Name
Title | ||
|---|---|---|
A text-based visual context modulation neural model for multimodal machine translation. |
Abstract | ||
|---|---|---|
•A new approach to utilize image data conditioning on textual data on multimodal machine translation.•A modular neural network based layer to modulate image context with low training cost and maintaining resolution.•Evaluate our model using BLEU and METEOR metrics.•Verify whether our model is effective by ablation studies. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.patrec.2020.06.010 | Pattern Recognition Letters |
Keywords | DocType | Volume |
41A05,41A10,65D05,65D17 | Journal | 136 |
ISSN | Citations | PageRank |
0167-8655 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Soonmo Kwon | 1 | 0 | 0.34 |
| Byung-Hyun Go | 2 | 0 | 0.34 |
| Jong-Hyeok Lee | 3 | 740 | 97.88 |