JIPS (한국정보처리학회)
Current Result Document :
| 한글제목(Korean Title) |
Multimodal Context Embedding for Scene Graph Generation |
| 영문제목(English Title) |
Multimodal Context Embedding for Scene Graph Generation |
| 저자(Author) |
Gayoung Jung
Incheol Kim
|
| 원문수록처(Citation) |
VOL 16 NO. 06 PP. 1250 ~ 1260 (2020. 12) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.
|
| 키워드(Keyword) |
Deep Neural Network
Multimodal Context
Relationship Detection
Scene Graph Generation
|
| 파일첨부 |
PDF 다운로드
|
