CITE is a crowd-sourced resource for multimodal discourse: this resource characterises inferences in image-text contexts in the domain of cooking recipes in the form of coherence relations.
Source: CITE: A Corpus of Image-Text Discourse RelationsBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
CiteULike
|
RATE-CSE
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
