Visual descriptor extraction from patent figure captions: a case study of data efficiency between BiLSTM and transformer

Published in Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries, 2022

Recommended citation: Xin Wei, Jian Wu, Kehinde Ajayi, Diane Oyen. " Visual descriptor extraction from patent figure captions: a case study of data efficiency between BiLSTM and transformer." Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries, 2022.