Statements (56)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Model
|
| gptkbp:bfsLayer |
6
|
| gptkbp:bfsParent |
gptkb:UNITER
|
| gptkbp:applies_to |
object detection
video analysis scene understanding image retrieval image captioning visual question answering |
| gptkbp:based_on |
gptkb:BERT
|
| gptkbp:can_be_used_with |
text and image data
|
| gptkbp:developed_by |
gptkb:Facebook_AI_Research
AI applications |
| gptkbp:has |
pre-trained models
|
| gptkbp:has_achievements |
state-of-the-art results
|
| https://www.w3.org/2000/01/rdf-schema#label |
Vi LBERT
|
| gptkbp:improves |
multimodal understanding
|
| gptkbp:introduced |
gptkb:2019
|
| gptkbp:is_cited_in |
numerous papers
|
| gptkbp:is_compared_to |
other multimodal models
|
| gptkbp:is_compatible_with |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
| gptkbp:is_considered_as |
a significant advancement
|
| gptkbp:is_discussed_in |
AI conferences
|
| gptkbp:is_documented_in |
research papers
|
| gptkbp:is_evaluated_by |
accuracy metrics
F1 score benchmark datasets mean average precision real-world tasks |
| gptkbp:is_influenced_by |
BERT architecture
|
| gptkbp:is_influential_in |
AI development
|
| gptkbp:is_integrated_with |
various applications
|
| gptkbp:is_optimized_for |
gptkb:benchmark
efficiency scalability |
| gptkbp:is_part_of |
deep learning frameworks
AI research community AI toolkits multimodal models |
| gptkbp:is_recognized_for |
innovation in AI
|
| gptkbp:is_related_to |
visual-language tasks
|
| gptkbp:is_supported_by |
community contributions
open-source community |
| gptkbp:is_used_for |
computer vision
natural language processing |
| gptkbp:is_used_in |
gptkb:academic_research
commercial products research applications |
| gptkbp:supports |
transfer learning
|
| gptkbp:training |
large datasets
supervised learning unsupervised learning self-supervised learning |
| gptkbp:uses |
gptkb:Transformers_character
|
| gptkbp:utilizes |
attention mechanisms
|