ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph

GPTKB entity

Statements (19)
Predicate Object
gptkbp:instanceOf gptkb:academic_journal
gptkbp:author gptkb:Ming_Zhou
Daxin Jiang
Jian Yin
Linjun Shou
Ming Gong
Nan Duan
Weijie Wang
gptkbp:focusesOn vision-language representation learning
gptkbp:hasMethod incorporating scene graph knowledge into vision-language models
https://www.w3.org/2000/01/rdf-schema#label ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph
gptkbp:improves image-text retrieval
visual question answering
gptkbp:language English
gptkbp:publicationYear 2021
gptkbp:publishedIn gptkb:AAAI_2021
gptkbp:uses scene graph knowledge
gptkbp:bfsParent gptkb:ERNIE-ViL
gptkbp:bfsLayer 6