Low-shot transfer with attention for highly imbalanced cursive character recognition.

Jalali, Amin; Kavuri, Swathi; Lee, Minho

Jalali, Amin; Kavuri, Swathi; Lee, Minho.

Afiliación

Jalali A; School of Electronics and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea. Electronic address: max.jalali@gmail.com.
Kavuri S; School of Electronics and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea. Electronic address: swati.kavuri@gmail.com.
Lee M; School of Electronics and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea; Graduate School of Artificial Intelligence, Kyungpook National University, Daegu, 41566, South Korea. Electronic address: mholee@gmail.com.

Neural Netw ; 143: 489-499, 2021 Nov.

Article en En | MEDLINE | ID: mdl-34280608

Asunto(s)

Atención; Reconocimiento en Psicología

Palabras clave

Attention transfer learning; Decoupled -normalized classifier; Highly imbalanced data samples; Low-shot regularizer; Traditional cursive character recognition

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Atención / Reconocimiento en Psicología Tipo de estudio: Prognostic_studies Idioma: En Revista: Neural Netw Asunto de la revista: NEUROLOGIA Año: 2021 Tipo del documento: Article

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google