Search Result

1

基于全局与序列变分自编码的图像描述生成

Liu Mingming

Liu Hao

Wang Dong

Zhang Haiyan

image description generation

diverse image captioning

variational Transformer

latent embedding

No. 7, 2024 : 2215-2220 doi:10.19734/j.issn.1001-3695.2023.09.0510

2

基于跨模态多维关系增强的多模态模型研究

Cheng Xi

Yang Guan

Liu Xiaoming

Liu Yang

image description

visual question answering

feature diversification

spatial relationship

contextual semantic relationship

feature fusion

multimodal encoding

No. 8, 2023 : 2367-2374 doi:10.19734/j.issn.1001-3695.2022.11.0517

3

结合引导解码和视觉注意力的图像语义描述模型

Ma Kunyang

Lin Jinzhao

Pang Yu

image description

multiple instance learning

guide decoding

visual attention mechanism

No. 11, 2020 : 3504-3506,3515 doi:10.19734/j.issn.1001-3695.2019.06.0243