Quantization-Based Adaptive Deep Image Compression Using Semantic Information

Deep image coding (DIC) for hybrid application contexts has recently attracted significant research interest because of its potential to support both human and machine visual tasks. Since the regions of interest (ROI) are different for different application contexts, it is important to design an ada...

ver descrição completa

Detalhes bibliográficos
Principais autores: Zhongyue Lei, Xuemin Hong, Jianghong Shi, Minxian Su, Chaoheng Lin, Wei Xia
Formato: Artigo
Idioma:English
Publicado em: IEEE 2023-01-01
coleção:IEEE Access
Assuntos:
Acesso em linha:https://ieeexplore.ieee.org/document/10290903/

Registros relacionados