Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12188/23134
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Smilevski, Marko | en_US |
dc.contributor.author | Lalkovski, Ilija | en_US |
dc.contributor.author | Madjarov, Gjorgji | en_US |
dc.date.accessioned | 2022-09-27T12:58:58Z | - |
dc.date.available | 2022-09-27T12:58:58Z | - |
dc.date.issued | 2018-09-17 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.12188/23134 | - |
dc.description.abstract | Recent research in AI is focusing towards generating narrative stories about visual scenes. It has the potential to achieve more human-like understanding than just basic description generation of imagesin-sequence. In this work, we propose a solution for generating stories for images-in-sequence that is based on the Sequence to Sequence model. As a novelty, our encoder model is composed of two separate encoders, one that models the behaviour of the image sequence and other that models the sentence-story generated for the previous image in the sequence of images. By using the image sequence encoder we capture the temporal dependencies between the image sequence and the sentence-story and by using the previous sentence-story encoder we achieve a better story flow. Our solution generates long human-like stories that not only describe the visual context of the image sequence but also contains narrative and evaluative language. The obtained results were confirmed by manual human evaluation. | en_US |
dc.publisher | Springer, Cham | en_US |
dc.subject | Visual storytelling · Deep learning · Vision-to-language | en_US |
dc.title | Stories for images-in-sequence by using visual and narrative components | en_US |
dc.type | Proceedings | en_US |
dc.relation.conference | International Conference on Telecommunications | en_US |
item.fulltext | With Fulltext | - |
item.grantfulltext | open | - |
Appears in Collections: | Faculty of Computer Science and Engineering: Conference papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1805.05622.pdf | 2.76 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.