UNITER

GPTKB entity

Statements (34)
Predicate Object
gptkbp:instanceOf vision-language model
gptkbp:architecture gptkb:transformation
gptkbp:author gptkb:Faisal_Ahmed
Ahmed El Kholy
Jingjing Liu
Licheng Yu
Linjie Li
Yen-Chun Chen
Yu Cheng
Zhe Gan
gptkbp:citation over 1000 (as of 2023)
gptkbp:developedBy gptkb:Microsoft_Research_Asia
gptkbp:fullName Universal Image-Text Representation
https://www.w3.org/2000/01/rdf-schema#label UNITER
gptkbp:improves gptkb:LXMERT
gptkb:ViLBERT
VisualBERT
gptkbp:inputModalities gptkb:illustrator
gptkb:text
gptkbp:introducedIn 2019
gptkbp:language English
gptkbp:notablePublication UNITER: Learning Universal Image-Text Representations
gptkbp:pretrainingTasks masked language modeling
image region alignment
word-region alignment
gptkbp:publishedIn ECCV 2020
gptkbp:repository https://github.com/ChenRocks/UNITER
gptkbp:trainer image-text pairs
gptkbp:usedFor visual reasoning
image-text retrieval
visual question answering
gptkbp:bfsParent gptkb:UNITER_Award
gptkb:Visual_Question_Answering
gptkbp:bfsLayer 7