This task aims to extract named entities and entity types while further predicting segmentation masks of visual objects.
Variants: Twitter-SMNER
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Segmented Multimodal Named Entity Recognition | RiVEG | Advancing Grounded Multimodal Named Entity … | 2024-06-11 |
Recent papers with results on this dataset: