Learning to recognise visual content from textual annotation
This thesis explores how machine learning can be applied to the task of learning to recognise visual content from different forms of textual annotation, bringing together computer vision and natural language processing. The data used in the thesis is taken from real world sources including broadcast...
Main Author: | Marter, Matthew John |
---|---|
Other Authors: | Bowden, Richard ; Hadfield, Simon |
Published: |
University of Surrey
2019
|
Subjects: | |
Online Access: | https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.767000 |
Similar Items
-
Visual feature learning
by: Zhu, Fan
Published: (2015) -
Learning discriminative feature representations for visual categorization
by: Liu, Li
Published: (2015) -
Machine learning for human performance capture from multi-viewpoint video
by: Trumble, Matthew
Published: (2019) -
Automatic edema segmentation and quantification from cardiac MRI with 3D visualization
by: Kadir, Kushsairy Abdul
Published: (2012) -
Remote High-definition Visual Monitoring of cetaceans from offshore vessels and platforms
by: Baruwa, Ladipo
Published: (2017)