Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO
42568Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Multimodal Models
Method |
evaluatedIn |
Image Captioning Datasets
Material |
|
Multitask Dual Encoder
Method |
trainedOn |
Image Captioning Datasets
Material |
|
Unimodal Models
OtherEntity |
evaluatedIn |
Image Captioning Datasets
Material |