Context-aware multimodal Recurrent Neural Network for automatic image captioning

Simple item page
dc.contributor.advisorGrootjen, F.A.
dc.contributor.advisorVersteeg, R.
dc.contributor.authorRijn, F.W. van
dc.date.issued2016-08-25
dc.description.abstractAutomatic image captioning is a state-of-the-art computer vision task where any image can be described with text. There are cases where an image is supported by text in for instance books or news articles. In this study a context-aware model is proposed that uses not only the image, but also the text surrounding the image to generate a description. The model uses a joint LSTM with attention on both the image and the context and is trained on the Microsoft COCO dataset. This study also explored several setups to represent the text into a feature vector. Results show quantitative and qualitative improvements when context is included. Future directions are automating the feature crafting as well as applying the model to more datasets.en_US
dc.identifier.urihttp://hdl.handle.net/123456789/2634
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationMaster Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeMasteren_US
dc.titleContext-aware multimodal Recurrent Neural Network for automatic image captioningen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Rijn, van,F._MSc_Thesis.pdf
Size:
5.18 MB
Format:
Adobe Portable Document Format
Description:
Thesis text
Download
Collections
Faculteit der Sociale Wetenschappen