.png){kind=icon}
返回
Multi-view semantic understanding for visual dialog
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2023.110427.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Visual dialog, as a challenging cross-media task, requires answering a sequence of questions based on a given image and dialog history. Hence the key problem becomes how to answer visually grounded questions based on ambiguous reference information from dialog. In this work, we propose a novel method called Multi-View Semantic Understanding for Visual Dialog (MVSU) to resolve the visual coreference resolution problem. The model consists of two main textual processing modules, SRR (Semantic Retention RNN) and CRoT (Coreference Resolution on Text). Specifically, the SRR module generates word features that have semantical meaning by considering contextual information. The CRoT module is from a textual perspective to divide all useful nouns and pronouns into different clusters that serve as the supplement of the detailed information for semantic understanding. In experiments, we demonstrate that MVSU enhances the ability to understand the semantical information on the VisDial v1.0 dataset.
Keyword:
Visual dialog
Cross-media
Reference information
Semantic understanding
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Learning Dual Encoding Model for Adaptive Visual Understanding in Visual Dialogue视觉对话中自适应视觉理解的学习双编码模型
PREAI
分享收藏Reduced ACTH, while normal β-endorphin CSF levels in early epileptic encephalopathies.png)
Peptides
PeptidesIF0
PREAI
分享收藏
查看更多内容