Inductive visual localisation: factorised training for superior generalisation
End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to generalise to sequences longer than the ones encountered dur...
| Главные авторы: | , , |
|---|---|
| Формат: | Conference item |
| Язык: | English |
| Опубликовано: |
British Machine Vision Association
2018
|