Deep Multimodal Information Retrieval
GPTKB entity
Statements (43)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
research
|
| gptkbp:appliesTo |
search engines
recommendation systems multimedia analysis medical information retrieval |
| gptkbp:field |
gptkb:machine_learning
information retrieval multimodal learning |
| gptkbp:focusesOn |
retrieving information from multiple modalities
|
| gptkbp:goal |
improve retrieval accuracy across modalities
|
| https://www.w3.org/2000/01/rdf-schema#label |
Deep Multimodal Information Retrieval
|
| gptkbp:includes |
text retrieval
image retrieval video retrieval audio retrieval |
| gptkbp:relatedTo |
gptkb:ALIGN
gptkb:CLIP feature extraction benchmarking evaluation metrics semantic matching multimodal search cross-modal retrieval multimodal fusion multimodal datasets Visual Semantic Embedding multimodal retrieval models zero-shot retrieval |
| gptkbp:uses |
convolutional neural networks
deep learning neural networks self-supervised learning transformers supervised learning recurrent neural networks unsupervised learning contrastive learning representation learning large-scale datasets attention mechanisms joint embedding spaces |
| gptkbp:bfsParent |
gptkb:DMIR
|
| gptkbp:bfsLayer |
8
|