An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
Abstract Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CR...
Guardado en:
Autores principales: | Pengfei Meng, Shuangcheng Jia, Qian Li |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/da4d000f1ad24142a21e258db08b060d |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
por: Muhammad Umair Ali, et al.
Publicado: (2021) -
ON-OFF receptive fields in auditory cortex diverge during development and contribute to directional sweep selectivity
por: Joseph Sollini, et al.
Publicado: (2018) -
Short term prediction of wind speed based on long-short term memory networks
por: Salman Umar T., et al.
Publicado: (2021) -
Invariance of visual operations at the level of receptive fields.
por: Tony Lindeberg
Publicado: (2013) -
Are there multiple visual short-term memory stores?
por: Ilja G Sligte, et al.
Publicado: (2008)