장면 그래프 생성을 위한 물체간의 관계 표현

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 297
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKang, Haeyongko
dc.contributor.authorCAO, NGUYEN NGOCko
dc.contributor.authorThang, Vuko
dc.contributor.authorYoo, Chang-Dongko
dc.date.accessioned2019-11-28T05:21:02Z-
dc.date.available2019-11-28T05:21:02Z-
dc.date.created2019-11-27-
dc.date.issued2019-11-22-
dc.identifier.citation2019 대한전자공학회 추계학술대회-
dc.identifier.urihttp://hdl.handle.net/10203/268670-
dc.description.abstractThis paper considers a scene graph generation algorithm referred to as Relational Object Message Passing to enhance the representation of object relationships. In the scene graph, there are various kinds of relationship pattern depending on both subject and object. For example, given an image of a person and a bicycle, the relationship can be interpreted as the man riding, pushing, leaning against, or even falling off the bicycle. In this paper, for acquiring the good relational representation, two types of message passing algorithms are investigated: it operates on direct graph and undirect graph. The experiments showed the direct graph-based message passing is better than the undirect one, while comparing with the baseline.-
dc.languageEnglish-
dc.publisher사단법인 대한전자공학회-
dc.title장면 그래프 생성을 위한 물체간의 관계 표현-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationname2019 대한전자공학회 추계학술대회-
dc.identifier.conferencecountryKO-
dc.identifier.conferencelocation라카이 샌드파인 리조트, 강릉-
dc.contributor.localauthorYoo, Chang-Dong-
Appears in Collection
EE-Conference Papers(학술회의논문)
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