Question aware prediction with candidate answer recommendation for visual question answering후보 답변 예측을 통한 영상 기반 질의응답에 대한 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 656
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorKim, Junmo-
dc.contributor.advisor김준모-
dc.contributor.authorKim, Byungju-
dc.contributor.author김병주-
dc.date.accessioned2017-03-29T02:37:22Z-
dc.date.available2017-03-29T02:37:22Z-
dc.date.issued2016-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=663442&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/221700-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2016.8 ,[iv, 26 p. :]-
dc.description.abstractThis paper describes a novel approach for Visual Question Answering. Our proposed network solves an open-ended problem with candidate answer recommendation, which is generated solely from the given question. Then, we combine the score from our question-aware prediction module and the score from candidate answer recommendation module to determine the final composite score. Our approach uses the bag-of-words (BOW) framework to understand questions, instead of a complex and neural-network-based module-
dc.description.abstracttherefore, an additional dataset to pre-train the language model is not required. Moreover, we show that the BOW framework is capable of extracting the keywords from the question. Although our proposed approach does not achieve the state-of-the-art performance overall, our approach performs the best for certain types of questions with a small amount of training data.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectDeep learning-
dc.subjectVisual question answering-
dc.subjectImage understanding-
dc.subjectCandidate answer recommendation-
dc.subjectConvolution-
dc.subject딥 러닝-
dc.subject영상기반 질의응답-
dc.subject영상 이해-
dc.subject후보 답변 추천-
dc.subject컨볼루션-
dc.titleQuestion aware prediction with candidate answer recommendation for visual question answering-
dc.title.alternative후보 답변 예측을 통한 영상 기반 질의응답에 대한 연구-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0