DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, Seung-Ho | ko |
dc.contributor.author | Go, Bo-Won | ko |
dc.contributor.author | Choi, Ho-Jin | ko |
dc.date.accessioned | 2020-06-22T03:20:19Z | - |
dc.date.available | 2020-06-22T03:20:19Z | - |
dc.date.created | 2020-06-11 | - |
dc.date.created | 2020-06-11 | - |
dc.date.created | 2020-06-11 | - |
dc.date.created | 2020-06-11 | - |
dc.date.created | 2020-06-11 | - |
dc.date.issued | 2019-03-02 | - |
dc.identifier.citation | The 6th IEEE International Conference on Big Data and Smart Computing (BigComp2019), pp.355 - 358 | - |
dc.identifier.issn | 2375-933X | - |
dc.identifier.uri | http://hdl.handle.net/10203/274726 | - |
dc.description.abstract | In this paper, We propose a novel video captioning model that utilizes context information of correlated clips. Unlike the ordinary "one clip - one caption" algorithms, we concatenate multiple neighboring clips as a chunk and train the network in "one chunk - multiple caption" manner. We train and evaluate our algorithm using M-VAD dataset and report the performance of caption and keyword generation. Our model is a foundation model for generating a video story using several captions. Therefore, in this paper, we focus on caption generation for several videos and trend analysis of the generated captions. In the experiments, we show the performance of intermediate results of our model in both qualitative and quantitative aspects. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Multiple Videos Captioning Model for Video Storytelling | - |
dc.type | Conference | - |
dc.identifier.wosid | 000469779800058 | - |
dc.identifier.scopusid | 2-s2.0-85064714962 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 355 | - |
dc.citation.endingpage | 358 | - |
dc.citation.publicationname | The 6th IEEE International Conference on Big Data and Smart Computing (BigComp2019) | - |
dc.identifier.conferencecountry | JA | - |
dc.identifier.conferencelocation | Kyoto | - |
dc.identifier.doi | 10.1109/BIGCOMP.2019.8679213 | - |
dc.contributor.localauthor | Choi, Ho-Jin | - |
dc.contributor.nonIdAuthor | Go, Bo-Won | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.