LXMERT

GPTKB entity

Statements (27)
Predicate Object
gptkbp:instanceOf vision-and-language model
gptkbp:architecture transformer-based
gptkbp:author gptkb:Mohit_Bansal
Hao Tan
gptkbp:citation over 1000
gptkbp:developedBy gptkb:Facebook_AI_Research
https://www.w3.org/2000/01/rdf-schema#label LXMERT
gptkbp:inputModalities gptkb:illustrator
gptkb:text
gptkbp:introducedIn 2019
gptkbp:language English
gptkbp:memiliki_tugas visual reasoning
image captioning
visual question answering
gptkbp:notablePublication LXMERT: Learning Cross-Modality Encoder Representations from Transformers
gptkbp:relatedTo gptkb:UNITER
gptkb:ViLBERT
VisualBERT
gptkbp:repository https://github.com/airsplay/lxmert
gptkbp:trainer gptkb:COCO
gptkb:VQA
gptkb:Visual_Genome
GQA
gptkbp:uses cross-modal attention
object detection features
gptkbp:bfsParent gptkb:Visual_Question_Answering
gptkbp:bfsLayer 7