Cargando…
Read, spot and translate
We propose multimodal machine translation (MMT) approaches that exploit the correspondences between words and image regions. In contrast to existing work, our referential grounding method considers objects as the visual unit for grounding, rather than whole images or abstract image regions, and perf...
| Autores principales: | , , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Springer Netherlands
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550676/ https://www.ncbi.nlm.nih.gov/pubmed/34776635 http://dx.doi.org/10.1007/s10590-021-09259-z |