Recognition, with an emphasis on multi-modal learning from text and visual data. I am currently exploring the use of text to complement learning object category models from images.

Learning Models for Object Recognition from Natural Language Descriptions

[In BMVC 2009]

Can a system automatically learn an object category model solely from a textual description?

See conference presentation on videolectures.net

Dataset available for download (new!)

• Josiah Wang, Katja Markert, and Mark Everingham. "Learning Models for Object Recognition from Natural Language Descriptions". In Proceedings of the 20th British Machine Vision Conference (BMVC2009), September 2009.
  Download: [ Paper | Presentation Slides | Video Lecture (BMVC2009) | Dataset ]

Theses

• Josiah Wang. "Representation and Recognition of Compound Spatio-Temporal Entities". M.Sc. Thesis. School of Computing, University of Leeds, England, 2007.