Exploring coherence from heterogeneous representations for OCR image captioning
Crossref DOI link: https://doi.org/10.1007/s00530-024-01470-1
Published Online: 2024-09-06
Published Print: 2024-10
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Zhang, Yao
Song, Zijie
Hu, Zhenzhen
Text and Data Mining valid from 2024-09-06
Version of Record valid from 2024-09-06
Article History
Received: 10 July 2024
Accepted: 23 August 2024
First Online: 6 September 2024
Declarations
:
: The authors declare no competing interests.