DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Junmo | - |
dc.contributor.advisor | 김준모 | - |
dc.contributor.author | Kim, Byungju | - |
dc.contributor.author | 김병주 | - |
dc.date.accessioned | 2017-03-29T02:37:22Z | - |
dc.date.available | 2017-03-29T02:37:22Z | - |
dc.date.issued | 2016 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=663442&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/221700 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2016.8 ,[iv, 26 p. :] | - |
dc.description.abstract | This 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.abstract | therefore, 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.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning | - |
dc.subject | Visual question answering | - |
dc.subject | Image understanding | - |
dc.subject | Candidate answer recommendation | - |
dc.subject | Convolution | - |
dc.subject | 딥 러닝 | - |
dc.subject | 영상기반 질의응답 | - |
dc.subject | 영상 이해 | - |
dc.subject | 후보 답변 추천 | - |
dc.subject | 컨볼루션 | - |
dc.title | Question aware prediction with candidate answer recommendation for visual question answering | - |
dc.title.alternative | 후보 답변 예측을 통한 영상 기반 질의응답에 대한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.