Multimodal grid features and cell pointers for scene text visual question answering

出版年份 2021 全文链接

标题

作者

关键词

Deep learning, Scene text, Visual question answering, Multi-modal learning, MSC, 41A05, 41A10, 65D05, 65D17

出版物

Volume 150, Issue -, Pages 242-249

出版商

Elsevier BV

发表日期

2021-07-20

DOI

10.1016/j.patrec.2021.06.026

参考文献

查看 1 条相关文献

联系作者

Discuss science. Find collaborators. Network.

Join a conversation

Explore over 38,000 international journals covering a vast array of academic fields.